From 87c1880fee7a6975433a6b7283e3a942af51ea6c Mon Sep 17 00:00:00 2001 From: Archit Kumar <108719922+Archit-Kumar-16@users.noreply.github.com> Date: Wed, 21 Oct 2026 14:19:36 +0530 Subject: [PATCH 1/4] fix(pricing): add flex and ultrafast catalog prices Co-authored-by: Cursor --- .github/test/model.cue | 2 ++ providers/openai/gpt-5.6-luna.yaml | 33 ++++++++++++++++++ providers/openai/gpt-5.6-sol.yaml | 33 ++++++++++++++++++ providers/openai/gpt-5.6-terra.yaml | 33 ++++++++++++++++++ providers/openai/gpt-6-astra.yaml | 52 ++++++++++++++++++++++++++++ providers/openai/gpt-6-luna.yaml | 33 ++++++++++++++++++ providers/openai/gpt-6-sol.yaml | 33 ++++++++++++++++++ providers/openai/gpt-6.1-sol.yaml | 52 ++++++++++++++++++++++++++++ providers/openai/ra-gpt-5.6-sol.yaml | 33 ++++++++++++++++++ 9 files changed, 304 insertions(+) diff --git a/.github/test/model.cue b/.github/test/model.cue index ec5ee95424..7ab07b7a1d 100644 --- a/.github/test/model.cue +++ b/.github/test/model.cue @@ -179,6 +179,8 @@ package model region: "*" | #AWSRegion | #GCPRegion | #AzureRegion | #VertexRegion #Cost priority_pricing?: #Cost + flex_pricing?: #Cost + ultrafast_pricing?: #Cost } // Provider-specific configuration that cannot be expressed through the generic diff --git a/providers/openai/gpt-5.6-luna.yaml b/providers/openai/gpt-5.6-luna.yaml index 97f88b14b0..abdda09abe 100644 --- a/providers/openai/gpt-5.6-luna.yaml +++ b/providers/openai/gpt-5.6-luna.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 4e-8 input_cost_per_token: 4e-7 output_cost_per_token: 0.0000024 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 0.000001 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 0.0000036 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-sol.yaml b/providers/openai/gpt-5.6-sol.yaml index 64029923b8..c50921ba8b 100644 --- a/providers/openai/gpt-5.6-sol.yaml +++ b/providers/openai/gpt-5.6-sol.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 8e-7 input_cost_per_token: 0.000008 output_cost_per_token: 0.00004 + tiered_pricing: + cache_read: + - cost_per_token: 0.0000016 + from: 272000 + cache_write: + - cost_per_token: 0.00002 + from: 272000 + input: + - cost_per_token: 0.000016 + from: 272000 + output: + - cost_per_token: 0.00006 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.0000025 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 0.000002 + output_cost_per_token: 0.00001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 0.000005 + from: 272000 + input: + - cost_per_token: 0.000004 + from: 272000 + output: + - cost_per_token: 0.000015 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-terra.yaml b/providers/openai/gpt-5.6-terra.yaml index 6fc764cc91..7aa879f156 100644 --- a/providers/openai/gpt-5.6-terra.yaml +++ b/providers/openai/gpt-5.6-terra.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 4e-7 input_cost_per_token: 0.000004 output_cost_per_token: 0.000024 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 0.00001 + from: 272000 + input: + - cost_per_token: 0.000008 + from: 272000 + output: + - cost_per_token: 0.000036 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.00000125 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 0.000001 + output_cost_per_token: 0.000006 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 0.0000025 + from: 272000 + input: + - cost_per_token: 0.000002 + from: 272000 + output: + - cost_per_token: 0.000009 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-astra.yaml b/providers/openai/gpt-6-astra.yaml index 0248e042d5..8d88b9787a 100644 --- a/providers/openai/gpt-6-astra.yaml +++ b/providers/openai/gpt-6-astra.yaml @@ -10,6 +10,58 @@ costs: cache_read_input_token_cost: 0.000002 input_cost_per_token: 0.000020 output_cost_per_token: 0.000100 + tiered_pricing: + cache_read: + - cost_per_token: 0.000004 + from: 272000 + cache_write: + - cost_per_token: 0.00005 + from: 272000 + input: + - cost_per_token: 0.00004 + from: 272000 + output: + - cost_per_token: 0.00015 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.00000625 + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 0.000005 + output_cost_per_token: 0.000025 + tiered_pricing: + cache_read: + - cost_per_token: 0.000001 + from: 272000 + cache_write: + - cost_per_token: 0.0000125 + from: 272000 + input: + - cost_per_token: 0.00001 + from: 272000 + output: + - cost_per_token: 0.0000375 + from: 272000 + pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 0.000075 + cache_read_input_token_cost: 0.000006 + input_cost_per_token: 0.00006 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 0.000012 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-luna.yaml b/providers/openai/gpt-6-luna.yaml index 2d70f2bcd3..940d2a0077 100644 --- a/providers/openai/gpt-6-luna.yaml +++ b/providers/openai/gpt-6-luna.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 2e-8 input_cost_per_token: 2e-7 output_cost_per_token: 0.000001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-8 + from: 272000 + cache_write: + - cost_per_token: 5e-7 + from: 272000 + input: + - cost_per_token: 4e-7 + from: 272000 + output: + - cost_per_token: 0.0000015 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 6.25e-8 + cache_read_input_token_cost: 5e-9 + input_cost_per_token: 5e-8 + output_cost_per_token: 2.5e-7 + tiered_pricing: + cache_read: + - cost_per_token: 1e-8 + from: 272000 + cache_write: + - cost_per_token: 1.25e-7 + from: 272000 + input: + - cost_per_token: 1e-7 + from: 272000 + output: + - cost_per_token: 3.75e-7 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-sol.yaml b/providers/openai/gpt-6-sol.yaml index 5a3c0db28a..75cf44246d 100644 --- a/providers/openai/gpt-6-sol.yaml +++ b/providers/openai/gpt-6-sol.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 4e-7 input_cost_per_token: 0.000004 output_cost_per_token: 0.00002 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 0.00001 + from: 272000 + input: + - cost_per_token: 0.000008 + from: 272000 + output: + - cost_per_token: 0.00003 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.00000125 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 0.000001 + output_cost_per_token: 0.000005 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 0.0000025 + from: 272000 + input: + - cost_per_token: 0.000002 + from: 272000 + output: + - cost_per_token: 0.0000075 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6.1-sol.yaml b/providers/openai/gpt-6.1-sol.yaml index 8b6549e27b..e09ea905be 100644 --- a/providers/openai/gpt-6.1-sol.yaml +++ b/providers/openai/gpt-6.1-sol.yaml @@ -10,6 +10,58 @@ costs: cache_read_input_token_cost: 2e-7 input_cost_per_token: 0.000004 output_cost_per_token: 0.00002 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 0.00001 + from: 272000 + input: + - cost_per_token: 0.000008 + from: 272000 + output: + - cost_per_token: 0.00003 + from: 272000 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.00000125 + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 0.000001 + output_cost_per_token: 0.000005 + tiered_pricing: + cache_read: + - cost_per_token: 1e-7 + from: 272000 + cache_write: + - cost_per_token: 0.0000025 + from: 272000 + input: + - cost_per_token: 0.000002 + from: 272000 + output: + - cost_per_token: 0.0000075 + from: 272000 + pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 0.000015 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 0.000012 + output_cost_per_token: 0.00006 + tiered_pricing: + cache_read: + - cost_per_token: 0.0000012 + from: 272000 + cache_write: + - cost_per_token: 0.00003 + from: 272000 + input: + - cost_per_token: 0.000024 + from: 272000 + output: + - cost_per_token: 0.00009 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/ra-gpt-5.6-sol.yaml b/providers/openai/ra-gpt-5.6-sol.yaml index 2f2b67da51..01ad12461e 100644 --- a/providers/openai/ra-gpt-5.6-sol.yaml +++ b/providers/openai/ra-gpt-5.6-sol.yaml @@ -10,6 +10,39 @@ costs: cache_read_input_token_cost: 8e-7 input_cost_per_token: 0.000008 output_cost_per_token: 0.00004 + tiered_pricing: + cache_read: + - cost_per_token: 0.0000016 + from: 272001 + cache_write: + - cost_per_token: 0.00002 + from: 272001 + input: + - cost_per_token: 0.000016 + from: 272001 + output: + - cost_per_token: 0.00006 + from: 272001 + pricing_mode: cumulative + flex_pricing: + cache_creation_input_token_cost: 0.0000025 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 0.000002 + output_cost_per_token: 0.00001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272001 + cache_write: + - cost_per_token: 0.000005 + from: 272001 + input: + - cost_per_token: 0.000004 + from: 272001 + output: + - cost_per_token: 0.000015 + from: 272001 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: From 75d05147d217c2b6ca002c1a569f5d11b61d3d4c Mon Sep 17 00:00:00 2001 From: Archit Kumar <108719922+Archit-Kumar-16@users.noreply.github.com> Date: Wed, 21 Oct 2026 14:25:00 +0530 Subject: [PATCH 2/4] fix(pricing): sort flex and ultrafast YAML keys Co-authored-by: Cursor --- providers/openai/gpt-5.6-luna.yaml | 38 ++++++++--------- providers/openai/gpt-5.6-sol.yaml | 38 ++++++++--------- providers/openai/gpt-5.6-terra.yaml | 38 ++++++++--------- providers/openai/gpt-6-astra.yaml | 64 ++++++++++++++-------------- providers/openai/gpt-6-luna.yaml | 38 ++++++++--------- providers/openai/gpt-6-sol.yaml | 38 ++++++++--------- providers/openai/gpt-6.1-sol.yaml | 64 ++++++++++++++-------------- providers/openai/ra-gpt-5.6-sol.yaml | 38 ++++++++--------- 8 files changed, 178 insertions(+), 178 deletions(-) diff --git a/providers/openai/gpt-5.6-luna.yaml b/providers/openai/gpt-5.6-luna.yaml index abdda09abe..c3c0efb1ed 100644 --- a/providers/openai/gpt-5.6-luna.yaml +++ b/providers/openai/gpt-5.6-luna.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 output_cost_per_token: 0.0000012 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.0000036 from: 272000 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 1.25e-7 - cache_read_input_token_cost: 1e-8 - input_cost_per_token: 1e-7 - output_cost_per_token: 6e-7 - tiered_pricing: - cache_read: - - cost_per_token: 2e-8 - from: 272000 - cache_write: - - cost_per_token: 2.5e-7 - from: 272000 - input: - - cost_per_token: 2e-7 - from: 272000 - output: - - cost_per_token: 9e-7 - from: 272000 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-sol.yaml b/providers/openai/gpt-5.6-sol.yaml index c50921ba8b..790a2bc2a2 100644 --- a/providers/openai/gpt-5.6-sol.yaml +++ b/providers/openai/gpt-5.6-sol.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 0.000005 cache_read_input_token_cost: 4e-7 + flex_pricing: + cache_creation_input_token_cost: 0.0000025 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 0.000002 + output_cost_per_token: 0.00001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 0.000005 + from: 272000 + input: + - cost_per_token: 0.000004 + from: 272000 + output: + - cost_per_token: 0.000015 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 0.000004 input_cost_per_token_batches: 0.000002 output_cost_per_token: 0.00002 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.00006 from: 272000 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 0.0000025 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 - tiered_pricing: - cache_read: - - cost_per_token: 4e-7 - from: 272000 - cache_write: - - cost_per_token: 0.000005 - from: 272000 - input: - - cost_per_token: 0.000004 - from: 272000 - output: - - cost_per_token: 0.000015 - from: 272000 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-terra.yaml b/providers/openai/gpt-5.6-terra.yaml index 7aa879f156..cda50b9d99 100644 --- a/providers/openai/gpt-5.6-terra.yaml +++ b/providers/openai/gpt-5.6-terra.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 0.0000025 cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_creation_input_token_cost: 0.00000125 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 0.000001 + output_cost_per_token: 0.000006 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 0.0000025 + from: 272000 + input: + - cost_per_token: 0.000002 + from: 272000 + output: + - cost_per_token: 0.000009 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 0.000002 input_cost_per_token_batches: 0.000001 output_cost_per_token: 0.000012 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.000036 from: 272000 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 0.00000125 - cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000001 - output_cost_per_token: 0.000006 - tiered_pricing: - cache_read: - - cost_per_token: 2e-7 - from: 272000 - cache_write: - - cost_per_token: 0.0000025 - from: 272000 - input: - - cost_per_token: 0.000002 - from: 272000 - output: - - cost_per_token: 0.000009 - from: 272000 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-astra.yaml b/providers/openai/gpt-6-astra.yaml index 8d88b9787a..8ca034d453 100644 --- a/providers/openai/gpt-6-astra.yaml +++ b/providers/openai/gpt-6-astra.yaml @@ -1,29 +1,6 @@ costs: - cache_creation_input_token_cost: 0.0000125 cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.000010 - input_cost_per_token_batches: 0.000005 - output_cost_per_token: 0.000050 - output_cost_per_token_batches: 0.000025 - priority_pricing: - cache_creation_input_token_cost: 0.000025 - cache_read_input_token_cost: 0.000002 - input_cost_per_token: 0.000020 - output_cost_per_token: 0.000100 - tiered_pricing: - cache_read: - - cost_per_token: 0.000004 - from: 272000 - cache_write: - - cost_per_token: 0.00005 - from: 272000 - input: - - cost_per_token: 0.00004 - from: 272000 - output: - - cost_per_token: 0.00015 - from: 272000 - pricing_mode: cumulative flex_pricing: cache_creation_input_token_cost: 0.00000625 cache_read_input_token_cost: 5e-7 @@ -43,23 +20,27 @@ costs: - cost_per_token: 0.0000375 from: 272000 pricing_mode: cumulative - ultrafast_pricing: - cache_creation_input_token_cost: 0.000075 - cache_read_input_token_cost: 0.000006 - input_cost_per_token: 0.00006 - output_cost_per_token: 0.0003 + input_cost_per_token: 0.000010 + input_cost_per_token_batches: 0.000005 + output_cost_per_token: 0.000050 + output_cost_per_token_batches: 0.000025 + priority_pricing: + cache_creation_input_token_cost: 0.000025 + cache_read_input_token_cost: 0.000002 + input_cost_per_token: 0.000020 + output_cost_per_token: 0.000100 tiered_pricing: cache_read: - - cost_per_token: 0.000012 + - cost_per_token: 0.000004 from: 272000 cache_write: - - cost_per_token: 0.00015 + - cost_per_token: 0.00005 from: 272000 input: - - cost_per_token: 0.00012 + - cost_per_token: 0.00004 from: 272000 output: - - cost_per_token: 0.00045 + - cost_per_token: 0.00015 from: 272000 pricing_mode: cumulative region: "*" @@ -77,6 +58,25 @@ costs: - cost_per_token: 0.000075 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 0.000075 + cache_read_input_token_cost: 0.000006 + input_cost_per_token: 0.00006 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 0.000012 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative features: - function_calling - structured_output diff --git a/providers/openai/gpt-6-luna.yaml b/providers/openai/gpt-6-luna.yaml index 940d2a0077..9b0bfeb4c1 100644 --- a/providers/openai/gpt-6-luna.yaml +++ b/providers/openai/gpt-6-luna.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 1.25e-7 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_creation_input_token_cost: 6.25e-8 + cache_read_input_token_cost: 5e-9 + input_cost_per_token: 5e-8 + output_cost_per_token: 2.5e-7 + tiered_pricing: + cache_read: + - cost_per_token: 1e-8 + from: 272000 + cache_write: + - cost_per_token: 1.25e-7 + from: 272000 + input: + - cost_per_token: 1e-7 + from: 272000 + output: + - cost_per_token: 3.75e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 5e-7 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.0000015 from: 272000 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 6.25e-8 - cache_read_input_token_cost: 5e-9 - input_cost_per_token: 5e-8 - output_cost_per_token: 2.5e-7 - tiered_pricing: - cache_read: - - cost_per_token: 1e-8 - from: 272000 - cache_write: - - cost_per_token: 1.25e-7 - from: 272000 - input: - - cost_per_token: 1e-7 - from: 272000 - output: - - cost_per_token: 3.75e-7 - from: 272000 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-sol.yaml b/providers/openai/gpt-6-sol.yaml index 75cf44246d..f427b646db 100644 --- a/providers/openai/gpt-6-sol.yaml +++ b/providers/openai/gpt-6-sol.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 0.0000025 cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_creation_input_token_cost: 0.00000125 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 0.000001 + output_cost_per_token: 0.000005 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 0.0000025 + from: 272000 + input: + - cost_per_token: 0.000002 + from: 272000 + output: + - cost_per_token: 0.0000075 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 0.000002 input_cost_per_token_batches: 0.000001 output_cost_per_token: 0.00001 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.00003 from: 272000 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 0.00000125 - cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000001 - output_cost_per_token: 0.000005 - tiered_pricing: - cache_read: - - cost_per_token: 2e-7 - from: 272000 - cache_write: - - cost_per_token: 0.0000025 - from: 272000 - input: - - cost_per_token: 0.000002 - from: 272000 - output: - - cost_per_token: 0.0000075 - from: 272000 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6.1-sol.yaml b/providers/openai/gpt-6.1-sol.yaml index e09ea905be..4856bf680f 100644 --- a/providers/openai/gpt-6.1-sol.yaml +++ b/providers/openai/gpt-6.1-sol.yaml @@ -1,29 +1,6 @@ costs: - cache_creation_input_token_cost: 0.0000025 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 - priority_pricing: - cache_creation_input_token_cost: 0.000005 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000004 - output_cost_per_token: 0.00002 - tiered_pricing: - cache_read: - - cost_per_token: 4e-7 - from: 272000 - cache_write: - - cost_per_token: 0.00001 - from: 272000 - input: - - cost_per_token: 0.000008 - from: 272000 - output: - - cost_per_token: 0.00003 - from: 272000 - pricing_mode: cumulative flex_pricing: cache_creation_input_token_cost: 0.00000125 cache_read_input_token_cost: 5e-8 @@ -43,23 +20,27 @@ costs: - cost_per_token: 0.0000075 from: 272000 pricing_mode: cumulative - ultrafast_pricing: - cache_creation_input_token_cost: 0.000015 - cache_read_input_token_cost: 6e-7 - input_cost_per_token: 0.000012 - output_cost_per_token: 0.00006 + input_cost_per_token: 0.000002 + input_cost_per_token_batches: 0.000001 + output_cost_per_token: 0.00001 + output_cost_per_token_batches: 0.000005 + priority_pricing: + cache_creation_input_token_cost: 0.000005 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 0.000004 + output_cost_per_token: 0.00002 tiered_pricing: cache_read: - - cost_per_token: 0.0000012 + - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.00003 + - cost_per_token: 0.00001 from: 272000 input: - - cost_per_token: 0.000024 + - cost_per_token: 0.000008 from: 272000 output: - - cost_per_token: 0.00009 + - cost_per_token: 0.00003 from: 272000 pricing_mode: cumulative region: "*" @@ -77,6 +58,25 @@ costs: - cost_per_token: 0.000015 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 0.000015 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 0.000012 + output_cost_per_token: 0.00006 + tiered_pricing: + cache_read: + - cost_per_token: 0.0000012 + from: 272000 + cache_write: + - cost_per_token: 0.00003 + from: 272000 + input: + - cost_per_token: 0.000024 + from: 272000 + output: + - cost_per_token: 0.00009 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling diff --git a/providers/openai/ra-gpt-5.6-sol.yaml b/providers/openai/ra-gpt-5.6-sol.yaml index 01ad12461e..0a8ec12857 100644 --- a/providers/openai/ra-gpt-5.6-sol.yaml +++ b/providers/openai/ra-gpt-5.6-sol.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 0.000005 cache_read_input_token_cost: 4e-7 + flex_pricing: + cache_creation_input_token_cost: 0.0000025 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 0.000002 + output_cost_per_token: 0.00001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272001 + cache_write: + - cost_per_token: 0.000005 + from: 272001 + input: + - cost_per_token: 0.000004 + from: 272001 + output: + - cost_per_token: 0.000015 + from: 272001 + pricing_mode: cumulative input_cost_per_token: 0.000004 input_cost_per_token_batches: 0.000002 output_cost_per_token: 0.00002 @@ -24,25 +43,6 @@ costs: - cost_per_token: 0.00006 from: 272001 pricing_mode: cumulative - flex_pricing: - cache_creation_input_token_cost: 0.0000025 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 - tiered_pricing: - cache_read: - - cost_per_token: 4e-7 - from: 272001 - cache_write: - - cost_per_token: 0.000005 - from: 272001 - input: - - cost_per_token: 0.000004 - from: 272001 - output: - - cost_per_token: 0.000015 - from: 272001 - pricing_mode: cumulative region: "*" tiered_pricing: cache_read: From 88a1dd6838ee83575320503a0e033732f06f8b5c Mon Sep 17 00:00:00 2001 From: Archit Kumar <108719922+Archit-Kumar-16@users.noreply.github.com> Date: Wed, 21 Oct 2026 16:54:11 +0530 Subject: [PATCH 3/4] fix(pricing): add flex, priority, and ultrafast overlays for other providers Co-authored-by: Cursor --- .../aws-bedrock-mantle/deepseek.v3.1.yaml | 109 +- .../google.gemma-4-26b-a4b.yaml | 32 +- .../google.gemma-4-31b.yaml | 32 +- .../google.gemma-4-e2b.yaml | 32 +- .../moonshotai.kimi-k2-thinking.yaml | 108 +- .../openai.gpt-6-astra.yaml | 70 +- .../openai.gpt-6.1-sol.yaml | 31 +- .../openai.gpt-oss-120b.yaml | 120 ++- .../openai.gpt-oss-20b.yaml | 104 +- .../openai.gpt-oss-safeguard-120b.yaml | 112 +- .../openai.gpt-oss-safeguard-20b.yaml | 112 +- .../qwen.qwen3-235b-a22b-2507.yaml | 112 +- .../aws-bedrock-mantle/qwen.qwen3-32b.yaml | 112 +- .../qwen.qwen3-coder-30b-a3b-instruct.yaml | 112 +- .../qwen.qwen3-coder-480b-a35b-instruct.yaml | 88 +- .../qwen.qwen3-next-80b-a3b-instruct.yaml | 130 ++- .../qwen.qwen3-vl-235b-a22b-instruct.yaml | 130 ++- .../aws-bedrock-mantle/xai.grok-4.3.yaml | 48 +- .../aws-bedrock-mantle/xai.grok-4.6.yaml | 24 +- .../aws-bedrock/amazon.nova-pro-v1:0.yaml | 280 ++++- .../apac.amazon.nova-pro-v1:0.yaml | 68 +- providers/aws-bedrock/deepseek.v3.2.yaml | 106 +- .../aws-bedrock/eu.amazon.nova-pro-v1:0.yaml | 60 +- .../global.amazon.nova-2-lite-v1:0.yaml | 156 ++- .../global.moonshotai.kimi-k3.yaml | 576 ++++++++--- .../global.openai.gpt-6-astra.yaml | 595 ++++++++--- .../global.openai.gpt-6.1-sol.yaml | 961 ++++++++++++++---- .../aws-bedrock/global.xai.grok-4.6.yaml | 384 +++++-- .../aws-bedrock/global.xai.grok-4.7.yaml | 240 +++++ providers/aws-bedrock/global.zai.glm-5.3.yaml | 496 +++++++-- .../aws-bedrock/google.gemma-3-12b-it.yaml | 88 +- .../aws-bedrock/google.gemma-3-27b-it.yaml | 88 +- .../aws-bedrock/google.gemma-3-4b-it.yaml | 88 +- .../aws-bedrock/in.moonshotai.kimi-k3.yaml | 24 +- .../jp.amazon.nova-2-lite-v1:0.yaml | 8 + .../aws-bedrock/minimax.minimax-m2.1.yaml | 130 ++- .../aws-bedrock/minimax.minimax-m2.5.yaml | 104 +- providers/aws-bedrock/minimax.minimax-m2.yaml | 138 ++- .../aws-bedrock/mistral.devstral-2-123b.yaml | 130 ++- .../mistral.magistral-small-2509.yaml | 100 +- .../mistral.ministral-3-14b-instruct.yaml | 104 +- .../mistral.ministral-3-3b-instruct.yaml | 104 +- .../mistral.ministral-3-8b-instruct.yaml | 104 +- ...mistral.mistral-large-3-675b-instruct.yaml | 80 +- .../mistral.voxtral-mini-3b-2507.yaml | 80 +- .../mistral.voxtral-small-24b-2507.yaml | 80 +- .../moonshot.kimi-k2-thinking.yaml | 45 +- .../aws-bedrock/moonshotai.kimi-k2.5.yaml | 100 +- .../nvidia.nemotron-nano-12b-v2.yaml | 112 +- .../nvidia.nemotron-nano-3-30b.yaml | 112 +- .../nvidia.nemotron-nano-9b-v2.yaml | 88 +- .../nvidia.nemotron-super-3-120b.yaml | 90 +- .../aws-bedrock/openai.gpt-oss-120b-1:0.yaml | 104 +- .../aws-bedrock/openai.gpt-oss-20b-1:0.yaml | 104 +- .../openai.gpt-oss-safeguard-120b.yaml | 80 +- .../openai.gpt-oss-safeguard-20b.yaml | 80 +- .../qwen.qwen3-235b-a22b-2507-v1:0.yaml | 60 +- .../aws-bedrock/qwen.qwen3-32b-v1:0.yaml | 104 +- .../qwen.qwen3-coder-30b-a3b-v1:0.yaml | 39 + .../aws-bedrock/qwen.qwen3-coder-next.yaml | 130 ++- .../aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml | 50 +- .../us.amazon.nova-2-lite-v1:0.yaml | 60 +- .../aws-bedrock/us.amazon.nova-pro-v1:0.yaml | 42 +- .../aws-bedrock/us.moonshotai.kimi-k3.yaml | 96 +- .../aws-bedrock/us.openai.gpt-6-astra.yaml | 210 +++- .../aws-bedrock/us.openai.gpt-6.1-sol.yaml | 186 +++- providers/aws-bedrock/us.xai.grok-4.6.yaml | 48 +- providers/aws-bedrock/us.xai.grok-4.7.yaml | 72 +- providers/aws-bedrock/us.zai.glm-5.3.yaml | 40 + .../aws-bedrock/writer.palmyra-vision-7b.yaml | 112 +- providers/aws-bedrock/zai.glm-4.7-flash.yaml | 104 +- providers/aws-bedrock/zai.glm-4.7.yaml | 100 +- providers/aws-bedrock/zai.glm-5.yaml | 77 +- .../azure-open-ai/gpt-4.1-2025-04-14.yaml | 8 + .../gpt-4.1-mini-2025-04-14.yaml | 8 + providers/azure-open-ai/gpt-4.1-mini.yaml | 8 + providers/azure-open-ai/gpt-4.1.yaml | 12 + providers/azure-open-ai/gpt-5-2025-08-07.yaml | 30 +- .../azure-open-ai/gpt-5-mini-2025-08-07.yaml | 32 +- providers/azure-open-ai/gpt-5-mini.yaml | 32 +- .../azure-open-ai/gpt-5.1-2025-11-13.yaml | 40 +- .../gpt-5.1-codex-2025-11-13.yaml | 32 +- .../gpt-5.1-codex-mini-2025-11-13.yaml | 24 +- providers/azure-open-ai/gpt-5.1.yaml | 40 +- .../azure-open-ai/gpt-5.2-2025-12-11.yaml | 30 +- providers/azure-open-ai/gpt-5.2.yaml | 30 +- providers/azure-open-ai/gpt-5.3-codex.yaml | 12 + .../azure-open-ai/gpt-5.4-2026-03-05.yaml | 123 ++- .../gpt-5.4-mini-2026-03-17.yaml | 36 +- providers/azure-open-ai/gpt-5.4-mini.yaml | 24 + .../gpt-5.4-nano-2026-03-17.yaml | 18 +- providers/azure-open-ai/gpt-5.4-nano.yaml | 12 + .../azure-open-ai/gpt-5.4-pro-2026-03-05.yaml | 23 +- providers/azure-open-ai/gpt-5.4-pro.yaml | 61 +- providers/azure-open-ai/gpt-5.4.yaml | 87 ++ .../azure-open-ai/gpt-5.5-2026-04-24.yaml | 69 ++ providers/azure-open-ai/gpt-5.5.yaml | 69 ++ .../gpt-5.6-luna-2026-07-09.yaml | 126 ++- providers/azure-open-ai/gpt-5.6-luna.yaml | 114 +++ .../azure-open-ai/gpt-5.6-sol-2026-07-09.yaml | 150 ++- providers/azure-open-ai/gpt-5.6-sol.yaml | 114 +++ .../gpt-5.6-terra-2026-07-09.yaml | 150 ++- providers/azure-open-ai/gpt-5.6-terra.yaml | 114 +++ providers/azure-open-ai/gpt-5.yaml | 30 +- .../azure-open-ai/gpt-6-sol-2026-09-22.yaml | 93 +- providers/azure-open-ai/gpt-6-sol.yaml | 93 +- .../google-gemini/gemini-2.5-flash-image.yaml | 4 + .../google-gemini/gemini-2.5-flash-lite.yaml | 11 +- providers/google-gemini/gemini-2.5-flash.yaml | 17 +- providers/google-gemini/gemini-2.5-pro.yaml | 31 +- .../google-gemini/gemini-3-flash-preview.yaml | 17 +- .../gemini-3-pro-image-preview.yaml | 8 +- .../google-gemini/gemini-3-pro-image.yaml | 14 +- .../gemini-3.1-flash-lite-preview.yaml | 8 + .../google-gemini/gemini-3.1-flash-lite.yaml | 13 +- .../gemini-3.1-pro-preview-customtools.yaml | 33 +- .../google-gemini/gemini-3.1-pro-preview.yaml | 33 +- .../google-gemini/gemini-3.5-flash-lite.yaml | 8 + providers/google-gemini/gemini-3.5-flash.yaml | 17 +- providers/google-gemini/gemini-3.6-flash.yaml | 8 + providers/google-gemini/gemini-3.7-flash.yaml | 12 +- .../gemini-3.8-flash-lite-tts.yaml | 12 +- .../google-gemini/gemini-3.8-flash-tts.yaml | 12 +- providers/google-gemini/gemini-3.8-flash.yaml | 12 +- .../google-gemini/gemini-flash-latest.yaml | 12 +- .../gemini-flash-lite-latest.yaml | 10 +- .../google-gemini/gemini-pro-latest.yaml | 33 +- .../nano-banana-pro-preview.yaml | 8 +- .../google-vertex/gemini-2.5-flash-image.yaml | 70 +- .../google-vertex/gemini-2.5-flash-lite.yaml | 135 +++ providers/google-vertex/gemini-2.5-flash.yaml | 408 ++++++-- providers/google-vertex/gemini-2.5-pro.yaml | 527 ++++++++-- .../google-vertex/gemini-3-flash-preview.yaml | 16 +- .../gemini-3-pro-image-preview.yaml | 23 +- .../google-vertex/gemini-3-pro-preview.yaml | 810 +++++++++++---- .../google-vertex/gemini-3.1-pro-preview.yaml | 32 +- providers/google-vertex/gemini-3.5-flash.yaml | 102 +- providers/google-vertex/gemini-3.6-flash.yaml | 8 + .../google/gemini-2.5-flash-image.yaml | 70 +- .../google/gemini-2.5-flash-lite.yaml | 135 +++ .../google/gemini-2.5-flash.yaml | 17 +- .../google-vertex/google/gemini-2.5-pro.yaml | 527 ++++++++-- .../google/gemini-3-flash-preview.yaml | 16 +- .../google/gemini-3-pro-image-preview.yaml | 15 + .../google/gemini-3-pro-image.yaml | 27 +- .../google/gemini-3.1-flash-image.yaml | 44 +- .../google/gemini-3.1-flash-lite-image.yaml | 14 +- .../google/gemini-3.1-flash-lite.yaml | 39 +- .../google/gemini-3.1-pro-preview.yaml | 32 +- .../google/gemini-3.5-flash-lite.yaml | 24 + .../google/gemini-3.5-flash.yaml | 119 ++- .../google/gemini-3.6-flash.yaml | 24 + .../google/gemini-3.7-flash.yaml | 24 + .../google/gemini-3.8-flash.yaml | 24 + .../google-vertex/google/gemini-4-argon.yaml | 63 +- .../google/gemini-nano-banana-2.1.yaml | 4 + .../microsoft-foundry/gpt-4.1-2025-04-14.yaml | 8 + .../gpt-4.1-mini-2025-04-14.yaml | 8 + providers/microsoft-foundry/gpt-4.1-mini.yaml | 8 + providers/microsoft-foundry/gpt-4.1.yaml | 12 + .../microsoft-foundry/gpt-5-2025-08-07.yaml | 30 +- .../gpt-5-mini-2025-08-07.yaml | 32 +- providers/microsoft-foundry/gpt-5-mini.yaml | 32 +- .../microsoft-foundry/gpt-5.1-2025-11-13.yaml | 40 +- .../gpt-5.1-codex-2025-11-13.yaml | 32 +- .../gpt-5.1-codex-mini-2025-11-13.yaml | 24 +- providers/microsoft-foundry/gpt-5.1.yaml | 40 +- .../microsoft-foundry/gpt-5.2-2025-12-11.yaml | 10 +- providers/microsoft-foundry/gpt-5.2.yaml | 30 +- .../microsoft-foundry/gpt-5.3-codex.yaml | 12 + .../microsoft-foundry/gpt-5.4-2026-03-05.yaml | 103 +- .../gpt-5.4-mini-2026-03-17.yaml | 36 +- providers/microsoft-foundry/gpt-5.4-mini.yaml | 8 + .../gpt-5.4-nano-2026-03-17.yaml | 18 +- providers/microsoft-foundry/gpt-5.4-nano.yaml | 4 + .../gpt-5.4-pro-2026-03-05.yaml | 19 +- providers/microsoft-foundry/gpt-5.4-pro.yaml | 19 +- providers/microsoft-foundry/gpt-5.4.yaml | 87 ++ .../microsoft-foundry/gpt-5.5-2026-04-24.yaml | 69 ++ providers/microsoft-foundry/gpt-5.5.yaml | 69 ++ .../gpt-5.6-luna-2026-07-09.yaml | 126 ++- providers/microsoft-foundry/gpt-5.6-luna.yaml | 152 +++ .../gpt-5.6-sol-2026-07-09.yaml | 114 +++ providers/microsoft-foundry/gpt-5.6-sol.yaml | 114 +++ .../gpt-5.6-terra-2026-07-09.yaml | 150 ++- .../microsoft-foundry/gpt-5.6-terra.yaml | 114 +++ providers/microsoft-foundry/gpt-5.yaml | 30 +- .../gpt-6-sol-2026-09-22.yaml | 124 ++- providers/microsoft-foundry/gpt-6-sol.yaml | 124 ++- .../truefoundry-managed/gpt-6-astra.yaml | 74 +- providers/truefoundry-managed/gpt-6-luna.yaml | 35 +- .../truefoundry-managed/gpt-6.1-sol.yaml | 52 + 192 files changed, 14225 insertions(+), 2695 deletions(-) diff --git a/providers/aws-bedrock-mantle/deepseek.v3.1.yaml b/providers/aws-bedrock-mantle/deepseek.v3.1.yaml index 48951fff48..156216941e 100644 --- a/providers/aws-bedrock-mantle/deepseek.v3.1.yaml +++ b/providers/aws-bedrock-mantle/deepseek.v3.1.yaml @@ -1,35 +1,100 @@ costs: - - input_cost_per_token: 5.8e-7 - output_cost_per_token: 0.00000168 + - flex_pricing: + input_cost_per_token: 2.9e-7 + output_cost_per_token: 8.4e-7 + input_cost_per_token: 5.8e-7 + output_cost_per_token: 1.68e-6 + priority_pricing: + input_cost_per_token: 1.015e-6 + output_cost_per_token: 2.94e-6 region: us-west-2 - - input_cost_per_token: 5.8e-7 - output_cost_per_token: 0.00000168 + - flex_pricing: + input_cost_per_token: 2.9e-7 + output_cost_per_token: 8.4e-7 + input_cost_per_token: 5.8e-7 + output_cost_per_token: 1.68e-6 + priority_pricing: + input_cost_per_token: 1.015e-6 + output_cost_per_token: 2.94e-6 region: us-east-2 - - input_cost_per_token: 5.8e-7 - output_cost_per_token: 0.00000168 + - flex_pricing: + input_cost_per_token: 2.9e-7 + output_cost_per_token: 8.4e-7 + input_cost_per_token: 5.8e-7 + output_cost_per_token: 1.68e-6 + priority_pricing: + input_cost_per_token: 1.015e-6 + output_cost_per_token: 2.94e-6 region: us-east-1 - - input_cost_per_token: 6.96e-7 - output_cost_per_token: 0.000002016 + - flex_pricing: + input_cost_per_token: 3.48e-7 + output_cost_per_token: 1.008e-6 + input_cost_per_token: 6.96e-7 + output_cost_per_token: 2.016e-6 + priority_pricing: + input_cost_per_token: 1.218e-6 + output_cost_per_token: 3.528e-6 region: sa-east-1 - - input_cost_per_token: 8.99985e-7 - output_cost_per_token: 0.000002606853 + - flex_pricing: + input_cost_per_token: 4.499925e-7 + output_cost_per_token: 1.30342655172414e-6 + input_cost_per_token: 8.99985e-7 + output_cost_per_token: 2.606853e-6 + priority_pricing: + input_cost_per_token: 1.57497375e-6 + output_cost_per_token: 4.56199293103448e-6 region: eu-west-2 - - input_cost_per_token: 5.8e-7 - output_cost_per_token: 0.00000168 + - flex_pricing: + input_cost_per_token: 2.9e-7 + output_cost_per_token: 8.4e-7 + input_cost_per_token: 5.8e-7 + output_cost_per_token: 1.68e-6 + priority_pricing: + input_cost_per_token: 1.015e-6 + output_cost_per_token: 2.94e-6 region: eu-north-1 - - region: ap-southeast-4 - # not found in official docs — V3.1 pricing not published for this region - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000174 + - flex_pricing: + input_cost_per_token: 2.9e-7 + output_cost_per_token: 8.4e-7 + priority_pricing: + input_cost_per_token: 1.015e-6 + output_cost_per_token: 2.94e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 8.68965517241379e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.74e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 3.04137931034483e-6 region: ap-southeast-3 - - input_cost_per_token: 5.974e-7 - output_cost_per_token: 0.0000017304 + - flex_pricing: + input_cost_per_token: 2.987e-7 + output_cost_per_token: 8.652e-7 + input_cost_per_token: 5.974e-7 + output_cost_per_token: 1.7304e-6 + priority_pricing: + input_cost_per_token: 1.04545e-6 + output_cost_per_token: 3.0282e-6 region: ap-southeast-2 - - input_cost_per_token: 6.82424e-7 - output_cost_per_token: 0.000001976678 + - flex_pricing: + input_cost_per_token: 3.41212e-7 + output_cost_per_token: 9.88338206896552e-7 + input_cost_per_token: 6.82424e-7 + output_cost_per_token: 1.976678e-6 + priority_pricing: + input_cost_per_token: 1.194242e-6 + output_cost_per_token: 3.45918372413793e-6 region: ap-south-1 - - input_cost_per_token: 7.01666e-7 - output_cost_per_token: 0.000002032411 + - flex_pricing: + input_cost_per_token: 3.50833e-7 + output_cost_per_token: 1.01620593103448e-6 + input_cost_per_token: 7.01666e-7 + output_cost_per_token: 2.032411e-6 + priority_pricing: + input_cost_per_token: 1.2279155e-6 + output_cost_per_token: 3.55672075862069e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml b/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml index 7467bdc78a..7dca58b369 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml @@ -1,15 +1,39 @@ costs: - - input_cost_per_token: 1.3e-7 + - flex_pricing: + input_cost_per_token: 6.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.3e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.275e-7 + output_cost_per_token: 7e-7 region: us-west-2 - - input_cost_per_token: 1.3e-7 + - flex_pricing: + input_cost_per_token: 6.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.3e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.275e-7 + output_cost_per_token: 7e-7 region: us-east-2 - - input_cost_per_token: 1.3e-7 + - flex_pricing: + input_cost_per_token: 6.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.3e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.275e-7 + output_cost_per_token: 7e-7 region: us-east-1 - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 2.46153846153846e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 8.61538461538462e-7 region: eu-central-1 extra_configuration: bedrock_mantle_adhoc_prefix: /openai diff --git a/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml b/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml index 67de176f3a..9169740d81 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml @@ -1,15 +1,39 @@ costs: - - input_cost_per_token: 1.4e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.4e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.45e-7 + output_cost_per_token: 7e-7 region: us-west-2 - - input_cost_per_token: 1.4e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.4e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.45e-7 + output_cost_per_token: 7e-7 region: us-east-2 - - input_cost_per_token: 1.4e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 1.4e-7 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 2.45e-7 + output_cost_per_token: 7e-7 region: us-east-1 - - input_cost_per_token: 1.68e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 2.4e-7 + input_cost_per_token: 1.68e-7 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 2.94e-7 + output_cost_per_token: 8.4e-7 region: eu-central-1 extra_configuration: bedrock_mantle_adhoc_prefix: /openai diff --git a/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml b/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml index a1ec7e6c81..c856d39f08 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml @@ -1,15 +1,39 @@ costs: - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-west-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-east-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-east-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: eu-central-1 extra_configuration: bedrock_mantle_adhoc_prefix: /openai diff --git a/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml b/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml index 749782d1a1..31a38ddbb5 100644 --- a/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml +++ b/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml @@ -1,34 +1,100 @@ costs: - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-west-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-east-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-east-1 - - input_cost_per_token: 7.3e-7 - output_cost_per_token: 0.00000303 + - flex_pricing: + input_cost_per_token: 3.65e-7 + output_cost_per_token: 1.52083333333333e-6 + input_cost_per_token: 7.3e-7 + output_cost_per_token: 3.03e-6 + priority_pricing: + input_cost_per_token: 1.2775e-6 + output_cost_per_token: 5.329e-6 region: sa-east-1 - - input_cost_per_token: 9.3e-7 - output_cost_per_token: 0.000003875 + - flex_pricing: + input_cost_per_token: 4.65e-7 + output_cost_per_token: 1.9375e-6 + input_cost_per_token: 9.3e-7 + output_cost_per_token: 3.875e-6 + priority_pricing: + input_cost_per_token: 1.6275e-6 + output_cost_per_token: 6.789e-6 region: eu-west-2 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.000003 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 5.256e-6 region: eu-north-1 - - region: ap-southeast-4 # pricing not yet published on AWS Bedrock pricing page - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.000003 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.25e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 5.256e-6 region: ap-southeast-3 - - input_cost_per_token: 6.18e-7 - output_cost_per_token: 0.000002575 + - flex_pricing: + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.2875e-6 + input_cost_per_token: 6.18e-7 + output_cost_per_token: 2.575e-6 + priority_pricing: + input_cost_per_token: 1.0815e-6 + output_cost_per_token: 4.5114e-6 region: ap-southeast-2 - - input_cost_per_token: 7.1e-7 - output_cost_per_token: 0.00000294 + - flex_pricing: + input_cost_per_token: 3.55e-7 + output_cost_per_token: 1.47916666666667e-6 + input_cost_per_token: 7.1e-7 + output_cost_per_token: 2.94e-6 + priority_pricing: + input_cost_per_token: 1.2425e-6 + output_cost_per_token: 5.183e-6 region: ap-south-1 - - input_cost_per_token: 7.3e-7 - output_cost_per_token: 0.00000303 + - flex_pricing: + input_cost_per_token: 3.65e-7 + output_cost_per_token: 1.52083333333333e-6 + input_cost_per_token: 7.3e-7 + output_cost_per_token: 3.03e-6 + priority_pricing: + input_cost_per_token: 1.2775e-6 + output_cost_per_token: 5.329e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml b/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml index 6bcc2148ed..41da77138d 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml @@ -1,42 +1,80 @@ costs: - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-west-2 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-east-1 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative extra_configuration: bedrock_mantle_adhoc_prefix: /openai features: diff --git a/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml b/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml index adeecf52df..40318eede3 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml @@ -1,23 +1,42 @@ costs: - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: us-east-1 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative extra_configuration: bedrock_mantle_adhoc_prefix: /openai features: diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml index 73d29fe99b..961f650661 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml @@ -1,48 +1,138 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.2e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: us-gov-west-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 3.2e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 input_cost_per_token_batches: 7.73e-8 output_cost_per_token: 6.18e-7 output_cost_per_token_batches: 3.09e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml index 6cc35eceff..b76f761263 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml @@ -1,44 +1,122 @@ costs: - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-east-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-east-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: sa-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 5.5e-8 + output_cost_per_token: 2.35714285714286e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 4.7e-7 + priority_pricing: + input_cost_per_token: 1.925e-7 + output_cost_per_token: 8.25e-7 region: eu-west-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: eu-west-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.92857142857143e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.575e-7 + output_cost_per_token: 6.75e-7 region: eu-south-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: eu-north-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.92857142857143e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.575e-7 + output_cost_per_token: 6.75e-7 region: eu-central-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3.1e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: ap-southeast-3 - - input_cost_per_token: 7.21e-8 + - flex_pricing: + input_cost_per_token: 3.605e-8 + output_cost_per_token: 1.545e-7 + input_cost_per_token: 7.21e-8 input_cost_per_token_batches: 3.61e-8 output_cost_per_token: 3.09e-7 output_cost_per_token_batches: 1.545e-7 + priority_pricing: + input_cost_per_token: 1.26175e-7 + output_cost_per_token: 5.4075e-7 region: ap-southeast-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: ap-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml index a50c18b837..21b3cb8e9e 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml @@ -1,43 +1,127 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.07333333333333e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 3.98666666666667e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.2e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-north-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.2e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-central-1 - - region: ap-southeast-4 # pricing not published on AWS Bedrock pricing page - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.2e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.21e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.678e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml index d6d7ea0944..b9081fa967 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml @@ -1,43 +1,127 @@ costs: - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-east-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-east-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: sa-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 4.71428571428571e-8 + output_cost_per_token: 1.57142857142857e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.1e-7 + priority_pricing: + input_cost_per_token: 1.88571428571429e-7 + output_cost_per_token: 5.5e-7 region: eu-west-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: eu-west-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: eu-south-1 - - input_cost_per_token: 8.4e-8 + - flex_pricing: + input_cost_per_token: 3.6e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 8.4e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.44e-7 + output_cost_per_token: 4.2e-7 region: eu-north-1 - - input_cost_per_token: 8.4e-8 + - flex_pricing: + input_cost_per_token: 3.6e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 8.4e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.44e-7 + output_cost_per_token: 4.2e-7 region: eu-central-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: ap-southeast-3 - - input_cost_per_token: 7.21e-8 + - flex_pricing: + input_cost_per_token: 3.09e-8 + output_cost_per_token: 1.03e-7 + input_cost_per_token: 7.21e-8 output_cost_per_token: 2.06e-7 + priority_pricing: + input_cost_per_token: 1.236e-7 + output_cost_per_token: 3.605e-7 region: ap-southeast-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: ap-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml index 37da3d1847..0de6dff846 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml @@ -1,43 +1,127 @@ costs: - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 + priority_pricing: + input_cost_per_token: 3.85e-7 + output_cost_per_token: 1.54e-6 region: us-west-2 - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 + priority_pricing: + input_cost_per_token: 3.85e-7 + output_cost_per_token: 1.54e-6 region: us-east-2 - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 + priority_pricing: + input_cost_per_token: 3.85e-7 + output_cost_per_token: 1.54e-6 region: us-east-1 - - input_cost_per_token: 2.64e-7 + - flex_pricing: + input_cost_per_token: 1.32e-7 + output_cost_per_token: 5.28e-7 + input_cost_per_token: 2.64e-7 output_cost_per_token: 1.056e-6 + priority_pricing: + input_cost_per_token: 4.62e-7 + output_cost_per_token: 1.848e-6 region: sa-east-1 - - input_cost_per_token: 3.4e-7 + - flex_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 6.8e-7 + input_cost_per_token: 3.4e-7 output_cost_per_token: 1.37e-6 + priority_pricing: + input_cost_per_token: 5.95e-7 + output_cost_per_token: 2.38e-6 region: eu-west-2 - - input_cost_per_token: 2.64e-7 + - flex_pricing: + input_cost_per_token: 1.32e-7 + output_cost_per_token: 5.28e-7 + input_cost_per_token: 2.64e-7 output_cost_per_token: 1.056e-6 + priority_pricing: + input_cost_per_token: 4.62e-7 + output_cost_per_token: 1.848e-6 region: eu-west-1 - - input_cost_per_token: 2.9e-7 + - flex_pricing: + input_cost_per_token: 1.45e-7 + output_cost_per_token: 5.8e-7 + input_cost_per_token: 2.9e-7 output_cost_per_token: 1.16e-6 + priority_pricing: + input_cost_per_token: 5.075e-7 + output_cost_per_token: 2.03e-6 region: eu-south-1 - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 + priority_pricing: + input_cost_per_token: 3.85e-7 + output_cost_per_token: 1.54e-6 region: eu-north-1 - - input_cost_per_token: 2.9e-7 + - flex_pricing: + input_cost_per_token: 1.45e-7 + output_cost_per_token: 5.8e-7 + input_cost_per_token: 2.9e-7 output_cost_per_token: 1.16e-6 + priority_pricing: + input_cost_per_token: 5.075e-7 + output_cost_per_token: 2.03e-6 region: eu-central-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + priority_pricing: + input_cost_per_token: 3.85e-7 + output_cost_per_token: 1.54e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.1e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: ap-southeast-3 - - input_cost_per_token: 2.266e-7 + - flex_pricing: + input_cost_per_token: 1.133e-7 + output_cost_per_token: 4.532e-7 + input_cost_per_token: 2.266e-7 output_cost_per_token: 9.064e-7 + priority_pricing: + input_cost_per_token: 3.9655e-7 + output_cost_per_token: 1.5862e-6 region: ap-southeast-2 - - input_cost_per_token: 2.6e-7 + - flex_pricing: + input_cost_per_token: 1.3e-7 + output_cost_per_token: 5.2e-7 + input_cost_per_token: 2.6e-7 output_cost_per_token: 1.04e-6 + priority_pricing: + input_cost_per_token: 4.55e-7 + output_cost_per_token: 1.82e-6 region: ap-south-1 - - input_cost_per_token: 2.7e-7 + - flex_pricing: + input_cost_per_token: 1.35e-7 + output_cost_per_token: 5.4e-7 + input_cost_per_token: 2.7e-7 output_cost_per_token: 1.06e-6 + priority_pricing: + input_cost_per_token: 4.725e-7 + output_cost_per_token: 1.89e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml index 976a338fb9..631c80dd6c 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml @@ -1,45 +1,129 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 3.2e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 input_cost_per_token_batches: 7.73e-8 output_cost_per_token: 6.18e-7 output_cost_per_token_batches: 3.09e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-coder-30b-a3b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-coder-30b-a3b-instruct.yaml index b7f2a46f5f..b198cb37e9 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-coder-30b-a3b-instruct.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-coder-30b-a3b-instruct.yaml @@ -1,43 +1,127 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 3.2e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-coder-480b-a35b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-coder-480b-a35b-instruct.yaml index 0656b520b1..9133d0f7e4 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-coder-480b-a35b-instruct.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-coder-480b-a35b-instruct.yaml @@ -1,34 +1,100 @@ costs: - - input_cost_per_token: 4.5e-7 + - flex_pricing: + input_cost_per_token: 2.25e-7 + output_cost_per_token: 9e-7 + input_cost_per_token: 4.5e-7 output_cost_per_token: 1.8e-6 + priority_pricing: + input_cost_per_token: 7.875e-7 + output_cost_per_token: 3.15e-6 region: us-west-2 - - input_cost_per_token: 4.5e-7 + - flex_pricing: + input_cost_per_token: 2.25e-7 + output_cost_per_token: 9e-7 + input_cost_per_token: 4.5e-7 output_cost_per_token: 1.8e-6 + priority_pricing: + input_cost_per_token: 7.875e-7 + output_cost_per_token: 3.15e-6 region: us-east-2 - - input_cost_per_token: 4.5e-7 + - flex_pricing: + input_cost_per_token: 2.25e-7 + output_cost_per_token: 9e-7 + input_cost_per_token: 4.5e-7 output_cost_per_token: 1.8e-6 + priority_pricing: + input_cost_per_token: 7.875e-7 + output_cost_per_token: 3.15e-6 region: us-east-1 - - input_cost_per_token: 5.4e-7 + - flex_pricing: + input_cost_per_token: 2.7e-7 + output_cost_per_token: 1.08e-6 + input_cost_per_token: 5.4e-7 output_cost_per_token: 2.16e-6 + priority_pricing: + input_cost_per_token: 9.45e-7 + output_cost_per_token: 3.78e-6 region: sa-east-1 - - input_cost_per_token: 7e-7 + - flex_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 + input_cost_per_token: 7e-7 output_cost_per_token: 2.79e-6 + priority_pricing: + input_cost_per_token: 1.225e-6 + output_cost_per_token: 4.9e-6 region: eu-west-2 - - input_cost_per_token: 4.5e-7 + - flex_pricing: + input_cost_per_token: 2.25e-7 + output_cost_per_token: 9e-7 + input_cost_per_token: 4.5e-7 output_cost_per_token: 1.8e-6 + priority_pricing: + input_cost_per_token: 7.875e-7 + output_cost_per_token: 3.15e-6 region: eu-north-1 - - region: ap-southeast-4 # not found in official docs - - input_cost_per_token: 4.7e-7 + - flex_pricing: + input_cost_per_token: 2.25e-7 + output_cost_per_token: 9e-7 + priority_pricing: + input_cost_per_token: 7.875e-7 + output_cost_per_token: 3.15e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 2.35e-7 + output_cost_per_token: 9.4e-7 + input_cost_per_token: 4.7e-7 output_cost_per_token: 1.87e-6 + priority_pricing: + input_cost_per_token: 8.225e-7 + output_cost_per_token: 3.29e-6 region: ap-southeast-3 - - input_cost_per_token: 4.635e-7 + - flex_pricing: + input_cost_per_token: 2.3175e-7 + output_cost_per_token: 9.27e-7 + input_cost_per_token: 4.635e-7 output_cost_per_token: 1.854e-6 + priority_pricing: + input_cost_per_token: 8.11125e-7 + output_cost_per_token: 3.2445e-6 region: ap-southeast-2 - - input_cost_per_token: 5.3e-7 + - flex_pricing: + input_cost_per_token: 2.65e-7 + output_cost_per_token: 1.06e-6 + input_cost_per_token: 5.3e-7 output_cost_per_token: 2.12e-6 + priority_pricing: + input_cost_per_token: 9.275e-7 + output_cost_per_token: 3.71e-6 region: ap-south-1 - - input_cost_per_token: 5.4e-7 + - flex_pricing: + input_cost_per_token: 2.7e-7 + output_cost_per_token: 1.08e-6 + input_cost_per_token: 5.4e-7 output_cost_per_token: 2.18e-6 + priority_pricing: + input_cost_per_token: 9.45e-7 + output_cost_per_token: 3.78e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml index ed8c3561e8..43bc18428c 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 1.5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 6.42857142857143e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.78571428571429e-7 + output_cost_per_token: 2.25e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 6.42857142857143e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.78571428571429e-7 + output_cost_per_token: 2.25e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 6.42857142857143e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.78571428571429e-7 + output_cost_per_token: 2.25e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 0.00000145 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 7.71428571428571e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + input_cost_per_token: 3.34285714285714e-7 + output_cost_per_token: 2.7e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 - output_cost_per_token: 0.00000186 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 9.85714285714286e-7 + input_cost_per_token: 2.3e-7 + output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 4.27142857142857e-7 + output_cost_per_token: 3.45e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 7.71428571428571e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.34285714285714e-7 + output_cost_per_token: 2.7e-6 region: eu-west-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 7.71428571428571e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.34285714285714e-7 + output_cost_per_token: 2.7e-6 region: eu-south-1 - - input_cost_per_token: 1.68e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 1.68e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 2.52e-6 region: eu-north-1 - - input_cost_per_token: 1.68e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 1.68e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 2.52e-6 region: eu-central-1 - - input_cost_per_token: 1.68e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 1.68e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 2.52e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 - output_cost_per_token: 0.000001236 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 6.62142857142857e-7 + input_cost_per_token: 1.545e-7 + output_cost_per_token: 1.236e-6 + priority_pricing: + input_cost_per_token: 2.86928571428571e-7 + output_cost_per_token: 2.3175e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 7.71428571428571e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.34285714285714e-7 + output_cost_per_token: 2.7e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 0.00000145 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 7.71428571428571e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + input_cost_per_token: 3.34285714285714e-7 + output_cost_per_token: 2.7e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml index b4220cafbf..97172cf852 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + - flex_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.33e-6 + input_cost_per_token: 5.3e-7 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-west-2 - - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + - flex_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.33e-6 + input_cost_per_token: 5.3e-7 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-east-2 - - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + - flex_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.33e-6 + input_cost_per_token: 5.3e-7 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-east-1 - - input_cost_per_token: 6.4e-7 - output_cost_per_token: 0.00000322 + - flex_pricing: + input_cost_per_token: 3.13962264150943e-7 + output_cost_per_token: 1.60603773584906e-6 + input_cost_per_token: 6.4e-7 + output_cost_per_token: 3.22e-6 + priority_pricing: + input_cost_per_token: 1.12301886792453e-6 + output_cost_per_token: 5.62716981132076e-6 region: sa-east-1 - - input_cost_per_token: 8.2e-7 - output_cost_per_token: 0.00000412 + - flex_pricing: + input_cost_per_token: 4.02264150943396e-7 + output_cost_per_token: 2.0577358490566e-6 + input_cost_per_token: 8.2e-7 + output_cost_per_token: 4.12e-6 + priority_pricing: + input_cost_per_token: 1.4388679245283e-6 + output_cost_per_token: 7.20981132075472e-6 region: eu-west-2 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + - flex_pricing: + input_cost_per_token: 3.04150943396226e-7 + output_cost_per_token: 1.55584905660377e-6 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: eu-west-1 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + - flex_pricing: + input_cost_per_token: 3.04150943396226e-7 + output_cost_per_token: 1.55584905660377e-6 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: eu-south-1 - - input_cost_per_token: 6.36e-7 - output_cost_per_token: 0.000003192 + - flex_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.596e-6 + input_cost_per_token: 6.36e-7 + output_cost_per_token: 3.192e-6 + priority_pricing: + input_cost_per_token: 1.116e-6 + output_cost_per_token: 5.592e-6 region: eu-north-1 - - input_cost_per_token: 6.36e-7 - output_cost_per_token: 0.000003192 + - flex_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.596e-6 + input_cost_per_token: 6.36e-7 + output_cost_per_token: 3.192e-6 + priority_pricing: + input_cost_per_token: 1.116e-6 + output_cost_per_token: 5.592e-6 region: eu-central-1 - - input_cost_per_token: 6.36e-7 - output_cost_per_token: 0.000003192 + - flex_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.596e-6 + input_cost_per_token: 6.36e-7 + output_cost_per_token: 3.192e-6 + priority_pricing: + input_cost_per_token: 1.116e-6 + output_cost_per_token: 5.592e-6 region: ap-southeast-3 - - input_cost_per_token: 5.459e-7 - output_cost_per_token: 0.0000027398 + - flex_pricing: + input_cost_per_token: 2.678e-7 + output_cost_per_token: 1.3699e-6 + input_cost_per_token: 5.459e-7 + output_cost_per_token: 2.7398e-6 + priority_pricing: + input_cost_per_token: 9.579e-7 + output_cost_per_token: 4.7998e-6 region: ap-southeast-2 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + - flex_pricing: + input_cost_per_token: 3.04150943396226e-7 + output_cost_per_token: 1.55584905660377e-6 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: ap-south-1 - - input_cost_per_token: 6.4e-7 - output_cost_per_token: 0.00000322 + - flex_pricing: + input_cost_per_token: 3.13962264150943e-7 + output_cost_per_token: 1.60603773584906e-6 + input_cost_per_token: 6.4e-7 + output_cost_per_token: 3.22e-6 + priority_pricing: + input_cost_per_token: 1.12301886792453e-6 + output_cost_per_token: 5.62716981132076e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock-mantle/xai.grok-4.3.yaml b/providers/aws-bedrock-mantle/xai.grok-4.3.yaml index 053cbf0c1a..54d8fb2877 100644 --- a/providers/aws-bedrock-mantle/xai.grok-4.3.yaml +++ b/providers/aws-bedrock-mantle/xai.grok-4.3.yaml @@ -1,19 +1,51 @@ costs: - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.0000025 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 2.1875e-6 + output_cost_per_token: 4.375e-6 region: us-west-2 - cache_read_input_token_cost: 2.4e-7 - input_cost_per_token: 0.0000015 - output_cost_per_token: 0.000003 + flex_pricing: + cache_read_input_token_cost: 1.2e-7 + input_cost_per_token: 7.5e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 3e-6 + priority_pricing: + cache_read_input_token_cost: 4.2e-7 + input_cost_per_token: 2.625e-6 + output_cost_per_token: 5.25e-6 region: us-gov-west-1 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.0000025 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 2.1875e-6 + output_cost_per_token: 4.375e-6 region: us-east-2 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.0000025 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 2.1875e-6 + output_cost_per_token: 4.375e-6 region: us-east-1 extra_configuration: bedrock_mantle_adhoc_prefix: /openai diff --git a/providers/aws-bedrock-mantle/xai.grok-4.6.yaml b/providers/aws-bedrock-mantle/xai.grok-4.6.yaml index baa89b7c03..7b4fea1818 100644 --- a/providers/aws-bedrock-mantle/xai.grok-4.6.yaml +++ b/providers/aws-bedrock-mantle/xai.grok-4.6.yaml @@ -1,11 +1,27 @@ costs: - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-west-2 - cache_read_input_token_cost: 6.6e-7 - input_cost_per_token: 0.00000264 - output_cost_per_token: 0.00000792 + flex_pricing: + cache_read_input_token_cost: 3.3e-7 + input_cost_per_token: 1.32e-6 + output_cost_per_token: 3.96e-6 + input_cost_per_token: 2.64e-6 + output_cost_per_token: 7.92e-6 + priority_pricing: + cache_read_input_token_cost: 1.155e-6 + input_cost_per_token: 4.62e-6 + output_cost_per_token: 1.386e-5 region: us-gov-east-1 extra_configuration: bedrock_mantle_adhoc_prefix: /openai diff --git a/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml b/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml index bd5c8cfb3d..38dff277cd 100644 --- a/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml @@ -1,97 +1,265 @@ costs: - - input_cost_per_token: 8e-7 + - flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 + input_cost_per_token: 8e-7 input_cost_per_token_batches: 4e-7 - output_cost_per_token: 0.0000032 - output_cost_per_token_batches: 0.0000016 + output_cost_per_token: 3.2e-6 + output_cost_per_token_batches: 1.6e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-west-2 - - input_cost_per_token: 0.00000103 - output_cost_per_token: 0.00000412 + - flex_pricing: + cache_read_input_token_cost: 1.2875e-7 + input_cost_per_token: 5.15e-7 + output_cost_per_token: 2.06e-6 + input_cost_per_token: 1.03e-6 + output_cost_per_token: 4.12e-6 + priority_pricing: + cache_read_input_token_cost: 4.50625e-7 + input_cost_per_token: 1.8025e-6 + output_cost_per_token: 7.21e-6 region: us-west-1 - - input_cost_per_token: 9.6e-7 + - flex_pricing: + cache_read_input_token_cost: 1.2e-7 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 1.92e-6 + input_cost_per_token: 9.6e-7 input_cost_per_token_batches: 4.8e-7 - output_cost_per_token: 0.00000384 - output_cost_per_token_batches: 0.00000192 + output_cost_per_token: 3.84e-6 + output_cost_per_token_batches: 1.92e-6 + priority_pricing: + cache_read_input_token_cost: 4.2e-7 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 6.72e-6 region: us-gov-west-1 - - input_cost_per_token: 8e-7 + - flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 + input_cost_per_token: 8e-7 input_cost_per_token_batches: 4e-7 - output_cost_per_token: 0.0000032 - output_cost_per_token_batches: 0.0000016 + output_cost_per_token: 3.2e-6 + output_cost_per_token_batches: 1.6e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-east-2 - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 input_cost_per_token: 8e-7 input_cost_per_token_batches: 4e-7 - output_cost_per_token: 0.0000032 - output_cost_per_token_batches: 0.0000016 + output_cost_per_token: 3.2e-6 + output_cost_per_token_batches: 1.6e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-east-1 - - input_cost_per_token: 8e-7 + - flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 + input_cost_per_token: 8e-7 input_cost_per_token_batches: 4e-7 - output_cost_per_token: 0.0000032 - output_cost_per_token_batches: 0.0000016 + output_cost_per_token: 3.2e-6 + output_cost_per_token_batches: 1.6e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: me-central-1 - - input_cost_per_token: 0.000001 + - flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 2e-6 + input_cost_per_token: 1e-6 input_cost_per_token_batches: 5e-7 - output_cost_per_token: 0.000004 - output_cost_per_token_batches: 0.000002 + output_cost_per_token: 4e-6 + output_cost_per_token_batches: 2e-6 + priority_pricing: + cache_read_input_token_cost: 4.375e-7 + input_cost_per_token: 1.75e-6 + output_cost_per_token: 7e-6 region: il-central-1 - - input_cost_per_token: 0.00000118 + - flex_pricing: + cache_read_input_token_cost: 1.475e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 2.36e-6 + input_cost_per_token: 1.18e-6 input_cost_per_token_batches: 5.9e-7 - output_cost_per_token: 0.00000472 - output_cost_per_token_batches: 0.00000236 + output_cost_per_token: 4.72e-6 + output_cost_per_token_batches: 2.36e-6 + priority_pricing: + cache_read_input_token_cost: 5.1625e-7 + input_cost_per_token: 2.065e-6 + output_cost_per_token: 8.26e-6 region: eu-west-3 - - input_cost_per_token: 0.00000113 - output_cost_per_token: 0.00000452 + - flex_pricing: + cache_read_input_token_cost: 1.4125e-7 + input_cost_per_token: 5.65e-7 + output_cost_per_token: 2.26e-6 + input_cost_per_token: 1.13e-6 + output_cost_per_token: 4.52e-6 + priority_pricing: + cache_read_input_token_cost: 4.94375e-7 + input_cost_per_token: 1.9775e-6 + output_cost_per_token: 7.91e-6 region: eu-west-2 - - input_cost_per_token: 9.2e-7 + - flex_pricing: + cache_read_input_token_cost: 1.15e-7 + input_cost_per_token: 4.6e-7 + output_cost_per_token: 1.84e-6 + input_cost_per_token: 9.2e-7 input_cost_per_token_batches: 4.6e-7 - output_cost_per_token: 0.00000368 - output_cost_per_token_batches: 0.00000184 + output_cost_per_token: 3.68e-6 + output_cost_per_token_batches: 1.84e-6 + priority_pricing: + cache_read_input_token_cost: 4.025e-7 + input_cost_per_token: 1.61e-6 + output_cost_per_token: 6.44e-6 region: eu-west-1 - - input_cost_per_token: 8.8e-7 - output_cost_per_token: 0.00000352 + - flex_pricing: + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 1.76e-6 + input_cost_per_token: 8.8e-7 + output_cost_per_token: 3.52e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 1.54e-6 + output_cost_per_token: 6.16e-6 region: eu-south-2 - - input_cost_per_token: 0.00000128 - output_cost_per_token: 0.00000521 + - flex_pricing: + cache_read_input_token_cost: 1.6e-7 + input_cost_per_token: 6.4e-7 + output_cost_per_token: 2.56e-6 + input_cost_per_token: 1.28e-6 + output_cost_per_token: 5.21e-6 + priority_pricing: + cache_read_input_token_cost: 5.6e-7 + input_cost_per_token: 2.24e-6 + output_cost_per_token: 8.96e-6 region: eu-south-1 - - input_cost_per_token: 8.7e-7 + - flex_pricing: + cache_read_input_token_cost: 1.0875e-7 + input_cost_per_token: 4.35e-7 + output_cost_per_token: 1.74e-6 + input_cost_per_token: 8.7e-7 input_cost_per_token_batches: 4.35e-7 - output_cost_per_token: 0.00000348 - output_cost_per_token_batches: 0.00000174 + output_cost_per_token: 3.48e-6 + output_cost_per_token_batches: 1.74e-6 + priority_pricing: + cache_read_input_token_cost: 3.80625e-7 + input_cost_per_token: 1.5225e-6 + output_cost_per_token: 6.09e-6 region: eu-north-1 - - input_cost_per_token: 0.00000105 + - flex_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 + input_cost_per_token: 1.05e-6 input_cost_per_token_batches: 5.25e-7 - output_cost_per_token: 0.0000042 - output_cost_per_token_batches: 0.0000021 + output_cost_per_token: 4.2e-6 + output_cost_per_token_batches: 2.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.59375e-7 + input_cost_per_token: 1.8375e-6 + output_cost_per_token: 7.35e-6 region: eu-central-1 - - input_cost_per_token: 8.7e-7 + - flex_pricing: + cache_read_input_token_cost: 1.0875e-7 + input_cost_per_token: 4.35e-7 + output_cost_per_token: 1.74e-6 + input_cost_per_token: 8.7e-7 input_cost_per_token_batches: 4.35e-7 - output_cost_per_token: 0.00000348 - output_cost_per_token_batches: 0.00000174 + output_cost_per_token: 3.48e-6 + output_cost_per_token_batches: 1.74e-6 + priority_pricing: + cache_read_input_token_cost: 3.80625e-7 + input_cost_per_token: 1.5225e-6 + output_cost_per_token: 6.09e-6 region: ap-southeast-4 - - region: ap-southeast-3 - - input_cost_per_token: 8.4e-7 + - flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 + region: ap-southeast-3 + - flex_pricing: + cache_read_input_token_cost: 1.05e-7 + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.68e-6 + input_cost_per_token: 8.4e-7 input_cost_per_token_batches: 4.2e-7 - output_cost_per_token: 0.00000336 - output_cost_per_token_batches: 0.00000168 + output_cost_per_token: 3.36e-6 + output_cost_per_token_batches: 1.68e-6 + priority_pricing: + cache_read_input_token_cost: 3.675e-7 + input_cost_per_token: 1.47e-6 + output_cost_per_token: 5.88e-6 region: ap-southeast-2 - - input_cost_per_token: 0.00000108 + - flex_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 2.16e-6 + input_cost_per_token: 1.08e-6 input_cost_per_token_batches: 5.4e-7 - output_cost_per_token: 0.00000432 - output_cost_per_token_batches: 0.00000216 + output_cost_per_token: 4.32e-6 + output_cost_per_token_batches: 2.16e-6 + priority_pricing: + cache_read_input_token_cost: 4.725e-7 + input_cost_per_token: 1.89e-6 + output_cost_per_token: 7.56e-6 region: ap-southeast-1 - - input_cost_per_token: 9.4e-7 + - flex_pricing: + cache_read_input_token_cost: 1.175e-7 + input_cost_per_token: 4.7e-7 + output_cost_per_token: 1.88e-6 + input_cost_per_token: 9.4e-7 input_cost_per_token_batches: 4.7e-7 - output_cost_per_token: 0.00000376 - output_cost_per_token_batches: 0.00000188 + output_cost_per_token: 3.76e-6 + output_cost_per_token_batches: 1.88e-6 + priority_pricing: + cache_read_input_token_cost: 4.1125e-7 + input_cost_per_token: 1.645e-6 + output_cost_per_token: 6.58e-6 region: ap-south-1 - - input_cost_per_token: 9.5e-7 + - flex_pricing: + cache_read_input_token_cost: 1.1875e-7 + input_cost_per_token: 4.75e-7 + output_cost_per_token: 1.9e-6 + input_cost_per_token: 9.5e-7 input_cost_per_token_batches: 4.75e-7 - output_cost_per_token: 0.0000038 - output_cost_per_token_batches: 0.0000019 + output_cost_per_token: 3.8e-6 + output_cost_per_token_batches: 1.9e-6 + priority_pricing: + cache_read_input_token_cost: 4.15625e-7 + input_cost_per_token: 1.6625e-6 + output_cost_per_token: 6.65e-6 region: ap-northeast-2 - - input_cost_per_token: 9.6e-7 + - flex_pricing: + cache_read_input_token_cost: 1.2e-7 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 1.92e-6 + input_cost_per_token: 9.6e-7 input_cost_per_token_batches: 4.8e-7 - output_cost_per_token: 0.00000384 - output_cost_per_token_batches: 0.00000192 + output_cost_per_token: 3.84e-6 + output_cost_per_token_batches: 1.92e-6 + priority_pricing: + cache_read_input_token_cost: 4.2e-7 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 6.72e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml b/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml index 83a007da93..6ad95b7815 100644 --- a/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml @@ -1,37 +1,81 @@ costs: - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 input_cost_per_token: 8e-7 - output_cost_per_token: 0.0000032 + output_cost_per_token: 3.2e-6 region: me-central-1 - - region: ap-southeast-7 - - input_cost_per_token: 9.6e-7 + - flex_pricing: + cache_read_input_token_cost: 1.05e-7 + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.68e-6 + region: ap-southeast-7 + - flex_pricing: + cache_read_input_token_cost: 1.2e-7 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 1.92e-6 + input_cost_per_token: 9.6e-7 region: ap-southeast-5 - cache_read_input_token_cost: 2.175e-7 + flex_pricing: + cache_read_input_token_cost: 1.0875e-7 + input_cost_per_token: 4.35e-7 + output_cost_per_token: 1.74e-6 input_cost_per_token: 8.7e-7 - output_cost_per_token: 0.00000348 + output_cost_per_token: 3.48e-6 region: ap-southeast-4 - - region: ap-southeast-3 + - flex_pricing: + cache_read_input_token_cost: 1.05e-7 + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.68e-6 + region: ap-southeast-3 - cache_read_input_token_cost: 2.1e-7 + flex_pricing: + cache_read_input_token_cost: 1.05e-7 + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.68e-6 input_cost_per_token: 8.4e-7 - output_cost_per_token: 0.00000336 + output_cost_per_token: 3.36e-6 region: ap-southeast-2 - cache_read_input_token_cost: 2.7e-7 - input_cost_per_token: 0.00000108 - output_cost_per_token: 0.00000432 + flex_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 2.16e-6 + input_cost_per_token: 1.08e-6 + output_cost_per_token: 4.32e-6 region: ap-southeast-1 - cache_read_input_token_cost: 2.35e-7 + flex_pricing: + cache_read_input_token_cost: 1.175e-7 + input_cost_per_token: 4.7e-7 + output_cost_per_token: 1.88e-6 input_cost_per_token: 9.4e-7 - output_cost_per_token: 0.00000376 + output_cost_per_token: 3.76e-6 region: ap-south-1 - cache_read_input_token_cost: 2.375e-7 + flex_pricing: + cache_read_input_token_cost: 1.1875e-7 + input_cost_per_token: 4.75e-7 + output_cost_per_token: 1.9e-6 input_cost_per_token: 9.5e-7 - output_cost_per_token: 0.0000038 + output_cost_per_token: 3.8e-6 region: ap-northeast-2 - cache_read_input_token_cost: 2.4e-7 + flex_pricing: + cache_read_input_token_cost: 1.2e-7 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 1.92e-6 input_cost_per_token: 9.6e-7 - output_cost_per_token: 0.00000384 + output_cost_per_token: 3.84e-6 region: ap-northeast-1 - - region: ap-east-2 + - flex_pricing: + cache_read_input_token_cost: 1.05e-7 + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.68e-6 + region: ap-east-2 features: - function_calling - tool_choice diff --git a/providers/aws-bedrock/deepseek.v3.2.yaml b/providers/aws-bedrock/deepseek.v3.2.yaml index 9710e113b7..5abd872b4c 100644 --- a/providers/aws-bedrock/deepseek.v3.2.yaml +++ b/providers/aws-bedrock/deepseek.v3.2.yaml @@ -1,32 +1,98 @@ costs: - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000185 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 9.25e-7 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 1.85e-6 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 3.2375e-6 region: us-west-2 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000185 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 9.25e-7 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 1.85e-6 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 3.2375e-6 region: us-east-2 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000185 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 9.25e-7 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 1.85e-6 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 3.2375e-6 region: us-east-1 - - input_cost_per_token: 7.4e-7 - output_cost_per_token: 0.00000222 + - flex_pricing: + input_cost_per_token: 3.7e-7 + output_cost_per_token: 1.10403225806452e-6 + input_cost_per_token: 7.4e-7 + output_cost_per_token: 2.22e-6 + priority_pricing: + input_cost_per_token: 1.295e-6 + output_cost_per_token: 3.86411290322581e-6 region: sa-east-1 - - region: eu-west-2 - - input_cost_per_token: 7.4e-7 - output_cost_per_token: 0.00000222 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 9.25e-7 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 3.2375e-6 + region: eu-west-2 + - flex_pricing: + input_cost_per_token: 3.7e-7 + output_cost_per_token: 1.10403225806452e-6 + input_cost_per_token: 7.4e-7 + output_cost_per_token: 2.22e-6 + priority_pricing: + input_cost_per_token: 1.295e-6 + output_cost_per_token: 3.86411290322581e-6 region: eu-north-1 - - region: ap-southeast-4 - - input_cost_per_token: 7.4e-7 - output_cost_per_token: 0.00000222 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 9.25e-7 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 3.2375e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 3.7e-7 + output_cost_per_token: 1.10403225806452e-6 + input_cost_per_token: 7.4e-7 + output_cost_per_token: 2.22e-6 + priority_pricing: + input_cost_per_token: 1.295e-6 + output_cost_per_token: 3.86411290322581e-6 region: ap-southeast-3 - - input_cost_per_token: 6.386e-7 - output_cost_per_token: 0.0000019055 + - flex_pricing: + input_cost_per_token: 3.193e-7 + output_cost_per_token: 9.5275e-7 + input_cost_per_token: 6.386e-7 + output_cost_per_token: 1.9055e-6 + priority_pricing: + input_cost_per_token: 1.11755e-6 + output_cost_per_token: 3.334625e-6 region: ap-southeast-2 - - input_cost_per_token: 7.4e-7 - output_cost_per_token: 0.00000222 + - flex_pricing: + input_cost_per_token: 3.7e-7 + output_cost_per_token: 1.10403225806452e-6 + input_cost_per_token: 7.4e-7 + output_cost_per_token: 2.22e-6 + priority_pricing: + input_cost_per_token: 1.295e-6 + output_cost_per_token: 3.86411290322581e-6 region: ap-south-1 - - input_cost_per_token: 7.4e-7 - output_cost_per_token: 0.00000222 + - flex_pricing: + input_cost_per_token: 3.7e-7 + output_cost_per_token: 1.10403225806452e-6 + input_cost_per_token: 7.4e-7 + output_cost_per_token: 2.22e-6 + priority_pricing: + input_cost_per_token: 1.295e-6 + output_cost_per_token: 3.86411290322581e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml b/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml index 596002e265..27651362b3 100644 --- a/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml @@ -1,41 +1,69 @@ costs: - cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 2e-6 + input_cost_per_token: 1e-6 input_cost_per_token_batches: 5e-7 - output_cost_per_token: 0.000004 - output_cost_per_token_batches: 0.000002 + output_cost_per_token: 4e-6 + output_cost_per_token_batches: 2e-6 region: il-central-1 - cache_read_input_token_cost: 2.95e-7 - input_cost_per_token: 0.00000118 + flex_pricing: + cache_read_input_token_cost: 1.475e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 2.36e-6 + input_cost_per_token: 1.18e-6 input_cost_per_token_batches: 5.9e-7 - output_cost_per_token: 0.00000472 - output_cost_per_token_batches: 0.00000236 + output_cost_per_token: 4.72e-6 + output_cost_per_token_batches: 2.36e-6 region: eu-west-3 - cache_read_input_token_cost: 2.3e-7 + flex_pricing: + cache_read_input_token_cost: 1.15e-7 + input_cost_per_token: 4.6e-7 + output_cost_per_token: 1.84e-6 input_cost_per_token: 9.2e-7 input_cost_per_token_batches: 4.6e-7 - output_cost_per_token: 0.00000368 - output_cost_per_token_batches: 0.00000184 + output_cost_per_token: 3.68e-6 + output_cost_per_token_batches: 1.84e-6 region: eu-west-1 - cache_read_input_token_cost: 2.2e-7 + flex_pricing: + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 1.76e-6 input_cost_per_token: 8.8e-7 - output_cost_per_token: 0.00000352 + output_cost_per_token: 3.52e-6 region: eu-south-2 - cache_read_input_token_cost: 3.2e-7 - input_cost_per_token: 0.00000128 - output_cost_per_token: 0.00000521 + flex_pricing: + cache_read_input_token_cost: 1.6e-7 + input_cost_per_token: 6.4e-7 + output_cost_per_token: 2.56e-6 + input_cost_per_token: 1.28e-6 + output_cost_per_token: 5.21e-6 region: eu-south-1 - cache_read_input_token_cost: 2.175e-7 + flex_pricing: + cache_read_input_token_cost: 1.0875e-7 + input_cost_per_token: 4.35e-7 + output_cost_per_token: 1.74e-6 input_cost_per_token: 8.7e-7 input_cost_per_token_batches: 4.35e-7 - output_cost_per_token: 0.00000348 - output_cost_per_token_batches: 0.00000174 + output_cost_per_token: 3.48e-6 + output_cost_per_token_batches: 1.74e-6 region: eu-north-1 - cache_read_input_token_cost: 2.625e-7 - input_cost_per_token: 0.00000105 + flex_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 + input_cost_per_token: 1.05e-6 input_cost_per_token_batches: 5.25e-7 - output_cost_per_token: 0.0000042 - output_cost_per_token_batches: 0.0000021 + output_cost_per_token: 4.2e-6 + output_cost_per_token_batches: 2.1e-6 region: eu-central-1 features: - function_calling diff --git a/providers/aws-bedrock/global.amazon.nova-2-lite-v1:0.yaml b/providers/aws-bedrock/global.amazon.nova-2-lite-v1:0.yaml index 2f528c358d..a14244ea07 100644 --- a/providers/aws-bedrock/global.amazon.nova-2-lite-v1:0.yaml +++ b/providers/aws-bedrock/global.amazon.nova-2-lite-v1:0.yaml @@ -1,107 +1,211 @@ costs: - cache_read_input_token_cost: 7.5e-8 input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 4.375e-6 region: us-west-2 - cache_read_input_token_cost: 9.75e-8 input_cost_per_token: 3.9e-7 - output_cost_per_token: 0.00000321 + output_cost_per_token: 3.21e-6 + priority_pricing: + cache_read_input_token_cost: 1.70625e-7 + input_cost_per_token: 6.825e-7 + output_cost_per_token: 5.6875e-6 region: us-west-1 - cache_read_input_token_cost: 7.5e-8 input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 4.375e-6 region: us-east-2 - cache_read_input_token_cost: 7.5e-8 input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 4.375e-6 region: us-east-1 - cache_read_input_token_cost: 7.5e-8 input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.3125e-7 + input_cost_per_token: 5.25e-7 + output_cost_per_token: 4.375e-6 region: me-central-1 - cache_read_input_token_cost: 9.5e-8 input_cost_per_token: 3.8e-7 - output_cost_per_token: 0.00000313 + output_cost_per_token: 3.13e-6 + priority_pricing: + cache_read_input_token_cost: 1.6625e-7 + input_cost_per_token: 6.65e-7 + output_cost_per_token: 5.54166666666667e-6 region: il-central-1 - cache_read_input_token_cost: 1.1e-7 input_cost_per_token: 4.4e-7 - output_cost_per_token: 0.00000369 + output_cost_per_token: 3.69e-6 + priority_pricing: + cache_read_input_token_cost: 1.925e-7 + input_cost_per_token: 7.7e-7 + output_cost_per_token: 6.41666666666667e-6 region: eu-west-3 - cache_read_input_token_cost: 1.05e-7 input_cost_per_token: 4.2e-7 - output_cost_per_token: 0.00000352 + output_cost_per_token: 3.52e-6 + priority_pricing: + cache_read_input_token_cost: 1.8375e-7 + input_cost_per_token: 7.35e-7 + output_cost_per_token: 6.125e-6 region: eu-west-2 - cache_read_input_token_cost: 8.5e-8 input_cost_per_token: 3.4e-7 - output_cost_per_token: 0.00000287 + output_cost_per_token: 2.87e-6 + priority_pricing: + cache_read_input_token_cost: 1.4875e-7 + input_cost_per_token: 5.95e-7 + output_cost_per_token: 4.95833333333333e-6 region: eu-west-1 - cache_read_input_token_cost: 8.25e-8 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000275 + output_cost_per_token: 2.75e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: eu-south-2 - cache_read_input_token_cost: 1.2025e-7 input_cost_per_token: 4.81e-7 - output_cost_per_token: 0.0000041 + output_cost_per_token: 4.1e-6 + priority_pricing: + cache_read_input_token_cost: 2.104375e-7 + input_cost_per_token: 8.4175e-7 + output_cost_per_token: 7.01458333333333e-6 region: eu-south-1 - cache_read_input_token_cost: 8.25e-8 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000272 + output_cost_per_token: 2.72e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: eu-north-1 - cache_read_input_token_cost: 9.75e-8 input_cost_per_token: 3.9e-7 - output_cost_per_token: 0.00000327 + output_cost_per_token: 3.27e-6 + priority_pricing: + cache_read_input_token_cost: 1.70625e-7 + input_cost_per_token: 6.825e-7 + output_cost_per_token: 5.6875e-6 region: eu-central-1 - cache_read_input_token_cost: 8.5e-8 input_cost_per_token: 3.4e-7 - output_cost_per_token: 0.00000281 + output_cost_per_token: 2.81e-6 + priority_pricing: + cache_read_input_token_cost: 1.4875e-7 + input_cost_per_token: 5.95e-7 + output_cost_per_token: 4.95833333333333e-6 region: ca-west-1 - cache_read_input_token_cost: 8e-8 input_cost_per_token: 3.2e-7 - output_cost_per_token: 0.00000267 + output_cost_per_token: 2.67e-6 + priority_pricing: + cache_read_input_token_cost: 1.4e-7 + input_cost_per_token: 5.6e-7 + output_cost_per_token: 4.66666666666667e-6 region: ca-central-1 - cache_read_input_token_cost: 1.025e-7 input_cost_per_token: 4.1e-7 - output_cost_per_token: 0.00000339 + output_cost_per_token: 3.39e-6 + priority_pricing: + cache_read_input_token_cost: 1.79375e-7 + input_cost_per_token: 7.175e-7 + output_cost_per_token: 5.97916666666667e-6 region: ap-southeast-7 - cache_read_input_token_cost: 8e-8 input_cost_per_token: 3.2e-7 - output_cost_per_token: 0.00000263 + output_cost_per_token: 2.63e-6 + priority_pricing: + cache_read_input_token_cost: 1.4e-7 + input_cost_per_token: 5.6e-7 + output_cost_per_token: 4.66666666666667e-6 region: ap-southeast-6 - cache_read_input_token_cost: 1.025e-7 input_cost_per_token: 4.1e-7 - output_cost_per_token: 0.00000339 + output_cost_per_token: 3.39e-6 + priority_pricing: + cache_read_input_token_cost: 1.79375e-7 + input_cost_per_token: 7.175e-7 + output_cost_per_token: 5.97916666666667e-6 region: ap-southeast-5 - cache_read_input_token_cost: 8.25e-8 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000271 + output_cost_per_token: 2.71e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: ap-southeast-4 - cache_read_input_token_cost: 8e-8 input_cost_per_token: 3.2e-7 - output_cost_per_token: 0.00000264 + output_cost_per_token: 2.64e-6 + priority_pricing: + cache_read_input_token_cost: 1.4e-7 + input_cost_per_token: 5.6e-7 + output_cost_per_token: 4.66666666666667e-6 region: ap-southeast-3 - cache_read_input_token_cost: 8e-8 input_cost_per_token: 3.2e-7 - output_cost_per_token: 0.00000263 + output_cost_per_token: 2.63e-6 + priority_pricing: + cache_read_input_token_cost: 1.4e-7 + input_cost_per_token: 5.6e-7 + output_cost_per_token: 4.66666666666667e-6 region: ap-southeast-2 - cache_read_input_token_cost: 1.025e-7 input_cost_per_token: 4.1e-7 - output_cost_per_token: 0.00000339 + output_cost_per_token: 3.39e-6 + priority_pricing: + cache_read_input_token_cost: 1.79375e-7 + input_cost_per_token: 7.175e-7 + output_cost_per_token: 5.97916666666667e-6 region: ap-southeast-1 - cache_read_input_token_cost: 8.75e-8 input_cost_per_token: 3.5e-7 - output_cost_per_token: 0.00000295 + output_cost_per_token: 2.95e-6 + priority_pricing: + cache_read_input_token_cost: 1.53125e-7 + input_cost_per_token: 6.125e-7 + output_cost_per_token: 5.10416666666667e-6 region: ap-south-1 - cache_read_input_token_cost: 9e-8 input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000296 + output_cost_per_token: 2.96e-6 + priority_pricing: + cache_read_input_token_cost: 1.575e-7 + input_cost_per_token: 6.3e-7 + output_cost_per_token: 5.25e-6 region: ap-northeast-2 - cache_read_input_token_cost: 9e-8 input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000301 + output_cost_per_token: 3.01e-6 + priority_pricing: + cache_read_input_token_cost: 1.575e-7 + input_cost_per_token: 6.3e-7 + output_cost_per_token: 5.25e-6 region: ap-northeast-1 - cache_read_input_token_cost: 9e-8 input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000301 + output_cost_per_token: 3.01e-6 + priority_pricing: + cache_read_input_token_cost: 1.575e-7 + input_cost_per_token: 6.3e-7 + output_cost_per_token: 5.25e-6 region: ap-east-2 features: - function_calling diff --git a/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml b/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml index b9b97fd711..ea1bb3e41e 100644 --- a/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml @@ -1,163 +1,483 @@ costs: - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: us-west-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: us-west-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: us-east-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: us-east-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: sa-east-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: me-south-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: me-central-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: il-central-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-west-3 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-west-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-west-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-south-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-south-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-north-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-central-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: eu-central-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ca-west-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ca-central-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-7 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-6 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-5 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-4 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-3 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-southeast-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-south-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-south-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-northeast-3 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-northeast-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-northeast-1 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: ap-east-2 - - cache_creation_input_token_cost: 0.00000375 - cache_read_input_token_cost: 3e-7 - input_cost_per_token: 0.000003 - output_cost_per_token: 0.000015 + - cache_creation_input_token_cost: 3.75e-6 + cache_read_input_token_cost: 3e-7 + flex_pricing: + cache_creation_input_token_cost: 1.875e-6 + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 7.5e-6 + input_cost_per_token: 3e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_creation_input_token_cost: 6.5625e-6 + cache_read_input_token_cost: 5.25e-7 + input_cost_per_token: 5.25e-6 + output_cost_per_token: 2.625e-5 region: af-south-1 features: - function_calling diff --git a/providers/aws-bedrock/global.openai.gpt-6-astra.yaml b/providers/aws-bedrock/global.openai.gpt-6-astra.yaml index 958a24ec69..58be430c86 100644 --- a/providers/aws-bedrock/global.openai.gpt-6-astra.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6-astra.yaml @@ -1,327 +1,650 @@ costs: - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: us-west-2 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: us-west-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: us-east-2 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: us-east-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: sa-east-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: eu-west-3 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: eu-west-2 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: eu-west-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: eu-north-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: eu-central-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ca-central-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-southeast-2 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-southeast-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-south-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-northeast-3 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-northeast-2 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000125 - cache_read_input_token_cost: 0.000001 - input_cost_per_token: 0.00001 - output_cost_per_token: 0.00005 + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.25e-5 + cache_read_input_token_cost: 1e-6 + input_cost_per_token: 1e-5 + output_cost_per_token: 5e-5 region: ap-northeast-1 tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.00002 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling diff --git a/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml b/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml index cb4fdd17d9..039ed88b48 100644 --- a/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml @@ -1,593 +1,1182 @@ costs: - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: us-west-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: us-west-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: us-east-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: us-east-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: sa-east-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: mx-central-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: il-central-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-west-3 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-west-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-west-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-south-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-south-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-north-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-central-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: eu-central-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ca-west-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ca-central-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-7 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-6 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-5 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-4 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-3 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-southeast-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-south-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-south-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-northeast-3 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-northeast-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-northeast-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: ap-east-2 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 region: af-south-1 tiered_pricing: cache_read: - cost_per_token: 2e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling diff --git a/providers/aws-bedrock/global.xai.grok-4.6.yaml b/providers/aws-bedrock/global.xai.grok-4.6.yaml index 624fa40972..5e7840a7b5 100644 --- a/providers/aws-bedrock/global.xai.grok-4.6.yaml +++ b/providers/aws-bedrock/global.xai.grok-4.6.yaml @@ -1,131 +1,387 @@ costs: - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-west-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-west-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-east-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-east-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: sa-east-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: me-south-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: me-central-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: il-central-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-3 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-south-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-south-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-north-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-central-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-central-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ca-west-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ca-central-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-7 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-6 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-5 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-4 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-3 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-south-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-south-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-3 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-1 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-east-2 - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 + input_cost_per_token: 2e-6 + output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: af-south-1 features: - function_calling diff --git a/providers/aws-bedrock/global.xai.grok-4.7.yaml b/providers/aws-bedrock/global.xai.grok-4.7.yaml index 52a922a4af..f1b30b23d5 100644 --- a/providers/aws-bedrock/global.xai.grok-4.7.yaml +++ b/providers/aws-bedrock/global.xai.grok-4.7.yaml @@ -1,123 +1,363 @@ costs: - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-west-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-west-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-east-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: us-east-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: sa-east-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: mx-central-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: il-central-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-3 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-west-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-south-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-south-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-north-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-central-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: eu-central-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ca-central-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-7 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-6 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-5 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-4 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-3 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-southeast-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-south-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-south-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-3 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-northeast-1 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: ap-east-2 - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 3e-6 input_cost_per_token: 2e-6 output_cost_per_token: 6e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.05e-5 region: af-south-1 features: - function_calling diff --git a/providers/aws-bedrock/global.zai.glm-5.3.yaml b/providers/aws-bedrock/global.zai.glm-5.3.yaml index 4155e8cdf0..c645826e97 100644 --- a/providers/aws-bedrock/global.zai.glm-5.3.yaml +++ b/providers/aws-bedrock/global.zai.glm-5.3.yaml @@ -1,158 +1,468 @@ costs: - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: us-west-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: us-west-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: us-east-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: us-east-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: sa-east-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: mx-central-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: il-central-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-west-3 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-west-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-west-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-south-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-south-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-north-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-central-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: eu-central-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ca-west-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ca-central-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-7 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-6 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-5 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-4 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-3 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-southeast-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-south-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-south-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-northeast-3 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-northeast-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-northeast-1 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: ap-east-2 - - cache_creation_input_token_cost: 0.0000021 + - cache_creation_input_token_cost: 2.1e-6 cache_read_input_token_cost: 3.12e-7 - input_cost_per_token: 0.00000168 - output_cost_per_token: 0.00000528 + flex_pricing: + cache_creation_input_token_cost: 1.05e-6 + cache_read_input_token_cost: 1.56e-7 + input_cost_per_token: 8.4e-7 + output_cost_per_token: 2.64e-6 + input_cost_per_token: 1.68e-6 + output_cost_per_token: 5.28e-6 + priority_pricing: + cache_creation_input_token_cost: 3.675e-6 + cache_read_input_token_cost: 5.46e-7 + input_cost_per_token: 2.94e-6 + output_cost_per_token: 9.24e-6 region: af-south-1 features: - function_calling diff --git a/providers/aws-bedrock/google.gemma-3-12b-it.yaml b/providers/aws-bedrock/google.gemma-3-12b-it.yaml index e16f8f24c1..a69828c2b5 100644 --- a/providers/aws-bedrock/google.gemma-3-12b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-12b-it.yaml @@ -1,36 +1,102 @@ costs: - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 2.9e-7 + priority_pricing: + input_cost_per_token: 1.6e-7 + output_cost_per_token: 5.1e-7 region: us-west-2 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 2.9e-7 + priority_pricing: + input_cost_per_token: 1.6e-7 + output_cost_per_token: 5.1e-7 region: us-east-2 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 2.9e-7 + priority_pricing: + input_cost_per_token: 1.6e-7 + output_cost_per_token: 5.1e-7 region: us-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: sa-east-1 - - input_cost_per_token: 1.4e-7 + - flex_pricing: + input_cost_per_token: 7.77777777777778e-8 + output_cost_per_token: 2.33333333333333e-7 + input_cost_per_token: 1.4e-7 output_cost_per_token: 4.5e-7 + priority_pricing: + input_cost_per_token: 2.48888888888889e-7 + output_cost_per_token: 7.93333333333333e-7 region: eu-west-2 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.4e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: eu-west-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.4e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: eu-south-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.4e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: eu-central-1 - - input_cost_per_token: 9.27e-8 + - flex_pricing: + input_cost_per_token: 5.15e-8 + output_cost_per_token: 1.545e-7 + input_cost_per_token: 9.27e-8 output_cost_per_token: 2.987e-7 + priority_pricing: + input_cost_per_token: 1.648e-7 + output_cost_per_token: 5.253e-7 region: ap-southeast-2 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.4e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: ap-south-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 6.11111111111111e-8 + output_cost_per_token: 1.83333333333333e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.95555555555556e-7 + output_cost_per_token: 6.23333333333333e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/google.gemma-3-27b-it.yaml b/providers/aws-bedrock/google.gemma-3-27b-it.yaml index 4b7f65e292..d943b5c661 100644 --- a/providers/aws-bedrock/google.gemma-3-27b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-27b-it.yaml @@ -1,36 +1,102 @@ costs: - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.9e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 3.8e-7 + priority_pricing: + input_cost_per_token: 4e-7 + output_cost_per_token: 6.7e-7 region: us-west-2 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.9e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 3.8e-7 + priority_pricing: + input_cost_per_token: 4e-7 + output_cost_per_token: 6.7e-7 region: us-east-2 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.9e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 3.8e-7 + priority_pricing: + input_cost_per_token: 4e-7 + output_cost_per_token: 6.7e-7 region: us-east-1 - - input_cost_per_token: 2.8e-7 + - flex_pricing: + input_cost_per_token: 1.46086956521739e-7 + output_cost_per_token: 2.31304347826087e-7 + input_cost_per_token: 2.8e-7 output_cost_per_token: 4.6e-7 + priority_pricing: + input_cost_per_token: 4.8695652173913e-7 + output_cost_per_token: 8.15652173913044e-7 region: sa-east-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.87826086956522e-7 + output_cost_per_token: 2.97391304347826e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 5.9e-7 + priority_pricing: + input_cost_per_token: 6.26086956521739e-7 + output_cost_per_token: 1.04869565217391e-6 region: eu-west-2 - - input_cost_per_token: 2.7e-7 + - flex_pricing: + input_cost_per_token: 1.40869565217391e-7 + output_cost_per_token: 2.2304347826087e-7 + input_cost_per_token: 2.7e-7 output_cost_per_token: 4.5e-7 + priority_pricing: + input_cost_per_token: 4.69565217391304e-7 + output_cost_per_token: 7.86521739130435e-7 region: eu-west-1 - - input_cost_per_token: 2.7e-7 + - flex_pricing: + input_cost_per_token: 1.40869565217391e-7 + output_cost_per_token: 2.2304347826087e-7 + input_cost_per_token: 2.7e-7 output_cost_per_token: 4.5e-7 + priority_pricing: + input_cost_per_token: 4.69565217391304e-7 + output_cost_per_token: 7.86521739130435e-7 region: eu-south-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.9e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 3.8e-7 + priority_pricing: + input_cost_per_token: 4e-7 + output_cost_per_token: 6.7e-7 region: eu-central-1 - - input_cost_per_token: 2.369e-7 + - flex_pricing: + input_cost_per_token: 1.236e-7 + output_cost_per_token: 1.957e-7 + input_cost_per_token: 2.369e-7 output_cost_per_token: 3.914e-7 + priority_pricing: + input_cost_per_token: 4.12e-7 + output_cost_per_token: 6.901e-7 region: ap-southeast-2 - - input_cost_per_token: 2.7e-7 + - flex_pricing: + input_cost_per_token: 1.40869565217391e-7 + output_cost_per_token: 2.2304347826087e-7 + input_cost_per_token: 2.7e-7 output_cost_per_token: 4.5e-7 + priority_pricing: + input_cost_per_token: 4.69565217391304e-7 + output_cost_per_token: 7.86521739130435e-7 region: ap-south-1 - - input_cost_per_token: 2.8e-7 + - flex_pricing: + input_cost_per_token: 1.46086956521739e-7 + output_cost_per_token: 2.31304347826087e-7 + input_cost_per_token: 2.8e-7 output_cost_per_token: 4.6e-7 + priority_pricing: + input_cost_per_token: 4.8695652173913e-7 + output_cost_per_token: 8.15652173913044e-7 region: ap-northeast-1 features: - system_messages diff --git a/providers/aws-bedrock/google.gemma-3-4b-it.yaml b/providers/aws-bedrock/google.gemma-3-4b-it.yaml index 991d3d3e9c..e2ed7e3d2e 100644 --- a/providers/aws-bedrock/google.gemma-3-4b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-4b-it.yaml @@ -1,36 +1,102 @@ costs: - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-west-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-east-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 4e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 8e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 1.4e-7 region: us-east-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: sa-east-1 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 6e-8 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 1.05e-7 + output_cost_per_token: 2.1e-7 region: eu-west-2 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 9e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: eu-west-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 9e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: eu-south-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: eu-central-1 - - input_cost_per_token: 4.12e-8 + - flex_pricing: + input_cost_per_token: 2.06e-8 + output_cost_per_token: 4.12e-8 + input_cost_per_token: 4.12e-8 output_cost_per_token: 8.24e-8 + priority_pricing: + input_cost_per_token: 7.21e-8 + output_cost_per_token: 1.442e-7 region: ap-southeast-2 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 9e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: ap-south-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 1.75e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml b/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml index 0d3917adbb..49d0d6440f 100644 --- a/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml @@ -1,6 +1,26 @@ costs: - - region: ap-south-2 # India CRIS pricing not documented in official docs - - region: ap-south-1 # India CRIS pricing not documented in official docs + - flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 + region: ap-south-2 + - flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 + region: ap-south-1 features: - function_calling - prompt_caching diff --git a/providers/aws-bedrock/jp.amazon.nova-2-lite-v1:0.yaml b/providers/aws-bedrock/jp.amazon.nova-2-lite-v1:0.yaml index 09daf1470b..94f264c111 100644 --- a/providers/aws-bedrock/jp.amazon.nova-2-lite-v1:0.yaml +++ b/providers/aws-bedrock/jp.amazon.nova-2-lite-v1:0.yaml @@ -1,9 +1,17 @@ costs: - cache_read_input_token_cost: 9.9e-8 + flex_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 1.98e-7 + output_cost_per_token: 1.6555e-6 input_cost_per_token: 3.96e-7 input_cost_per_token_batches: 1.98e-7 output_cost_per_token: 3.311e-6 output_cost_per_token_batches: 1.6555e-6 + priority_pricing: + cache_read_input_token_cost: 1.7325e-7 + input_cost_per_token: 6.93e-7 + output_cost_per_token: 5.79425e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/minimax.minimax-m2.1.yaml b/providers/aws-bedrock/minimax.minimax-m2.1.yaml index e82532c919..be9db1a9ef 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.1.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.1.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-west-2 - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-east-2 - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-east-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: sa-east-1 - - input_cost_per_token: 4.7e-7 - output_cost_per_token: 0.00000186 + - flex_pricing: + input_cost_per_token: 2.35e-7 + output_cost_per_token: 9.4e-7 + input_cost_per_token: 4.7e-7 + output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 8.225e-7 + output_cost_per_token: 3.29e-6 region: eu-west-2 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-west-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-south-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-north-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-central-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-southeast-3 - - input_cost_per_token: 3.09e-7 - output_cost_per_token: 0.000001236 + - flex_pricing: + input_cost_per_token: 1.545e-7 + output_cost_per_token: 6.18e-7 + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.236e-6 + priority_pricing: + input_cost_per_token: 5.4075e-7 + output_cost_per_token: 2.163e-6 region: ap-southeast-2 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-south-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/minimax.minimax-m2.5.yaml b/providers/aws-bedrock/minimax.minimax-m2.5.yaml index 940a3780bf..c1665de181 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.5.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.5.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-west-2 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-east-2 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.25e-7 + output_cost_per_token: 2.1e-6 region: us-east-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: sa-east-1 - - input_cost_per_token: 4.7e-7 + - flex_pricing: + input_cost_per_token: 2.35e-7 + output_cost_per_token: 9.4e-7 + input_cost_per_token: 4.7e-7 output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 8.225e-7 + output_cost_per_token: 3.29e-6 region: eu-west-2 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-west-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-south-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-north-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: eu-central-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-southeast-3 - - input_cost_per_token: 3.1e-7 + - flex_pricing: + input_cost_per_token: 1.55e-7 + output_cost_per_token: 6.2e-7 + input_cost_per_token: 3.1e-7 output_cost_per_token: 1.24e-6 + priority_pricing: + input_cost_per_token: 5.425e-7 + output_cost_per_token: 2.17e-6 region: ap-southeast-2 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-south-1 - - input_cost_per_token: 3.6e-7 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.3e-7 + output_cost_per_token: 2.52e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/minimax.minimax-m2.yaml b/providers/aws-bedrock/minimax.minimax-m2.yaml index 6c20f789c6..85bdd0db48 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.yaml @@ -1,43 +1,127 @@ costs: - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.2e-7 + output_cost_per_token: 2.1e-6 region: us-west-2 - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.2e-7 + output_cost_per_token: 2.1e-6 region: us-east-2 - - input_cost_per_token: 3e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 3e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 5.2e-7 + output_cost_per_token: 2.1e-6 region: us-east-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000145 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + input_cost_per_token: 6.24e-7 + output_cost_per_token: 2.52e-6 region: sa-east-1 - - input_cost_per_token: 4.7e-7 - output_cost_per_token: 0.00000186 + - flex_pricing: + input_cost_per_token: 2.35e-7 + output_cost_per_token: 9.4e-7 + input_cost_per_token: 4.7e-7 + output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 8.14666666666667e-7 + output_cost_per_token: 3.29e-6 region: eu-west-2 - - input_cost_per_token: 3.5e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 1.75e-7 + output_cost_per_token: 7e-7 + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 6.06666666666667e-7 + output_cost_per_token: 2.45e-6 region: eu-west-1 - - input_cost_per_token: 3.5e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 1.75e-7 + output_cost_per_token: 7e-7 + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 6.06666666666667e-7 + output_cost_per_token: 2.45e-6 region: eu-south-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.24e-7 + output_cost_per_token: 2.52e-6 region: eu-north-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.24e-7 + output_cost_per_token: 2.52e-6 region: eu-central-1 - - region: ap-southeast-4 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 5.2e-7 + output_cost_per_token: 2.1e-6 + region: ap-southeast-4 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 6.24e-7 + output_cost_per_token: 2.52e-6 region: ap-southeast-3 - - input_cost_per_token: 3.09e-7 - output_cost_per_token: 0.000001236 + - flex_pricing: + input_cost_per_token: 1.545e-7 + output_cost_per_token: 6.18e-7 + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.236e-6 + priority_pricing: + input_cost_per_token: 5.356e-7 + output_cost_per_token: 2.163e-6 region: ap-southeast-2 - - input_cost_per_token: 3.5e-7 - output_cost_per_token: 0.00000141 + - flex_pricing: + input_cost_per_token: 1.75e-7 + output_cost_per_token: 7e-7 + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 6.06666666666667e-7 + output_cost_per_token: 2.45e-6 region: ap-south-1 - - input_cost_per_token: 3.6e-7 - output_cost_per_token: 0.00000145 + - flex_pricing: + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + input_cost_per_token: 6.24e-7 + output_cost_per_token: 2.52e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.devstral-2-123b.yaml b/providers/aws-bedrock/mistral.devstral-2-123b.yaml index 74a3df74d5..afde5af57c 100644 --- a/providers/aws-bedrock/mistral.devstral-2-123b.yaml +++ b/providers/aws-bedrock/mistral.devstral-2-123b.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 4e-7 - output_cost_per_token: 0.000002 + - flex_pricing: + input_cost_per_token: 2e-7 + output_cost_per_token: 1e-6 + input_cost_per_token: 4e-7 + output_cost_per_token: 2e-6 + priority_pricing: + input_cost_per_token: 7e-7 + output_cost_per_token: 3.5e-6 region: us-west-2 - - input_cost_per_token: 4e-7 - output_cost_per_token: 0.000002 + - flex_pricing: + input_cost_per_token: 2e-7 + output_cost_per_token: 1e-6 + input_cost_per_token: 4e-7 + output_cost_per_token: 2e-6 + priority_pricing: + input_cost_per_token: 7e-7 + output_cost_per_token: 3.5e-6 region: us-east-2 - - input_cost_per_token: 4e-7 - output_cost_per_token: 0.000002 + - flex_pricing: + input_cost_per_token: 2e-7 + output_cost_per_token: 1e-6 + input_cost_per_token: 4e-7 + output_cost_per_token: 2e-6 + priority_pricing: + input_cost_per_token: 7e-7 + output_cost_per_token: 3.5e-6 region: us-east-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: sa-east-1 - - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.0000031 + - flex_pricing: + input_cost_per_token: 3.1e-7 + output_cost_per_token: 1.55e-6 + input_cost_per_token: 6.2e-7 + output_cost_per_token: 3.1e-6 + priority_pricing: + input_cost_per_token: 1.085e-6 + output_cost_per_token: 5.425e-6 region: eu-west-2 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: eu-west-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: eu-south-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: eu-north-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: eu-central-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: ap-southeast-3 - - input_cost_per_token: 4.1e-7 - output_cost_per_token: 0.00000206 + - flex_pricing: + input_cost_per_token: 2.05e-7 + output_cost_per_token: 1.025e-6 + input_cost_per_token: 4.1e-7 + output_cost_per_token: 2.06e-6 + priority_pricing: + input_cost_per_token: 7.175e-7 + output_cost_per_token: 3.5875e-6 region: ap-southeast-2 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: ap-south-1 - - input_cost_per_token: 4.8e-7 - output_cost_per_token: 0.0000024 + - flex_pricing: + input_cost_per_token: 2.4e-7 + output_cost_per_token: 1.2e-6 + input_cost_per_token: 4.8e-7 + output_cost_per_token: 2.4e-6 + priority_pricing: + input_cost_per_token: 8.4e-7 + output_cost_per_token: 4.2e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.magistral-small-2509.yaml b/providers/aws-bedrock/mistral.magistral-small-2509.yaml index 2582c242f7..6399c7396d 100644 --- a/providers/aws-bedrock/mistral.magistral-small-2509.yaml +++ b/providers/aws-bedrock/mistral.magistral-small-2509.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-west-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-east-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-east-1 - - input_cost_per_token: 6.1e-7 - output_cost_per_token: 0.00000182 + - flex_pricing: + input_cost_per_token: 3.05e-7 + output_cost_per_token: 9.15e-7 + input_cost_per_token: 6.1e-7 + output_cost_per_token: 1.82e-6 + priority_pricing: + input_cost_per_token: 1.0736e-6 + output_cost_per_token: 3.2086e-6 region: sa-east-1 - - input_cost_per_token: 7.8e-7 - output_cost_per_token: 0.00000233 + - flex_pricing: + input_cost_per_token: 3.9e-7 + output_cost_per_token: 1.17e-6 + input_cost_per_token: 7.8e-7 + output_cost_per_token: 2.33e-6 + priority_pricing: + input_cost_per_token: 1.3728e-6 + output_cost_per_token: 4.1028e-6 region: eu-west-2 - - input_cost_per_token: 5.9e-7 - output_cost_per_token: 0.00000176 + - flex_pricing: + input_cost_per_token: 2.95e-7 + output_cost_per_token: 8.85e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 1.76e-6 + priority_pricing: + input_cost_per_token: 1.0384e-6 + output_cost_per_token: 3.1034e-6 region: eu-west-1 - - input_cost_per_token: 5.9e-7 - output_cost_per_token: 0.00000176 + - flex_pricing: + input_cost_per_token: 2.95e-7 + output_cost_per_token: 8.85e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 1.76e-6 + priority_pricing: + input_cost_per_token: 1.0384e-6 + output_cost_per_token: 3.1034e-6 region: eu-south-1 - - input_cost_per_token: 5.15e-7 - output_cost_per_token: 0.000001545 + - flex_pricing: + input_cost_per_token: 2.575e-7 + output_cost_per_token: 7.725e-7 + input_cost_per_token: 5.15e-7 + output_cost_per_token: 1.545e-6 + priority_pricing: + input_cost_per_token: 9.064e-7 + output_cost_per_token: 2.7089e-6 region: ap-southeast-2 - - input_cost_per_token: 5.9e-7 - output_cost_per_token: 0.00000176 + - flex_pricing: + input_cost_per_token: 2.95e-7 + output_cost_per_token: 8.85e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 1.76e-6 + priority_pricing: + input_cost_per_token: 1.0384e-6 + output_cost_per_token: 3.1034e-6 region: ap-south-1 - - input_cost_per_token: 6.1e-7 - output_cost_per_token: 0.00000182 + - flex_pricing: + input_cost_per_token: 3.05e-7 + output_cost_per_token: 9.15e-7 + input_cost_per_token: 6.1e-7 + output_cost_per_token: 1.82e-6 + priority_pricing: + input_cost_per_token: 1.0736e-6 + output_cost_per_token: 3.2086e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml index 99a4d2c231..b1dd4488d9 100644 --- a/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 1e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 3.5e-7 region: us-west-2 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 1e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 3.5e-7 region: us-east-2 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 1e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 3.5e-7 region: us-east-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: sa-east-1 - - input_cost_per_token: 3.1e-7 + - flex_pricing: + input_cost_per_token: 1.55e-7 + output_cost_per_token: 1.55e-7 + input_cost_per_token: 3.1e-7 output_cost_per_token: 3.1e-7 + priority_pricing: + input_cost_per_token: 5.425e-7 + output_cost_per_token: 5.425e-7 region: eu-west-2 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: eu-west-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: eu-south-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: eu-north-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: eu-central-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: ap-southeast-3 - - input_cost_per_token: 2.06e-7 + - flex_pricing: + input_cost_per_token: 1.03e-7 + output_cost_per_token: 1.03e-7 + input_cost_per_token: 2.06e-7 output_cost_per_token: 2.06e-7 + priority_pricing: + input_cost_per_token: 3.605e-7 + output_cost_per_token: 3.605e-7 region: ap-southeast-2 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: ap-south-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 4.2e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml index 06c3f35fb1..efd1ac5ce1 100644 --- a/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 1e-7 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 1.7e-7 region: us-west-2 - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 1e-7 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 1.7e-7 region: us-east-2 - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 5e-8 + input_cost_per_token: 1e-7 output_cost_per_token: 1e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 1.7e-7 region: us-east-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: sa-east-1 - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 8e-8 + input_cost_per_token: 1.6e-7 output_cost_per_token: 1.6e-7 + priority_pricing: + input_cost_per_token: 2.72e-7 + output_cost_per_token: 2.72e-7 region: eu-west-2 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: eu-west-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: eu-south-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: eu-north-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: eu-central-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: ap-southeast-3 - - input_cost_per_token: 1.03e-7 + - flex_pricing: + input_cost_per_token: 5.15e-8 + output_cost_per_token: 5.15e-8 + input_cost_per_token: 1.03e-7 output_cost_per_token: 1.03e-7 + priority_pricing: + input_cost_per_token: 1.751e-7 + output_cost_per_token: 1.751e-7 region: ap-southeast-2 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: ap-south-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 6e-8 + input_cost_per_token: 1.2e-7 output_cost_per_token: 1.2e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 2.04e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml index 2869ce1495..118e91239f 100644 --- a/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 + input_cost_per_token: 1.5e-7 output_cost_per_token: 1.5e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 2.6e-7 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 + input_cost_per_token: 1.5e-7 output_cost_per_token: 1.5e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 2.6e-7 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 + input_cost_per_token: 1.5e-7 output_cost_per_token: 1.5e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 2.6e-7 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.07333333333333e-7 + output_cost_per_token: 1.07333333333333e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 3.98666666666667e-7 + output_cost_per_token: 3.98666666666667e-7 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: eu-west-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: eu-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: eu-north-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: eu-central-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.21e-8 + output_cost_per_token: 7.21e-8 + input_cost_per_token: 1.545e-7 output_cost_per_token: 1.545e-7 + priority_pricing: + input_cost_per_token: 2.678e-7 + output_cost_per_token: 2.678e-7 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 8.4e-8 + input_cost_per_token: 1.8e-7 output_cost_per_token: 1.8e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 3.12e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml b/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml index c99297a0b8..fd30d78f0c 100644 --- a/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml +++ b/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml @@ -1,27 +1,75 @@ costs: - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-west-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-east-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000015 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 7.5e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.5e-6 + priority_pricing: + input_cost_per_token: 8.8e-7 + output_cost_per_token: 2.63e-6 region: us-east-1 - - input_cost_per_token: 6.1e-7 - output_cost_per_token: 0.00000182 + - flex_pricing: + input_cost_per_token: 3.05e-7 + output_cost_per_token: 9.15e-7 + input_cost_per_token: 6.1e-7 + output_cost_per_token: 1.82e-6 + priority_pricing: + input_cost_per_token: 1.0736e-6 + output_cost_per_token: 3.2086e-6 region: sa-east-1 - - input_cost_per_token: 7.8e-7 - output_cost_per_token: 0.00000233 + - flex_pricing: + input_cost_per_token: 3.9e-7 + output_cost_per_token: 1.17e-6 + input_cost_per_token: 7.8e-7 + output_cost_per_token: 2.33e-6 + priority_pricing: + input_cost_per_token: 1.3728e-6 + output_cost_per_token: 4.1028e-6 region: eu-west-2 - - input_cost_per_token: 5.15e-7 - output_cost_per_token: 0.000001545 + - flex_pricing: + input_cost_per_token: 2.575e-7 + output_cost_per_token: 7.725e-7 + input_cost_per_token: 5.15e-7 + output_cost_per_token: 1.545e-6 + priority_pricing: + input_cost_per_token: 9.064e-7 + output_cost_per_token: 2.7089e-6 region: ap-southeast-2 - - input_cost_per_token: 5.9e-7 - output_cost_per_token: 0.00000176 + - flex_pricing: + input_cost_per_token: 2.95e-7 + output_cost_per_token: 8.85e-7 + input_cost_per_token: 5.9e-7 + output_cost_per_token: 1.76e-6 + priority_pricing: + input_cost_per_token: 1.0384e-6 + output_cost_per_token: 3.1034e-6 region: ap-south-1 - - input_cost_per_token: 6.1e-7 - output_cost_per_token: 0.00000182 + - flex_pricing: + input_cost_per_token: 3.05e-7 + output_cost_per_token: 9.15e-7 + input_cost_per_token: 6.1e-7 + output_cost_per_token: 1.82e-6 + priority_pricing: + input_cost_per_token: 1.0736e-6 + output_cost_per_token: 3.2086e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml b/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml index c737886c41..30fdfb1ef3 100644 --- a/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml +++ b/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 2e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 4e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 region: us-west-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 2e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 4e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 region: us-east-2 - - input_cost_per_token: 4e-8 + - flex_pricing: + input_cost_per_token: 2e-8 + output_cost_per_token: 2e-8 + input_cost_per_token: 4e-8 output_cost_per_token: 4e-8 + priority_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 7e-8 region: us-east-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2.5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 5e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 8.75e-8 region: sa-east-1 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 3e-8 + input_cost_per_token: 6e-8 output_cost_per_token: 6e-8 + priority_pricing: + input_cost_per_token: 1.05e-7 + output_cost_per_token: 1.05e-7 region: eu-west-2 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2.5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 5e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 8.75e-8 region: eu-west-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2.5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 5e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 8.75e-8 region: eu-south-1 - - input_cost_per_token: 4.12e-8 + - flex_pricing: + input_cost_per_token: 2.06e-8 + output_cost_per_token: 2.06e-8 + input_cost_per_token: 4.12e-8 output_cost_per_token: 4.12e-8 + priority_pricing: + input_cost_per_token: 7.21e-8 + output_cost_per_token: 7.21e-8 region: ap-southeast-2 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2.5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 5e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 8.75e-8 region: ap-south-1 - - input_cost_per_token: 5e-8 + - flex_pricing: + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2.5e-8 + input_cost_per_token: 5e-8 output_cost_per_token: 5e-8 + priority_pricing: + input_cost_per_token: 8.75e-8 + output_cost_per_token: 8.75e-8 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml b/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml index a609cbacc7..01369e8fd3 100644 --- a/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml +++ b/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 1e-7 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 5.2e-7 region: us-west-2 - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 1e-7 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 5.2e-7 region: us-east-2 - - input_cost_per_token: 1e-7 + - flex_pricing: + input_cost_per_token: 5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 1e-7 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 5.2e-7 region: us-east-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 1.2e-7 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 6.24e-7 region: sa-east-1 - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 2.4e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 4.7e-7 + priority_pricing: + input_cost_per_token: 2.72e-7 + output_cost_per_token: 8.32e-7 region: eu-west-2 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 1.2e-7 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 6.24e-7 region: eu-west-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 1.2e-7 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 6.24e-7 region: eu-south-1 - - input_cost_per_token: 1.03e-7 + - flex_pricing: + input_cost_per_token: 5.15e-8 + output_cost_per_token: 1.545e-7 + input_cost_per_token: 1.03e-7 output_cost_per_token: 3.09e-7 + priority_pricing: + input_cost_per_token: 1.751e-7 + output_cost_per_token: 5.356e-7 region: ap-southeast-2 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 1.2e-7 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 6.24e-7 region: ap-south-1 - - input_cost_per_token: 1.2e-7 + - flex_pricing: + input_cost_per_token: 6e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 1.2e-7 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 2.04e-7 + output_cost_per_token: 6.24e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml b/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml index ce8c2b7413..19d19d7b8c 100644 --- a/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml +++ b/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml @@ -1,30 +1,57 @@ costs: - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-west-2 - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-east-2 - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000025 + output_cost_per_token: 2.5e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 4.38e-6 region: us-east-1 - input_cost_per_token: 7.3e-7 - output_cost_per_token: 0.00000303 + output_cost_per_token: 3.03e-6 + priority_pricing: + input_cost_per_token: 1.2775e-6 + output_cost_per_token: 5.329e-6 region: sa-east-1 - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 5.256e-6 region: eu-north-1 - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 5.256e-6 region: ap-southeast-3 - input_cost_per_token: 6.18e-7 - output_cost_per_token: 0.000002575 + output_cost_per_token: 2.575e-6 + priority_pricing: + input_cost_per_token: 1.0815e-6 + output_cost_per_token: 4.5114e-6 region: ap-southeast-2 - input_cost_per_token: 7.1e-7 - output_cost_per_token: 0.00000294 + output_cost_per_token: 2.94e-6 + priority_pricing: + input_cost_per_token: 1.2425e-6 + output_cost_per_token: 5.183e-6 region: ap-south-1 - input_cost_per_token: 7.3e-7 - output_cost_per_token: 0.00000303 + output_cost_per_token: 3.03e-6 + priority_pricing: + input_cost_per_token: 1.2775e-6 + output_cost_per_token: 5.329e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml b/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml index 203454a86f..aa46ba5ded 100644 --- a/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml +++ b/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.000003 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 3e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 5.25e-6 region: us-west-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.000003 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 3e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 5.25e-6 region: us-east-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.000003 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 3e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 5.25e-6 region: us-east-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: sa-east-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: eu-west-2 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: eu-north-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: ap-southeast-3 - - input_cost_per_token: 6.18e-7 - output_cost_per_token: 0.00000309 + - flex_pricing: + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.545e-6 + input_cost_per_token: 6.18e-7 + output_cost_per_token: 3.09e-6 + priority_pricing: + input_cost_per_token: 1.0815e-6 + output_cost_per_token: 5.4075e-6 region: ap-southeast-2 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: ap-south-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.0000036 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.8e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 3.6e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 6.3e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml index 0ff40dd2a5..b5ab8fe0aa 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml @@ -1,45 +1,129 @@ costs: - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 3e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.2e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: us-gov-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 3e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 3e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 3.1e-7 + - flex_pricing: + input_cost_per_token: 1.55e-7 + output_cost_per_token: 4.65e-7 + input_cost_per_token: 3.1e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 5.425e-7 + output_cost_per_token: 1.6275e-6 region: eu-west-2 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: eu-south-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: eu-north-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: eu-central-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: ap-southeast-3 - - input_cost_per_token: 2.06e-7 + - flex_pricing: + input_cost_per_token: 1.03e-7 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 2.06e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 3.605e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 2.4e-7 + - flex_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 2.4e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 4.2e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml index a6786947b5..c78b812968 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml @@ -1,45 +1,129 @@ costs: - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.2e-7 region: us-west-2 - - input_cost_per_token: 7.2e-8 + - flex_pricing: + input_cost_per_token: 3.6e-8 + output_cost_per_token: 1.44e-7 + input_cost_per_token: 7.2e-8 output_cost_per_token: 2.88e-7 + priority_pricing: + input_cost_per_token: 1.32e-7 + output_cost_per_token: 5.04e-7 region: us-gov-west-1 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.2e-7 region: us-east-2 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.2e-7 region: us-east-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.9e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.9e-7 region: sa-east-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 3.7e-7 + priority_pricing: + input_cost_per_token: 1.65e-7 + output_cost_per_token: 6.3e-7 region: eu-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.8e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.9e-7 region: eu-west-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.8e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.9e-7 region: eu-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.3e-7 + output_cost_per_token: 1.26e-6 region: eu-north-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.3e-7 + output_cost_per_token: 1.26e-6 region: eu-central-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.3e-7 + output_cost_per_token: 1.26e-6 region: ap-southeast-3 - - input_cost_per_token: 6.18e-8 + - flex_pricing: + input_cost_per_token: 3.09e-8 + output_cost_per_token: 1.236e-7 + input_cost_per_token: 6.18e-8 output_cost_per_token: 2.472e-7 + priority_pricing: + input_cost_per_token: 1.133e-7 + output_cost_per_token: 4.326e-7 region: ap-southeast-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.8e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.9e-7 region: ap-south-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.9e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.9e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml index 9f971f5caf..05e15a471a 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml @@ -1,36 +1,102 @@ costs: - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4e-7 region: us-west-2 - - input_cost_per_token: 7.2e-8 + - flex_pricing: + input_cost_per_token: 3.6e-8 + output_cost_per_token: 1.44e-7 + input_cost_per_token: 7.2e-8 output_cost_per_token: 2.76e-7 + priority_pricing: + input_cost_per_token: 1.32e-7 + output_cost_per_token: 4.8e-7 region: us-gov-west-1 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4e-7 region: us-east-2 - - input_cost_per_token: 6e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1.2e-7 + input_cost_per_token: 6e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4e-7 region: us-east-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.8e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.66666666666667e-7 region: sa-east-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.8e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 1.65e-7 + output_cost_per_token: 6e-7 region: eu-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.7e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.66666666666667e-7 region: eu-west-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.7e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.66666666666667e-7 region: eu-south-1 - - input_cost_per_token: 6.18e-8 + - flex_pricing: + input_cost_per_token: 3.09e-8 + output_cost_per_token: 1.236e-7 + input_cost_per_token: 6.18e-8 output_cost_per_token: 2.369e-7 + priority_pricing: + input_cost_per_token: 1.133e-7 + output_cost_per_token: 4.12e-7 region: ap-southeast-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.7e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.66666666666667e-7 region: ap-south-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.4e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2.8e-7 + priority_pricing: + input_cost_per_token: 1.28333333333333e-7 + output_cost_per_token: 4.66666666666667e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml index 5d8c1817d5..99e2abe95b 100644 --- a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml @@ -1,36 +1,102 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3.25e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6.5e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.1375e-6 region: us-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: us-gov-west-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3.25e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6.5e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.1375e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3.25e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6.5e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.1375e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 - output_cost_per_token: 0.00000101 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.98333333333333e-7 + input_cost_per_token: 2.3e-7 + output_cost_per_token: 1.01e-6 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.74416666666667e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: eu-west-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3.25e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6.7e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.1375e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.9e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.8e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.365e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml b/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml index dd352e19cd..1ecb7ef061 100644 --- a/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 3.2e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml b/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml index f0ca87943f..e1fdbd7386 100644 --- a/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-east-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: us-east-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: sa-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 5.5e-8 + output_cost_per_token: 2.35714285714286e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 4.7e-7 + priority_pricing: + input_cost_per_token: 1.925e-7 + output_cost_per_token: 8.25e-7 region: eu-west-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: eu-west-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.92857142857143e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.575e-7 + output_cost_per_token: 6.75e-7 region: eu-south-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: eu-north-1 - - input_cost_per_token: 9e-8 + - flex_pricing: + input_cost_per_token: 4.5e-8 + output_cost_per_token: 1.92857142857143e-7 + input_cost_per_token: 9e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.575e-7 + output_cost_per_token: 6.75e-7 region: eu-central-1 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 1.5e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 3.1e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 5.25e-7 region: ap-southeast-3 - - input_cost_per_token: 7.21e-8 + - flex_pricing: + input_cost_per_token: 3.605e-8 + output_cost_per_token: 1.545e-7 + input_cost_per_token: 7.21e-8 output_cost_per_token: 3.09e-7 + priority_pricing: + input_cost_per_token: 1.26175e-7 + output_cost_per_token: 5.4075e-7 region: ap-southeast-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.5e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: ap-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 1.71428571428571e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 3.6e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 6e-7 region: ap-northeast-1 features: - system_messages diff --git a/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml b/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml index ecb946c8dc..4121af96d6 100644 --- a/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.07333333333333e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 3.98666666666667e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: eu-south-1 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.21e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.678e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 8.4e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.12e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml b/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml index d6a1b6468a..9dfee0cf33 100644 --- a/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-east-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3e-8 + output_cost_per_token: 1e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 2e-7 + priority_pricing: + input_cost_per_token: 1.2e-7 + output_cost_per_token: 3.5e-7 region: us-east-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: sa-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 4.71428571428571e-8 + output_cost_per_token: 1.57142857142857e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 3.1e-7 + priority_pricing: + input_cost_per_token: 1.88571428571429e-7 + output_cost_per_token: 5.5e-7 region: eu-west-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: eu-west-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.3e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: eu-south-1 - - input_cost_per_token: 7.21e-8 + - flex_pricing: + input_cost_per_token: 3.09e-8 + output_cost_per_token: 1.03e-7 + input_cost_per_token: 7.21e-8 output_cost_per_token: 2.06e-7 + priority_pricing: + input_cost_per_token: 1.236e-7 + output_cost_per_token: 3.605e-7 region: ap-southeast-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: ap-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 3.42857142857143e-8 + output_cost_per_token: 1.14285714285714e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 2.4e-7 + priority_pricing: + input_cost_per_token: 1.37142857142857e-7 + output_cost_per_token: 4e-7 region: ap-northeast-1 features: - system_messages diff --git a/providers/aws-bedrock/qwen.qwen3-235b-a22b-2507-v1:0.yaml b/providers/aws-bedrock/qwen.qwen3-235b-a22b-2507-v1:0.yaml index 004fdd420d..3eb31cc5be 100644 --- a/providers/aws-bedrock/qwen.qwen3-235b-a22b-2507-v1:0.yaml +++ b/providers/aws-bedrock/qwen.qwen3-235b-a22b-2507-v1:0.yaml @@ -1,33 +1,63 @@ costs: - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 region: us-west-2 - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 region: us-east-2 - - input_cost_per_token: 3.4e-7 - output_cost_per_token: 0.00000137 + - flex_pricing: + input_cost_per_token: 1.7e-7 + output_cost_per_token: 6.8e-7 + input_cost_per_token: 3.4e-7 + output_cost_per_token: 1.37e-6 region: eu-west-2 - - input_cost_per_token: 2.9e-7 - output_cost_per_token: 0.00000116 + - flex_pricing: + input_cost_per_token: 1.45e-7 + output_cost_per_token: 5.8e-7 + input_cost_per_token: 2.9e-7 + output_cost_per_token: 1.16e-6 region: eu-south-1 - - input_cost_per_token: 2.2e-7 + - flex_pricing: + input_cost_per_token: 1.1e-7 + output_cost_per_token: 4.4e-7 + input_cost_per_token: 2.2e-7 output_cost_per_token: 8.8e-7 region: eu-north-1 - - input_cost_per_token: 2.9e-7 - output_cost_per_token: 0.00000116 + - flex_pricing: + input_cost_per_token: 1.45e-7 + output_cost_per_token: 5.8e-7 + input_cost_per_token: 2.9e-7 + output_cost_per_token: 1.16e-6 region: eu-central-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.1e-7 region: ap-southeast-3 - - input_cost_per_token: 2.266e-7 + - flex_pricing: + input_cost_per_token: 1.133e-7 + output_cost_per_token: 4.532e-7 + input_cost_per_token: 2.266e-7 output_cost_per_token: 9.064e-7 region: ap-southeast-2 - - input_cost_per_token: 2.6e-7 - output_cost_per_token: 0.00000104 + - flex_pricing: + input_cost_per_token: 1.3e-7 + output_cost_per_token: 5.2e-7 + input_cost_per_token: 2.6e-7 + output_cost_per_token: 1.04e-6 region: ap-south-1 - - input_cost_per_token: 2.7e-7 - output_cost_per_token: 0.00000106 + - flex_pricing: + input_cost_per_token: 1.35e-7 + output_cost_per_token: 5.4e-7 + input_cost_per_token: 2.7e-7 + output_cost_per_token: 1.06e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml b/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml index 8709f518a6..77f2ea0948 100644 --- a/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml +++ b/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - - input_cost_per_token: 2.3e-7 + - flex_pricing: + input_cost_per_token: 1.15e-7 + output_cost_per_token: 4.6e-7 + input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 2e-7 + - flex_pricing: + input_cost_per_token: 1e-7 + output_cost_per_token: 4e-7 + input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - - input_cost_per_token: 1.6e-7 + - flex_pricing: + input_cost_per_token: 8e-8 + output_cost_per_token: 3.2e-7 + input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - - input_cost_per_token: 1.545e-7 + - flex_pricing: + input_cost_per_token: 7.725e-8 + output_cost_per_token: 3.09e-7 + input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - - input_cost_per_token: 1.8e-7 + - flex_pricing: + input_cost_per_token: 9e-8 + output_cost_per_token: 3.6e-7 + input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml b/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml index 59fbf0a38d..801e7e8b7c 100644 --- a/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml +++ b/providers/aws-bedrock/qwen.qwen3-coder-30b-a3b-v1:0.yaml @@ -1,42 +1,81 @@ costs: - input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: sa-east-1 - input_cost_per_token: 2.3e-7 output_cost_per_token: 9.3e-7 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 1.61e-6 region: eu-west-2 - input_cost_per_token: 1.8e-7 output_cost_per_token: 7e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: eu-west-1 - input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-south-1 - input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - input_cost_per_token: 2e-7 output_cost_per_token: 7.9e-7 + priority_pricing: + input_cost_per_token: 3.5e-7 + output_cost_per_token: 1.4e-6 region: eu-central-1 - input_cost_per_token: 1.6e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 2.8e-7 + output_cost_per_token: 1.12e-6 region: ap-southeast-3 - input_cost_per_token: 1.545e-7 output_cost_per_token: 6.18e-7 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 1.0815e-6 region: ap-southeast-2 - input_cost_per_token: 1.8e-7 output_cost_per_token: 7.1e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-south-1 - input_cost_per_token: 1.8e-7 output_cost_per_token: 7.3e-7 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 1.26e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/qwen.qwen3-coder-next.yaml b/providers/aws-bedrock/qwen.qwen3-coder-next.yaml index 086a94e0e0..4c6b87d664 100644 --- a/providers/aws-bedrock/qwen.qwen3-coder-next.yaml +++ b/providers/aws-bedrock/qwen.qwen3-coder-next.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 8.75e-7 + output_cost_per_token: 2.1e-6 region: us-west-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 8.75e-7 + output_cost_per_token: 2.1e-6 region: us-east-2 - - input_cost_per_token: 5e-7 - output_cost_per_token: 0.0000012 + - flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 6e-7 + input_cost_per_token: 5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 8.75e-7 + output_cost_per_token: 2.1e-6 region: us-east-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: sa-east-1 - - input_cost_per_token: 7.8e-7 - output_cost_per_token: 0.00000186 + - flex_pricing: + input_cost_per_token: 3.9e-7 + output_cost_per_token: 9.36e-7 + input_cost_per_token: 7.8e-7 + output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 1.365e-6 + output_cost_per_token: 3.276e-6 region: eu-west-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: eu-west-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: eu-south-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: eu-north-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: eu-central-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: ap-southeast-3 - - input_cost_per_token: 5.15e-7 - output_cost_per_token: 0.000001236 + - flex_pricing: + input_cost_per_token: 2.575e-7 + output_cost_per_token: 6.18e-7 + input_cost_per_token: 5.15e-7 + output_cost_per_token: 1.236e-6 + priority_pricing: + input_cost_per_token: 9.0125e-7 + output_cost_per_token: 2.163e-6 region: ap-southeast-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: ap-south-1 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.00000144 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 7.2e-7 + input_cost_per_token: 6e-7 + output_cost_per_token: 1.44e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 2.52e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml b/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml index aef50fa6b0..112efb8e49 100644 --- a/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml +++ b/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml @@ -1,33 +1,63 @@ costs: - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-west-2 - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-east-2 - input_cost_per_token: 5.3e-7 - output_cost_per_token: 0.00000266 + output_cost_per_token: 2.66e-6 + priority_pricing: + input_cost_per_token: 9.3e-7 + output_cost_per_token: 4.66e-6 region: us-east-1 - input_cost_per_token: 6.4e-7 - output_cost_per_token: 0.00000322 + output_cost_per_token: 3.22e-6 + priority_pricing: + input_cost_per_token: 1.12301886792453e-6 + output_cost_per_token: 5.62716981132076e-6 region: sa-east-1 - input_cost_per_token: 8.2e-7 - output_cost_per_token: 0.00000412 + output_cost_per_token: 4.12e-6 + priority_pricing: + input_cost_per_token: 1.4388679245283e-6 + output_cost_per_token: 7.20981132075472e-6 region: eu-west-2 - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: eu-west-1 - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: eu-south-1 - input_cost_per_token: 5.459e-7 - output_cost_per_token: 0.0000027398 + output_cost_per_token: 2.7398e-6 + priority_pricing: + input_cost_per_token: 9.579e-7 + output_cost_per_token: 4.7998e-6 region: ap-southeast-2 - input_cost_per_token: 6.2e-7 - output_cost_per_token: 0.00000313 + output_cost_per_token: 3.13e-6 + priority_pricing: + input_cost_per_token: 1.08792452830189e-6 + output_cost_per_token: 5.45132075471698e-6 region: ap-south-1 - input_cost_per_token: 6.4e-7 - output_cost_per_token: 0.00000322 + output_cost_per_token: 3.22e-6 + priority_pricing: + input_cost_per_token: 1.12301886792453e-6 + output_cost_per_token: 5.62716981132076e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml b/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml index 8176276d6c..7c18af873c 100644 --- a/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml +++ b/providers/aws-bedrock/us.amazon.nova-2-lite-v1:0.yaml @@ -1,27 +1,75 @@ costs: - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 1.65e-7 + output_cost_per_token: 1.375e-6 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000275 + output_cost_per_token: 2.75e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: us-west-2 - cache_read_input_token_cost: 1.0725e-7 + flex_pricing: + cache_read_input_token_cost: 5.3625e-8 + input_cost_per_token: 2.145e-7 + output_cost_per_token: 1.7875e-6 input_cost_per_token: 4.29e-7 - output_cost_per_token: 0.000003351 + output_cost_per_token: 3.351e-6 + priority_pricing: + cache_read_input_token_cost: 1.876875e-7 + input_cost_per_token: 7.5075e-7 + output_cost_per_token: 6.25625e-6 region: us-west-1 - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 1.65e-7 + output_cost_per_token: 1.375e-6 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000275 + output_cost_per_token: 2.75e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: us-east-2 - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 1.65e-7 + output_cost_per_token: 1.375e-6 input_cost_per_token: 3.3e-7 - output_cost_per_token: 0.00000275 + output_cost_per_token: 2.75e-6 + priority_pricing: + cache_read_input_token_cost: 1.44375e-7 + input_cost_per_token: 5.775e-7 + output_cost_per_token: 4.8125e-6 region: us-east-1 - cache_read_input_token_cost: 9.35e-8 + flex_pricing: + cache_read_input_token_cost: 4.675e-8 + input_cost_per_token: 1.87e-7 + output_cost_per_token: 1.55833333333333e-6 input_cost_per_token: 3.74e-7 - output_cost_per_token: 0.000003091 + output_cost_per_token: 3.091e-6 + priority_pricing: + cache_read_input_token_cost: 1.63625e-7 + input_cost_per_token: 6.545e-7 + output_cost_per_token: 5.45416666666667e-6 region: ca-west-1 - cache_read_input_token_cost: 8.8e-8 + flex_pricing: + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 1.76e-7 + output_cost_per_token: 1.46666666666667e-6 input_cost_per_token: 3.52e-7 - output_cost_per_token: 0.00000297 + output_cost_per_token: 2.97e-6 + priority_pricing: + cache_read_input_token_cost: 1.54e-7 + input_cost_per_token: 6.16e-7 + output_cost_per_token: 5.13333333333333e-6 region: ca-central-1 features: - function_calling diff --git a/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml b/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml index 476570ca73..909e4b07ca 100644 --- a/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml @@ -1,18 +1,50 @@ costs: - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 input_cost_per_token: 8e-7 - output_cost_per_token: 0.0000032 + output_cost_per_token: 3.2e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-west-2 - - input_cost_per_token: 0.00000103 - output_cost_per_token: 0.00000412 + - flex_pricing: + cache_read_input_token_cost: 1.2875e-7 + input_cost_per_token: 5.15e-7 + output_cost_per_token: 2.06e-6 + input_cost_per_token: 1.03e-6 + output_cost_per_token: 4.12e-6 + priority_pricing: + cache_read_input_token_cost: 4.50625e-7 + input_cost_per_token: 1.8025e-6 + output_cost_per_token: 7.21e-6 region: us-west-1 - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 input_cost_per_token: 8e-7 - output_cost_per_token: 0.0000032 + output_cost_per_token: 3.2e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-east-2 - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 4e-7 + output_cost_per_token: 1.6e-6 input_cost_per_token: 8e-7 - output_cost_per_token: 0.0000032 + output_cost_per_token: 3.2e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 1.4e-6 + output_cost_per_token: 5.6e-6 region: us-east-1 features: - function_calling diff --git a/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml b/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml index 0f89877bf0..d933d5f59e 100644 --- a/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml @@ -1,33 +1,93 @@ costs: - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: us-west-2 - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: us-west-1 - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: us-east-2 - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: us-east-1 - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: ca-west-1 - - cache_creation_input_token_cost: 0.000004125 + - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 - input_cost_per_token: 0.0000033 - output_cost_per_token: 0.0000165 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 8.25e-6 + input_cost_per_token: 3.3e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 5.775e-7 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 2.8875e-5 region: ca-central-1 features: - function_calling diff --git a/providers/aws-bedrock/us.openai.gpt-6-astra.yaml b/providers/aws-bedrock/us.openai.gpt-6-astra.yaml index bda0859b03..b261722d75 100644 --- a/providers/aws-bedrock/us.openai.gpt-6-astra.yaml +++ b/providers/aws-bedrock/us.openai.gpt-6-astra.yaml @@ -1,118 +1,232 @@ costs: - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-west-2 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-west-1 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-east-2 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: us-east-1 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: ca-west-1 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00001375 - cache_read_input_token_cost: 0.0000011 - input_cost_per_token: 0.000011 - output_cost_per_token: 0.000055 + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 1.375e-5 + cache_read_input_token_cost: 1.1e-6 + input_cost_per_token: 1.1e-5 + output_cost_per_token: 5.5e-5 region: ca-central-1 tiered_pricing: cache_read: - - cost_per_token: 0.0000022 + - cost_per_token: 2.2e-6 from: 272000 cache_write: - - cost_per_token: 0.0000275 + - cost_per_token: 2.75e-5 from: 272000 input: - - cost_per_token: 0.000022 + - cost_per_token: 2.2e-5 from: 272000 output: - - cost_per_token: 0.0000825 + - cost_per_token: 8.25e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 8.25e-5 + cache_read_input_token_cost: 6.6e-6 + input_cost_per_token: 6.6e-5 + output_cost_per_token: 0.00033 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-5 + from: 272000 + cache_write: + - cost_per_token: 0.000165 + from: 272000 + input: + - cost_per_token: 0.000132 + from: 272000 + output: + - cost_per_token: 0.000495 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling diff --git a/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml b/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml index caf22650ce..10c5b2d5cf 100644 --- a/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml @@ -1,118 +1,232 @@ costs: - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: us-west-2 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: us-west-1 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: us-east-2 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: us-east-1 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: ca-west-1 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 region: ca-central-1 tiered_pricing: cache_read: - cost_per_token: 2.2e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 1.65e-5 + cache_read_input_token_cost: 6.6e-7 + input_cost_per_token: 1.32e-5 + output_cost_per_token: 6.6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.32e-6 + from: 272000 + cache_write: + - cost_per_token: 3.3e-5 + from: 272000 + input: + - cost_per_token: 2.64e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling diff --git a/providers/aws-bedrock/us.xai.grok-4.6.yaml b/providers/aws-bedrock/us.xai.grok-4.6.yaml index 996379cf66..b0d7efed97 100644 --- a/providers/aws-bedrock/us.xai.grok-4.6.yaml +++ b/providers/aws-bedrock/us.xai.grok-4.6.yaml @@ -1,19 +1,51 @@ costs: - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-west-2 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-west-1 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-east-2 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-east-1 features: - function_calling diff --git a/providers/aws-bedrock/us.xai.grok-4.7.yaml b/providers/aws-bedrock/us.xai.grok-4.7.yaml index d2ddae1488..f8db6bafb1 100644 --- a/providers/aws-bedrock/us.xai.grok-4.7.yaml +++ b/providers/aws-bedrock/us.xai.grok-4.7.yaml @@ -1,27 +1,75 @@ costs: - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-west-2 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-west-1 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-east-2 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: us-east-1 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: ca-west-1 - cache_read_input_token_cost: 5.5e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000066 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 3.3e-6 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 6.6e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.155e-5 region: ca-central-1 features: - prompt_caching diff --git a/providers/aws-bedrock/us.zai.glm-5.3.yaml b/providers/aws-bedrock/us.zai.glm-5.3.yaml index 6f2e17ed73..62a539278e 100644 --- a/providers/aws-bedrock/us.zai.glm-5.3.yaml +++ b/providers/aws-bedrock/us.zai.glm-5.3.yaml @@ -1,31 +1,71 @@ costs: - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 3.06428571428571e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 5.18571428571429e-6 input_cost_per_token: 3.3e-6 input_cost_per_token_batches: 1.65e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 1.0725e-6 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 1.815e-5 region: us-west-2 - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 3.06428571428571e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 5.18571428571429e-6 input_cost_per_token: 3.3e-6 input_cost_per_token_batches: 1.65e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 1.0725e-6 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 1.815e-5 region: us-west-1 - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 3.06428571428571e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 5.18571428571429e-6 input_cost_per_token: 3.3e-6 input_cost_per_token_batches: 1.65e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 1.0725e-6 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 1.815e-5 region: us-east-2 - cache_creation_input_token_cost: 4.125e-6 cache_read_input_token_cost: 3.3e-7 + flex_pricing: + cache_creation_input_token_cost: 2.0625e-6 + cache_read_input_token_cost: 3.06428571428571e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 5.18571428571429e-6 input_cost_per_token: 3.3e-6 input_cost_per_token_batches: 1.65e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_creation_input_token_cost: 7.21875e-6 + cache_read_input_token_cost: 1.0725e-6 + input_cost_per_token: 5.775e-6 + output_cost_per_token: 1.815e-5 region: us-east-1 features: - function_calling diff --git a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml index 933578586d..b64a575744 100644 --- a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml +++ b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml @@ -1,45 +1,129 @@ costs: - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: us-east-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: sa-east-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-west-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-west-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-north-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: eu-central-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: ap-southeast-4 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: ap-southeast-3 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: ap-southeast-2 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: ap-south-1 - - input_cost_per_token: 1.5e-7 + - flex_pricing: + input_cost_per_token: 7.5e-8 + output_cost_per_token: 3e-7 + input_cost_per_token: 1.5e-7 output_cost_per_token: 6e-7 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 1.05e-6 region: ap-northeast-1 features: - system_messages diff --git a/providers/aws-bedrock/zai.glm-4.7-flash.yaml b/providers/aws-bedrock/zai.glm-4.7-flash.yaml index 01987fa92d..66b531f4f1 100644 --- a/providers/aws-bedrock/zai.glm-4.7-flash.yaml +++ b/providers/aws-bedrock/zai.glm-4.7-flash.yaml @@ -1,42 +1,120 @@ costs: - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 7e-7 region: us-west-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 7e-7 region: us-east-2 - - input_cost_per_token: 7e-8 + - flex_pricing: + input_cost_per_token: 3.5e-8 + output_cost_per_token: 2e-7 + input_cost_per_token: 7e-8 output_cost_per_token: 4e-7 + priority_pricing: + input_cost_per_token: 1.225e-7 + output_cost_per_token: 7e-7 region: us-east-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: sa-east-1 - - input_cost_per_token: 1.1e-7 + - flex_pricing: + input_cost_per_token: 5.5e-8 + output_cost_per_token: 3.14285714285714e-7 + input_cost_per_token: 1.1e-7 output_cost_per_token: 6.2e-7 + priority_pricing: + input_cost_per_token: 1.925e-7 + output_cost_per_token: 1.1e-6 region: eu-west-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: eu-west-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: eu-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: eu-north-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: eu-central-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: ap-southeast-3 - - input_cost_per_token: 7.21e-8 + - flex_pricing: + input_cost_per_token: 3.605e-8 + output_cost_per_token: 2.06e-7 + input_cost_per_token: 7.21e-8 output_cost_per_token: 4.12e-7 + priority_pricing: + input_cost_per_token: 1.26175e-7 + output_cost_per_token: 7.21e-7 region: ap-southeast-2 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: ap-south-1 - - input_cost_per_token: 8e-8 + - flex_pricing: + input_cost_per_token: 4e-8 + output_cost_per_token: 2.28571428571429e-7 + input_cost_per_token: 8e-8 output_cost_per_token: 4.8e-7 + priority_pricing: + input_cost_per_token: 1.4e-7 + output_cost_per_token: 8e-7 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/zai.glm-4.7.yaml b/providers/aws-bedrock/zai.glm-4.7.yaml index 40c6913d41..bb0ff17c42 100644 --- a/providers/aws-bedrock/zai.glm-4.7.yaml +++ b/providers/aws-bedrock/zai.glm-4.7.yaml @@ -1,33 +1,93 @@ costs: - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000022 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.1e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.2e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 3.85e-6 region: us-west-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000022 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.1e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.2e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 3.85e-6 region: us-east-2 - - input_cost_per_token: 6e-7 - output_cost_per_token: 0.0000022 + - flex_pricing: + input_cost_per_token: 3e-7 + output_cost_per_token: 1.1e-6 + input_cost_per_token: 6e-7 + output_cost_per_token: 2.2e-6 + priority_pricing: + input_cost_per_token: 1.05e-6 + output_cost_per_token: 3.85e-6 region: us-east-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.00000264 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.32e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 2.64e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 4.62e-6 region: sa-east-1 - - input_cost_per_token: 6.18e-7 - output_cost_per_token: 0.000002266 + - flex_pricing: + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.133e-6 + input_cost_per_token: 6.18e-7 + output_cost_per_token: 2.266e-6 + priority_pricing: + input_cost_per_token: 1.0815e-6 + output_cost_per_token: 3.9655e-6 region: eu-west-2 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.00000264 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.32e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 2.64e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 4.62e-6 region: eu-north-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.00000264 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.32e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 2.64e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 4.62e-6 region: ap-southeast-3 - - input_cost_per_token: 6.18e-7 - output_cost_per_token: 0.000002266 + - flex_pricing: + input_cost_per_token: 3.09e-7 + output_cost_per_token: 1.133e-6 + input_cost_per_token: 6.18e-7 + output_cost_per_token: 2.266e-6 + priority_pricing: + input_cost_per_token: 1.0815e-6 + output_cost_per_token: 3.9655e-6 region: ap-southeast-2 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.00000264 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.32e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 2.64e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 4.62e-6 region: ap-south-1 - - input_cost_per_token: 7.2e-7 - output_cost_per_token: 0.00000264 + - flex_pricing: + input_cost_per_token: 3.6e-7 + output_cost_per_token: 1.32e-6 + input_cost_per_token: 7.2e-7 + output_cost_per_token: 2.64e-6 + priority_pricing: + input_cost_per_token: 1.26e-6 + output_cost_per_token: 4.62e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/aws-bedrock/zai.glm-5.yaml b/providers/aws-bedrock/zai.glm-5.yaml index 067b1605de..b2457eb0c1 100644 --- a/providers/aws-bedrock/zai.glm-5.yaml +++ b/providers/aws-bedrock/zai.glm-5.yaml @@ -1,36 +1,69 @@ costs: - - input_cost_per_token: 0.000001 - output_cost_per_token: 0.0000032 + - input_cost_per_token: 1e-6 + output_cost_per_token: 3.2e-6 + priority_pricing: + input_cost_per_token: 1.75e-6 + output_cost_per_token: 5.6e-6 region: us-west-2 - - input_cost_per_token: 0.000001 - output_cost_per_token: 0.0000032 + - input_cost_per_token: 1e-6 + output_cost_per_token: 3.2e-6 + priority_pricing: + input_cost_per_token: 1.75e-6 + output_cost_per_token: 5.6e-6 region: us-east-2 - - input_cost_per_token: 0.000001 - output_cost_per_token: 0.0000032 + - input_cost_per_token: 1e-6 + output_cost_per_token: 3.2e-6 + priority_pricing: + input_cost_per_token: 1.75e-6 + output_cost_per_token: 5.6e-6 region: us-east-1 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: sa-east-1 - - input_cost_per_token: 0.00000155 - output_cost_per_token: 0.00000496 + - input_cost_per_token: 1.55e-6 + output_cost_per_token: 4.96e-6 + priority_pricing: + input_cost_per_token: 2.7125e-6 + output_cost_per_token: 8.68e-6 region: eu-west-2 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: eu-north-1 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: ap-southeast-4 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: ap-southeast-3 - - input_cost_per_token: 0.00000103 - output_cost_per_token: 0.0000033 + - input_cost_per_token: 1.03e-6 + output_cost_per_token: 3.3e-6 + priority_pricing: + input_cost_per_token: 1.8025e-6 + output_cost_per_token: 5.768e-6 region: ap-southeast-2 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: ap-south-1 - - input_cost_per_token: 0.0000012 - output_cost_per_token: 0.00000384 + - input_cost_per_token: 1.2e-6 + output_cost_per_token: 3.84e-6 + priority_pricing: + input_cost_per_token: 2.1e-6 + output_cost_per_token: 6.72e-6 region: ap-northeast-1 features: - function_calling diff --git a/providers/azure-open-ai/gpt-4.1-2025-04-14.yaml b/providers/azure-open-ai/gpt-4.1-2025-04-14.yaml index 460b34eaa0..bdb84bf519 100644 --- a/providers/azure-open-ai/gpt-4.1-2025-04-14.yaml +++ b/providers/azure-open-ai/gpt-4.1-2025-04-14.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_us - cache_read_input_token_cost: 5e-7 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-4.1-mini-2025-04-14.yaml b/providers/azure-open-ai/gpt-4.1-mini-2025-04-14.yaml index cef9c1e02f..240e55f12c 100644 --- a/providers/azure-open-ai/gpt-4.1-mini-2025-04-14.yaml +++ b/providers/azure-open-ai/gpt-4.1-mini-2025-04-14.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 2.2e-7 output_cost_per_token: 1.76e-6 output_cost_per_token_batches: 8.8e-7 + priority_pricing: + cache_read_input_token_cost: 1.925e-7 + input_cost_per_token: 7.7e-7 + output_cost_per_token: 3.08e-6 region: datazone_us - cache_read_input_token_cost: 1e-7 input_cost_per_token: 4e-7 input_cost_per_token_batches: 2e-7 output_cost_per_token: 1.6e-6 output_cost_per_token_batches: 8e-7 + priority_pricing: + cache_read_input_token_cost: 1.75e-7 + input_cost_per_token: 7e-7 + output_cost_per_token: 2.8e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-4.1-mini.yaml b/providers/azure-open-ai/gpt-4.1-mini.yaml index 9fb9a0e91a..8dec1bb98d 100644 --- a/providers/azure-open-ai/gpt-4.1-mini.yaml +++ b/providers/azure-open-ai/gpt-4.1-mini.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 2.2e-7 output_cost_per_token: 1.76e-6 output_cost_per_token_batches: 8.8e-7 + priority_pricing: + cache_read_input_token_cost: 1.925e-7 + input_cost_per_token: 7.7e-7 + output_cost_per_token: 3.08e-6 region: datazone_us - cache_read_input_token_cost: 1e-7 input_cost_per_token: 4e-7 input_cost_per_token_batches: 2e-7 output_cost_per_token: 1.6e-6 output_cost_per_token_batches: 8e-7 + priority_pricing: + cache_read_input_token_cost: 1.75e-7 + input_cost_per_token: 7e-7 + output_cost_per_token: 2.8e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-4.1.yaml b/providers/azure-open-ai/gpt-4.1.yaml index 5cca971df7..361e96cd09 100644 --- a/providers/azure-open-ai/gpt-4.1.yaml +++ b/providers/azure-open-ai/gpt-4.1.yaml @@ -4,18 +4,30 @@ costs: input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: global - cache_read_input_token_cost: 5.5e-7 input_cost_per_token: 2.2e-6 input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_us - cache_read_input_token_cost: 5.5e-7 input_cost_per_token: 2.2e-6 input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_eu features: - function_calling diff --git a/providers/azure-open-ai/gpt-5-2025-08-07.yaml b/providers/azure-open-ai/gpt-5-2025-08-07.yaml index fcf34df748..03a3cbdf20 100644 --- a/providers/azure-open-ai/gpt-5-2025-08-07.yaml +++ b/providers/azure-open-ai/gpt-5-2025-08-07.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5-mini-2025-08-07.yaml b/providers/azure-open-ai/gpt-5-mini-2025-08-07.yaml index 9189cffe02..b7587862d4 100644 --- a/providers/azure-open-ai/gpt-5-mini-2025-08-07.yaml +++ b/providers/azure-open-ai/gpt-5-mini-2025-08-07.yaml @@ -2,26 +2,42 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5-mini.yaml b/providers/azure-open-ai/gpt-5-mini.yaml index 9aea6e0596..f789f12034 100644 --- a/providers/azure-open-ai/gpt-5-mini.yaml +++ b/providers/azure-open-ai/gpt-5-mini.yaml @@ -2,26 +2,42 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.1-2025-11-13.yaml b/providers/azure-open-ai/gpt-5.1-2025-11-13.yaml index 6d40aaf71d..5d255648cb 100644 --- a/providers/azure-open-ai/gpt-5.1-2025-11-13.yaml +++ b/providers/azure-open-ai/gpt-5.1-2025-11-13.yaml @@ -1,27 +1,43 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.1-codex-2025-11-13.yaml b/providers/azure-open-ai/gpt-5.1-codex-2025-11-13.yaml index 84e5b37616..94b927c281 100644 --- a/providers/azure-open-ai/gpt-5.1-codex-2025-11-13.yaml +++ b/providers/azure-open-ai/gpt-5.1-codex-2025-11-13.yaml @@ -1,19 +1,35 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.00001 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 - output_cost_per_token: 0.000011 + input_cost_per_token: 1.375e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 - output_cost_per_token: 0.000011 + input_cost_per_token: 1.375e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.00001 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.1-codex-mini-2025-11-13.yaml b/providers/azure-open-ai/gpt-5.1-codex-mini-2025-11-13.yaml index 150dbd464b..b2d17a4f18 100644 --- a/providers/azure-open-ai/gpt-5.1-codex-mini-2025-11-13.yaml +++ b/providers/azure-open-ai/gpt-5.1-codex-mini-2025-11-13.yaml @@ -1,19 +1,35 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 - output_cost_per_token: 0.000002 + output_cost_per_token: 2e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 - output_cost_per_token: 0.0000022 + output_cost_per_token: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 - output_cost_per_token: 0.0000022 + output_cost_per_token: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 - output_cost_per_token: 0.000002 + output_cost_per_token: 2e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.1.yaml b/providers/azure-open-ai/gpt-5.1.yaml index ee9570c2b7..946f137e0a 100644 --- a/providers/azure-open-ai/gpt-5.1.yaml +++ b/providers/azure-open-ai/gpt-5.1.yaml @@ -1,27 +1,43 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.2-2025-12-11.yaml b/providers/azure-open-ai/gpt-5.2-2025-12-11.yaml index 1fb9d0e914..2393da7108 100644 --- a/providers/azure-open-ai/gpt-5.2-2025-12-11.yaml +++ b/providers/azure-open-ai/gpt-5.2-2025-12-11.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_us - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_eu - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.2.yaml b/providers/azure-open-ai/gpt-5.2.yaml index 57abeb8151..8f50ba6448 100644 --- a/providers/azure-open-ai/gpt-5.2.yaml +++ b/providers/azure-open-ai/gpt-5.2.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_us - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_eu - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.3-codex.yaml b/providers/azure-open-ai/gpt-5.3-codex.yaml index 2f3e9a4135..f1f70a7c6a 100644 --- a/providers/azure-open-ai/gpt-5.3-codex.yaml +++ b/providers/azure-open-ai/gpt-5.3-codex.yaml @@ -2,14 +2,26 @@ costs: - cache_read_input_token_cost: 1.925e-7 input_cost_per_token: 1.925e-6 output_cost_per_token: 1.54e-5 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_us - cache_read_input_token_cost: 1.925e-7 input_cost_per_token: 1.925e-6 output_cost_per_token: 1.54e-5 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_eu - cache_read_input_token_cost: 1.75e-7 input_cost_per_token: 1.75e-6 output_cost_per_token: 1.4e-5 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.4-2026-03-05.yaml b/providers/azure-open-ai/gpt-5.4-2026-03-05.yaml index 9027979974..eace3bc0c0 100644 --- a/providers/azure-open-ai/gpt-5.4-2026-03-05.yaml +++ b/providers/azure-open-ai/gpt-5.4-2026-03-05.yaml @@ -1,53 +1,140 @@ costs: - cache_read_input_token_cost: 2.75e-7 - input_cost_per_token: 0.00000275 - input_cost_per_token_batches: 0.000001375 - output_cost_per_token: 0.0000165 - output_cost_per_token_batches: 0.00000825 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.75e-6 + input_cost_per_token_batches: 1.375e-6 + output_cost_per_token: 1.65e-5 + output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 5.5e-7 from: 272000 input: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 output: - - cost_per_token: 0.00002475 + - cost_per_token: 2.475e-5 from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 2.75e-7 - input_cost_per_token: 0.00000275 - input_cost_per_token_batches: 0.000001375 - output_cost_per_token: 0.0000165 - output_cost_per_token_batches: 0.00000825 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.75e-6 + input_cost_per_token_batches: 1.375e-6 + output_cost_per_token: 1.65e-5 + output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 5.5e-7 from: 272000 input: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 output: - - cost_per_token: 0.00002475 + - cost_per_token: 2.475e-5 from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - input_cost_per_token_batches: 0.00000125 - output_cost_per_token: 0.000015 - output_cost_per_token_batches: 0.0000075 + flex_pricing: + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.5e-6 + input_cost_per_token_batches: 1.25e-6 + output_cost_per_token: 1.5e-5 + output_cost_per_token_batches: 7.5e-6 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 1e-5 + from: 272000 + output: + - cost_per_token: 4.5e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 5e-7 from: 272000 input: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 output: - - cost_per_token: 0.0000225 + - cost_per_token: 2.25e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/azure-open-ai/gpt-5.4-mini-2026-03-17.yaml b/providers/azure-open-ai/gpt-5.4-mini-2026-03-17.yaml index d7c673e05c..f2baa5665e 100644 --- a/providers/azure-open-ai/gpt-5.4-mini-2026-03-17.yaml +++ b/providers/azure-open-ai/gpt-5.4-mini-2026-03-17.yaml @@ -1,21 +1,45 @@ costs: - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 - output_cost_per_token: 0.00000495 - output_cost_per_token_batches: 0.000002475 + output_cost_per_token: 4.95e-6 + output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_us - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 - output_cost_per_token: 0.00000495 - output_cost_per_token_batches: 0.000002475 + output_cost_per_token: 4.95e-6 + output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_eu - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.0000045 - output_cost_per_token_batches: 0.00000225 + output_cost_per_token: 4.5e-6 + output_cost_per_token_batches: 2.25e-6 + priority_pricing: + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.4-mini.yaml b/providers/azure-open-ai/gpt-5.4-mini.yaml index 5a7852ea04..ef33043c47 100644 --- a/providers/azure-open-ai/gpt-5.4-mini.yaml +++ b/providers/azure-open-ai/gpt-5.4-mini.yaml @@ -1,21 +1,45 @@ costs: - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.95e-6 output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_us - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.95e-6 output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_eu - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 4.5e-6 output_cost_per_token_batches: 2.25e-6 + priority_pricing: + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-5.4-nano-2026-03-17.yaml b/providers/azure-open-ai/gpt-5.4-nano-2026-03-17.yaml index 0f01a52b9b..54dfe94142 100644 --- a/providers/azure-open-ai/gpt-5.4-nano-2026-03-17.yaml +++ b/providers/azure-open-ai/gpt-5.4-nano-2026-03-17.yaml @@ -1,20 +1,32 @@ costs: - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 - output_cost_per_token: 0.000001375 + output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_us - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 - output_cost_per_token: 0.000001375 + output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_eu - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 - output_cost_per_token: 0.00000125 + output_cost_per_token: 1.25e-6 output_cost_per_token_batches: 6.25e-7 region: "*" features: diff --git a/providers/azure-open-ai/gpt-5.4-nano.yaml b/providers/azure-open-ai/gpt-5.4-nano.yaml index 5bc1b23d84..d34484ff6e 100644 --- a/providers/azure-open-ai/gpt-5.4-nano.yaml +++ b/providers/azure-open-ai/gpt-5.4-nano.yaml @@ -1,17 +1,29 @@ costs: - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_us - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_eu - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 output_cost_per_token: 1.25e-6 diff --git a/providers/azure-open-ai/gpt-5.4-pro-2026-03-05.yaml b/providers/azure-open-ai/gpt-5.4-pro-2026-03-05.yaml index b00e86d64f..a145242153 100644 --- a/providers/azure-open-ai/gpt-5.4-pro-2026-03-05.yaml +++ b/providers/azure-open-ai/gpt-5.4-pro-2026-03-05.yaml @@ -1,16 +1,27 @@ costs: - - cache_read_input_token_cost: 0.000003 - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - cache_read_input_token_cost: 3e-6 + flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/azure-open-ai/gpt-5.4-pro.yaml b/providers/azure-open-ai/gpt-5.4-pro.yaml index 280eda622d..83934f231a 100644 --- a/providers/azure-open-ai/gpt-5.4-pro.yaml +++ b/providers/azure-open-ai/gpt-5.4-pro.yaml @@ -1,42 +1,75 @@ costs: - - input_cost_per_token: 0.000033 - input_cost_per_token_batches: 0.0000165 + - flex_pricing: + input_cost_per_token: 1.65e-5 + output_cost_per_token: 9.9e-5 + tiered_pricing: + input: + - cost_per_token: 3.3e-5 + from: 272000 + output: + - cost_per_token: 0.0001485 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3.3e-5 + input_cost_per_token_batches: 1.65e-5 output_cost_per_token: 0.000198 - output_cost_per_token_batches: 0.000099 + output_cost_per_token_batches: 9.9e-5 region: datazone_us tiered_pricing: input: - - cost_per_token: 0.000066 + - cost_per_token: 6.6e-5 from: 272000 output: - cost_per_token: 0.000297 from: 272000 pricing_mode: cumulative - - input_cost_per_token: 0.000033 - input_cost_per_token_batches: 0.0000165 + - flex_pricing: + input_cost_per_token: 1.65e-5 + output_cost_per_token: 9.9e-5 + tiered_pricing: + input: + - cost_per_token: 3.3e-5 + from: 272000 + output: + - cost_per_token: 0.0001485 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3.3e-5 + input_cost_per_token_batches: 1.65e-5 output_cost_per_token: 0.000198 - output_cost_per_token_batches: 0.000099 + output_cost_per_token_batches: 9.9e-5 region: datazone_eu tiered_pricing: input: - - cost_per_token: 0.000066 + - cost_per_token: 6.6e-5 from: 272000 output: - cost_per_token: 0.000297 from: 272000 pricing_mode: cumulative - - cache_read_input_token_cost: 0.000003 - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - cache_read_input_token_cost: 3e-6 + flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/azure-open-ai/gpt-5.4.yaml b/providers/azure-open-ai/gpt-5.4.yaml index 49efcc21b9..a76c7a63d9 100644 --- a/providers/azure-open-ai/gpt-5.4.yaml +++ b/providers/azure-open-ai/gpt-5.4.yaml @@ -1,9 +1,38 @@ costs: - cache_read_input_token_cost: 2.75e-7 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.75e-6 input_cost_per_token_batches: 1.375e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -17,10 +46,39 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 2.75e-7 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.75e-6 input_cost_per_token_batches: 1.375e-6 output_cost_per_token: 1.65e-5 output_cost_per_token_batches: 8.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -34,10 +92,39 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 2.5e-7 + flex_pricing: + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.5e-6 input_cost_per_token_batches: 1.25e-6 output_cost_per_token: 1.5e-5 output_cost_per_token_batches: 7.5e-6 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 1e-5 + from: 272000 + output: + - cost_per_token: 4.5e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.5-2026-04-24.yaml b/providers/azure-open-ai/gpt-5.5-2026-04-24.yaml index 0334611a07..42cb393da2 100644 --- a/providers/azure-open-ai/gpt-5.5-2026-04-24.yaml +++ b/providers/azure-open-ai/gpt-5.5-2026-04-24.yaml @@ -1,9 +1,32 @@ costs: - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 input_cost_per_token_batches: 2.75e-6 output_cost_per_token: 3.3e-5 output_cost_per_token_batches: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -17,10 +40,33 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 input_cost_per_token_batches: 2.75e-6 output_cost_per_token: 3.3e-5 output_cost_per_token_batches: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -34,10 +80,33 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + tiered_pricing: + input: + - cost_per_token: 5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5e-6 input_cost_per_token_batches: 2.5e-6 output_cost_per_token: 3e-5 output_cost_per_token_batches: 1.5e-5 + priority_pricing: + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2e-6 + from: 272000 + input: + - cost_per_token: 2e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.5.yaml b/providers/azure-open-ai/gpt-5.5.yaml index 8e3fc5da7e..c576c46bb8 100644 --- a/providers/azure-open-ai/gpt-5.5.yaml +++ b/providers/azure-open-ai/gpt-5.5.yaml @@ -1,9 +1,32 @@ costs: - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 input_cost_per_token_batches: 2.75e-6 output_cost_per_token: 3.3e-5 output_cost_per_token_batches: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -17,10 +40,33 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 input_cost_per_token_batches: 2.75e-6 output_cost_per_token: 3.3e-5 output_cost_per_token_batches: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -34,10 +80,33 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + tiered_pricing: + input: + - cost_per_token: 5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5e-6 input_cost_per_token_batches: 2.5e-6 output_cost_per_token: 3e-5 output_cost_per_token_batches: 1.5e-5 + priority_pricing: + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2e-6 + from: 272000 + input: + - cost_per_token: 2e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.6-luna-2026-07-09.yaml b/providers/azure-open-ai/gpt-5.6-luna-2026-07-09.yaml index bdbefe35d0..ee9075b81a 100644 --- a/providers/azure-open-ai/gpt-5.6-luna-2026-07-09.yaml +++ b/providers/azure-open-ai/gpt-5.6-luna-2026-07-09.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 - output_cost_per_token: 0.00000132 + output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -15,13 +53,51 @@ costs: - cost_per_token: 4.4e-7 from: 272000 output: - - cost_per_token: 0.00000198 + - cost_per_token: 1.98e-6 from: 272000 pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 - output_cost_per_token: 0.00000132 + output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -34,13 +110,51 @@ costs: - cost_per_token: 4.4e-7 from: 272000 output: - - cost_per_token: 0.00000198 + - cost_per_token: 1.98e-6 from: 272000 pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 - output_cost_per_token: 0.0000012 + output_cost_per_token: 1.2e-6 + priority_pricing: + cache_creation_input_token_cost: 5e-7 + cache_read_input_token_cost: 4e-8 + input_cost_per_token: 4e-7 + output_cost_per_token: 2.4e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 3.6e-6 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: @@ -53,7 +167,7 @@ costs: - cost_per_token: 4e-7 from: 272000 output: - - cost_per_token: 0.0000018 + - cost_per_token: 1.8e-6 from: 272000 pricing_mode: cumulative features: diff --git a/providers/azure-open-ai/gpt-5.6-luna.yaml b/providers/azure-open-ai/gpt-5.6-luna.yaml index d20476fc1f..8b36230fe6 100644 --- a/providers/azure-open-ai/gpt-5.6-luna.yaml +++ b/providers/azure-open-ai/gpt-5.6-luna.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + cache_creation_input_token_cost: 5e-7 + cache_read_input_token_cost: 4e-8 + input_cost_per_token: 4e-7 + output_cost_per_token: 2.4e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 3.6e-6 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml b/providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml index 8fea741ea0..7e16609b2c 100644 --- a/providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml +++ b/providers/azure-open-ai/gpt-5.6-sol-2026-07-09.yaml @@ -1,59 +1,173 @@ costs: - - cache_creation_input_token_cost: 0.0000055 + - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 - input_cost_per_token: 0.0000044 - output_cost_per_token: 0.000022 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 8.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000011 + - cost_per_token: 1.1e-5 from: 272000 input: - - cost_per_token: 0.0000088 + - cost_per_token: 8.8e-6 from: 272000 output: - - cost_per_token: 0.000033 + - cost_per_token: 3.3e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000055 + - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 - input_cost_per_token: 0.0000044 - output_cost_per_token: 0.000022 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 8.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000011 + - cost_per_token: 1.1e-5 from: 272000 input: - - cost_per_token: 0.0000088 + - cost_per_token: 8.8e-6 from: 272000 output: - - cost_per_token: 0.000033 + - cost_per_token: 3.3e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.000005 + - cache_creation_input_token_cost: 5e-6 cache_read_input_token_cost: 4e-7 - input_cost_per_token: 0.000004 - output_cost_per_token: 0.00002 + flex_pricing: + cache_creation_input_token_cost: 2.5e-6 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 5e-6 + from: 272000 + input: + - cost_per_token: 4e-6 + from: 272000 + output: + - cost_per_token: 1.5e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + priority_pricing: + cache_creation_input_token_cost: 1e-5 + cache_read_input_token_cost: 8e-7 + input_cost_per_token: 8e-6 + output_cost_per_token: 4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.6e-6 + from: 272000 + cache_write: + - cost_per_token: 2e-5 + from: 272000 + input: + - cost_per_token: 1.6e-5 + from: 272000 + output: + - cost_per_token: 6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 8e-7 from: 272000 cache_write: - - cost_per_token: 0.00001 + - cost_per_token: 1e-5 from: 272000 input: - - cost_per_token: 0.000008 + - cost_per_token: 8e-6 from: 272000 output: - - cost_per_token: 0.00003 + - cost_per_token: 3e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/azure-open-ai/gpt-5.6-sol.yaml b/providers/azure-open-ai/gpt-5.6-sol.yaml index 2e44e0fa69..1c33b6e09d 100644 --- a/providers/azure-open-ai/gpt-5.6-sol.yaml +++ b/providers/azure-open-ai/gpt-5.6-sol.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5e-6 cache_read_input_token_cost: 4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.5e-6 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 5e-6 + from: 272000 + input: + - cost_per_token: 4e-6 + from: 272000 + output: + - cost_per_token: 1.5e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4e-6 output_cost_per_token: 2e-5 + priority_pricing: + cache_creation_input_token_cost: 1e-5 + cache_read_input_token_cost: 8e-7 + input_cost_per_token: 8e-6 + output_cost_per_token: 4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.6e-6 + from: 272000 + cache_write: + - cost_per_token: 2e-5 + from: 272000 + input: + - cost_per_token: 1.6e-5 + from: 272000 + output: + - cost_per_token: 6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.6-terra-2026-07-09.yaml b/providers/azure-open-ai/gpt-5.6-terra-2026-07-09.yaml index 4de00a1448..2db2987c99 100644 --- a/providers/azure-open-ai/gpt-5.6-terra-2026-07-09.yaml +++ b/providers/azure-open-ai/gpt-5.6-terra-2026-07-09.yaml @@ -1,59 +1,173 @@ costs: - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000132 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000132 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000012 + flex_pricing: + cache_creation_input_token_cost: 1.25e-6 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.5e-6 + from: 272000 + input: + - cost_per_token: 2e-6 + from: 272000 + output: + - cost_per_token: 9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/azure-open-ai/gpt-5.6-terra.yaml b/providers/azure-open-ai/gpt-5.6-terra.yaml index ee84ed036a..5f7a9c415d 100644 --- a/providers/azure-open-ai/gpt-5.6-terra.yaml +++ b/providers/azure-open-ai/gpt-5.6-terra.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-6 output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-6 output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.25e-6 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.5e-6 + from: 272000 + input: + - cost_per_token: 2e-6 + from: 272000 + output: + - cost_per_token: 9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-6 output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/azure-open-ai/gpt-5.yaml b/providers/azure-open-ai/gpt-5.yaml index 6f87f664e3..8c61bdb48c 100644 --- a/providers/azure-open-ai/gpt-5.yaml +++ b/providers/azure-open-ai/gpt-5.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/azure-open-ai/gpt-6-sol-2026-09-22.yaml b/providers/azure-open-ai/gpt-6-sol-2026-09-22.yaml index 1ef15f1335..7f8e4083ee 100644 --- a/providers/azure-open-ai/gpt-6-sol-2026-09-22.yaml +++ b/providers/azure-open-ai/gpt-6-sol-2026-09-22.yaml @@ -1,59 +1,116 @@ costs: - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.3e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.000003 + - cache_creation_input_token_cost: 3e-6 cache_read_input_token_cost: 2.4e-7 - input_cost_per_token: 0.0000024 - output_cost_per_token: 0.000012 + input_cost_per_token: 2.4e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 6e-6 + cache_read_input_token_cost: 4.8e-7 + input_cost_per_token: 4.8e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 9.6e-7 + from: 272000 + cache_write: + - cost_per_token: 1.2e-5 + from: 272000 + input: + - cost_per_token: 9.6e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.0000048 + - cost_per_token: 4.8e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/azure-open-ai/gpt-6-sol.yaml b/providers/azure-open-ai/gpt-6-sol.yaml index e8b8ff7ff9..096dd26701 100644 --- a/providers/azure-open-ai/gpt-6-sol.yaml +++ b/providers/azure-open-ai/gpt-6-sol.yaml @@ -1,59 +1,116 @@ costs: - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.3e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.000003 + - cache_creation_input_token_cost: 3e-6 cache_read_input_token_cost: 2.4e-7 - input_cost_per_token: 0.0000024 - output_cost_per_token: 0.000012 + input_cost_per_token: 2.4e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 6e-6 + cache_read_input_token_cost: 4.8e-7 + input_cost_per_token: 4.8e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 9.6e-7 + from: 272000 + cache_write: + - cost_per_token: 1.2e-5 + from: 272000 + input: + - cost_per_token: 9.6e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.0000048 + - cost_per_token: 4.8e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/google-gemini/gemini-2.5-flash-image.yaml b/providers/google-gemini/gemini-2.5-flash-image.yaml index 894a718df4..bcf0cb4f3e 100644 --- a/providers/google-gemini/gemini-2.5-flash-image.yaml +++ b/providers/google-gemini/gemini-2.5-flash-image.yaml @@ -1,12 +1,16 @@ costs: - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 3e-8 + flex_pricing: + input_cost_per_token: 1.5e-7 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_1k: 0.039 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 + priority_pricing: + input_cost_per_token: 5.4e-7 region: "*" features: - prompt_caching diff --git a/providers/google-gemini/gemini-2.5-flash-lite.yaml b/providers/google-gemini/gemini-2.5-flash-lite.yaml index 033156d615..6929425a42 100644 --- a/providers/google-gemini/gemini-2.5-flash-lite.yaml +++ b/providers/google-gemini/gemini-2.5-flash-lite.yaml @@ -1,12 +1,21 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-2.5-flash.yaml b/providers/google-gemini/gemini-2.5-flash.yaml index 7c961433a9..ac96ac2f29 100644 --- a/providers/google-gemini/gemini-2.5-flash.yaml +++ b/providers/google-gemini/gemini-2.5-flash.yaml @@ -1,12 +1,21 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-2.5-pro.yaml b/providers/google-gemini/gemini-2.5-pro.yaml index 9bbeaf39b2..1dcede4291 100644 --- a/providers/google-gemini/gemini-2.5-pro.yaml +++ b/providers/google-gemini/gemini-2.5-pro.yaml @@ -1,20 +1,39 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 features: - function_calling diff --git a/providers/google-gemini/gemini-3-flash-preview.yaml b/providers/google-gemini/gemini-3-flash-preview.yaml index 6d57828b8d..80fb378f94 100644 --- a/providers/google-gemini/gemini-3-flash-preview.yaml +++ b/providers/google-gemini/gemini-3-flash-preview.yaml @@ -1,12 +1,21 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 5e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 2.5e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_token: 0.000003 - output_cost_per_token_batches: 0.0000015 + output_cost_per_token: 3e-6 + output_cost_per_token_batches: 1.5e-6 + priority_pricing: + cache_read_input_token_cost: 9e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 9e-7 + output_cost_per_token: 5.4e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3-pro-image-preview.yaml b/providers/google-gemini/gemini-3-pro-image-preview.yaml index 39f3b74119..cc0c74b9a8 100644 --- a/providers/google-gemini/gemini-3-pro-image-preview.yaml +++ b/providers/google-gemini/gemini-3-pro-image-preview.yaml @@ -1,5 +1,8 @@ costs: - - input_cost_per_image: 0.0011 + - flex_pricing: + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_image: 0.0011 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_image_1k: 0.134 @@ -7,6 +10,9 @@ costs: output_cost_per_image_4k: 0.24 output_cost_per_token: 1.2e-5 output_cost_per_token_batches: 6e-6 + priority_pricing: + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 region: "*" features: - system_messages diff --git a/providers/google-gemini/gemini-3-pro-image.yaml b/providers/google-gemini/gemini-3-pro-image.yaml index 5933c69fbf..3d95a8e28e 100644 --- a/providers/google-gemini/gemini-3-pro-image.yaml +++ b/providers/google-gemini/gemini-3-pro-image.yaml @@ -1,9 +1,15 @@ costs: - - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 + - flex_pricing: + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 output_cost_per_image_token: 0.00012 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 region: "*" limits: context_window: 65536 diff --git a/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml b/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml index ccc0bcfbec..e75833f891 100644 --- a/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml +++ b/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml @@ -2,11 +2,19 @@ costs: - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 5e-8 cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 7.5e-7 input_cost_per_audio_token: 5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 2.7e-6 region: "*" deprecationDate: "2026-05-25" features: diff --git a/providers/google-gemini/gemini-3.1-flash-lite.yaml b/providers/google-gemini/gemini-3.1-flash-lite.yaml index 823ebd0e9c..4d6c9b21f5 100644 --- a/providers/google-gemini/gemini-3.1-flash-lite.yaml +++ b/providers/google-gemini/gemini-3.1-flash-lite.yaml @@ -1,12 +1,21 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 5e-8 cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 7.5e-7 input_cost_per_audio_token: 5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.0000015 + output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_audio_token: 9e-7 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 2.7e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml b/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml index 81b04e2a51..6d3a967d66 100644 --- a/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml +++ b/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml @@ -1,20 +1,39 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-gemini/gemini-3.1-pro-preview.yaml b/providers/google-gemini/gemini-3.1-pro-preview.yaml index 584c969d02..a3aff566a1 100644 --- a/providers/google-gemini/gemini-3.1-pro-preview.yaml +++ b/providers/google-gemini/gemini-3.1-pro-preview.yaml @@ -1,20 +1,39 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-gemini/gemini-3.5-flash-lite.yaml b/providers/google-gemini/gemini-3.5-flash-lite.yaml index 1cdbfc31b1..c0e6a5b254 100644 --- a/providers/google-gemini/gemini-3.5-flash-lite.yaml +++ b/providers/google-gemini/gemini-3.5-flash-lite.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 3e-8 + flex_pricing: + cache_read_input_token_cost: 2e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3.5-flash.yaml b/providers/google-gemini/gemini-3.5-flash.yaml index 29b0ddd476..807b7f5d5a 100644 --- a/providers/google-gemini/gemini-3.5-flash.yaml +++ b/providers/google-gemini/gemini-3.5-flash.yaml @@ -1,10 +1,19 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 1.5e-7 - input_cost_per_token: 0.0000015 + flex_pricing: + cache_read_input_token_cost: 8e-8 + input_cost_per_token: 7.5e-7 + output_cost_per_token: 4.5e-6 + input_cost_per_token: 1.5e-6 input_cost_per_token_batches: 7.5e-7 - output_cost_per_token: 0.000009 - output_cost_per_token_batches: 0.0000045 + output_cost_per_token: 9e-6 + output_cost_per_token_batches: 4.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.7e-7 + input_cost_per_audio_token: 2.7e-6 + input_cost_per_token: 2.7e-6 + output_cost_per_token: 1.62e-5 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3.6-flash.yaml b/providers/google-gemini/gemini-3.6-flash.yaml index 9916642029..af9c68789d 100644 --- a/providers/google-gemini/gemini-3.6-flash.yaml +++ b/providers/google-gemini/gemini-3.6-flash.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3.7-flash.yaml b/providers/google-gemini/gemini-3.7-flash.yaml index b7ad0de147..6db07ebf9e 100644 --- a/providers/google-gemini/gemini-3.7-flash.yaml +++ b/providers/google-gemini/gemini-3.7-flash.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.00000375 - output_cost_per_token_batches: 0.000001875 + output_cost_per_token: 3.75e-6 + output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-3.8-flash-lite-tts.yaml b/providers/google-gemini/gemini-3.8-flash-lite-tts.yaml index 95ae8e5aba..6380c17d39 100644 --- a/providers/google-gemini/gemini-3.8-flash-lite-tts.yaml +++ b/providers/google-gemini/gemini-3.8-flash-lite-tts.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 1.25e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-8 + input_cost_per_token: 2.5e-7 + output_cost_per_token: 3e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_audio_token: 0.000006 - output_cost_per_token_batches: 0.000003 + output_cost_per_audio_token: 6e-6 + output_cost_per_token_batches: 3e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 9e-7 + output_cost_per_token: 1.08e-5 region: "*" features: - prompt_caching diff --git a/providers/google-gemini/gemini-3.8-flash-tts.yaml b/providers/google-gemini/gemini-3.8-flash-tts.yaml index bfe0ce0a54..d8ccc4fad1 100644 --- a/providers/google-gemini/gemini-3.8-flash-tts.yaml +++ b/providers/google-gemini/gemini-3.8-flash-tts.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 1.25e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-8 + input_cost_per_token: 2.5e-7 + output_cost_per_token: 4.5e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_audio_token: 0.000009 - output_cost_per_token_batches: 0.0000045 + output_cost_per_audio_token: 9e-6 + output_cost_per_token_batches: 4.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 9e-7 + output_cost_per_token: 1.62e-5 region: "*" features: - prompt_caching diff --git a/providers/google-gemini/gemini-3.8-flash.yaml b/providers/google-gemini/gemini-3.8-flash.yaml index 5e891d525d..19ae973b9b 100644 --- a/providers/google-gemini/gemini-3.8-flash.yaml +++ b/providers/google-gemini/gemini-3.8-flash.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.00000375 - output_cost_per_token_batches: 0.000001875 + output_cost_per_token: 3.75e-6 + output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-flash-latest.yaml b/providers/google-gemini/gemini-flash-latest.yaml index a56e5efde1..3e659d92b5 100644 --- a/providers/google-gemini/gemini-flash-latest.yaml +++ b/providers/google-gemini/gemini-flash-latest.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.00000375 - output_cost_per_token_batches: 0.000001875 + output_cost_per_token: 3.75e-6 + output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-flash-lite-latest.yaml b/providers/google-gemini/gemini-flash-lite-latest.yaml index 6851d827f8..9d12d2b237 100644 --- a/providers/google-gemini/gemini-flash-lite-latest.yaml +++ b/providers/google-gemini/gemini-flash-lite-latest.yaml @@ -1,12 +1,20 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 5e-8 cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.66666666666667e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 1.04166666666667e-6 input_cost_per_audio_token: 5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 + priority_pricing: + cache_read_input_token_cost: 4.16666666666667e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.75e-6 region: "*" features: - function_calling diff --git a/providers/google-gemini/gemini-pro-latest.yaml b/providers/google-gemini/gemini-pro-latest.yaml index cbd4710d3e..9086d85b11 100644 --- a/providers/google-gemini/gemini-pro-latest.yaml +++ b/providers/google-gemini/gemini-pro-latest.yaml @@ -1,20 +1,39 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + flex_pricing: + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 features: - function_calling diff --git a/providers/google-gemini/nano-banana-pro-preview.yaml b/providers/google-gemini/nano-banana-pro-preview.yaml index abbaa60db9..d84e4c7f45 100644 --- a/providers/google-gemini/nano-banana-pro-preview.yaml +++ b/providers/google-gemini/nano-banana-pro-preview.yaml @@ -1,5 +1,8 @@ costs: - - input_cost_per_image: 0.0011 + - flex_pricing: + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_image: 0.0011 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_image_1k: 0.134 @@ -7,6 +10,9 @@ costs: output_cost_per_image_4k: 0.24 output_cost_per_token: 1.2e-5 output_cost_per_token_batches: 6e-6 + priority_pricing: + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 region: "*" deprecationDate: "2026-06-25" features: diff --git a/providers/google-vertex/gemini-2.5-flash-image.yaml b/providers/google-vertex/gemini-2.5-flash-image.yaml index bb60d57232..2368c18dbf 100644 --- a/providers/google-vertex/gemini-2.5-flash-image.yaml +++ b/providers/google-vertex/gemini-2.5-flash-image.yaml @@ -1,83 +1,125 @@ costs: - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-west4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-west1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-south1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east5 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-central1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: global - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west8 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-southwest1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-north1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 diff --git a/providers/google-vertex/gemini-2.5-flash-lite.yaml b/providers/google-vertex/gemini-2.5-flash-lite.yaml index 6112ac33fd..3ffd350115 100644 --- a/providers/google-vertex/gemini-2.5-flash-lite.yaml +++ b/providers/google-vertex/gemini-2.5-flash-lite.yaml @@ -2,137 +2,272 @@ costs: - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-west4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-west1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-south1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east5 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-central1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: global - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west9 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west8 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-southwest1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-north1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-central2 features: - function_calling diff --git a/providers/google-vertex/gemini-2.5-flash.yaml b/providers/google-vertex/gemini-2.5-flash.yaml index 673bcfe68e..3e6a2f6fdb 100644 --- a/providers/google-vertex/gemini-2.5-flash.yaml +++ b/providers/google-vertex/gemini-2.5-flash.yaml @@ -1,219 +1,435 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-west4 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-west1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-south1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-east5 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-east4 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-east1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: us-central1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: southamerica-east1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: northamerica-northeast1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: global - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west9 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west8 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west4 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west3 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west2 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-west1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-southwest1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-north1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: europe-central2 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: australia-southeast1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: asia-southeast1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: asia-south1 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: asia-northeast3 - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: asia-northeast1 features: - function_calling diff --git a/providers/google-vertex/gemini-2.5-pro.yaml b/providers/google-vertex/gemini-2.5-pro.yaml index ade0ac2b56..2961cdfa8a 100644 --- a/providers/google-vertex/gemini-2.5-pro.yaml +++ b/providers/google-vertex/gemini-2.5-pro.yaml @@ -1,308 +1,631 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-west4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-west1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-south1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east5 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-central1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: northamerica-northeast1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west9 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west8 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-southwest1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-north1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-central2 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: asia-northeast1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-vertex/gemini-3-flash-preview.yaml b/providers/google-vertex/gemini-3-flash-preview.yaml index 165903d7f9..ff6f51f30b 100644 --- a/providers/google-vertex/gemini-3-flash-preview.yaml +++ b/providers/google-vertex/gemini-3-flash-preview.yaml @@ -1,12 +1,20 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 5e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_token: 0.000003 - output_cost_per_token_batches: 0.0000015 + output_cost_per_token: 3e-6 + output_cost_per_token_batches: 1.5e-6 + priority_pricing: + cache_read_input_token_cost: 9e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 9e-7 + output_cost_per_token: 5.4e-6 region: global features: - function_calling diff --git a/providers/google-vertex/gemini-3-pro-image-preview.yaml b/providers/google-vertex/gemini-3-pro-image-preview.yaml index e8717eeffb..4233871ed5 100644 --- a/providers/google-vertex/gemini-3-pro-image-preview.yaml +++ b/providers/google-vertex/gemini-3-pro-image-preview.yaml @@ -1,11 +1,26 @@ costs: - cache_read_input_token_cost: 2e-7 input_cost_per_image: 0.00112 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 output_cost_per_image_token: 0.00012 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global features: - system_messages diff --git a/providers/google-vertex/gemini-3-pro-preview.yaml b/providers/google-vertex/gemini-3-pro-preview.yaml index d03c03f9f0..0be17c197b 100644 --- a/providers/google-vertex/gemini-3-pro-preview.yaml +++ b/providers/google-vertex/gemini-3-pro-preview.yaml @@ -1,483 +1,933 @@ costs: - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-west4 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-west1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-south1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-east5 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-east4 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-east1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: us-central1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: southamerica-east1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: northamerica-northeast1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: me-west1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: me-central2 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: me-central1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west9 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west8 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west6 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west4 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west3 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west2 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-west1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-southwest1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-north1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: europe-central2 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: australia-southeast1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-southeast1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-south1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-northeast3 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-northeast1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-east2 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 - cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: asia-east1 tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 deprecationDate: "2026-03-26" features: diff --git a/providers/google-vertex/gemini-3.1-pro-preview.yaml b/providers/google-vertex/gemini-3.1-pro-preview.yaml index 1624be50dc..4129ee9aea 100644 --- a/providers/google-vertex/gemini-3.1-pro-preview.yaml +++ b/providers/google-vertex/gemini-3.1-pro-preview.yaml @@ -1,20 +1,38 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + flex_pricing: + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-vertex/gemini-3.5-flash.yaml b/providers/google-vertex/gemini-3.5-flash.yaml index f0d67887d6..b4f45aff2b 100644 --- a/providers/google-vertex/gemini-3.5-flash.yaml +++ b/providers/google-vertex/gemini-3.5-flash.yaml @@ -1,45 +1,99 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: us - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 1.5e-7 - input_cost_per_token: 0.0000015 + flex_pricing: + cache_read_input_token_cost: 7.5e-8 + input_cost_per_token: 7.5e-7 + output_cost_per_token: 4.5e-6 + input_cost_per_token: 1.5e-6 input_cost_per_token_batches: 7.5e-7 - output_cost_per_token: 0.000009 - output_cost_per_token_batches: 0.0000045 + output_cost_per_token: 9e-6 + output_cost_per_token_batches: 4.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.7e-7 + input_cost_per_audio_token: 2.7e-6 + input_cost_per_token: 2.7e-6 + output_cost_per_token: 1.62e-5 region: global - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: europe-west2 - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: eu - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: asia-southeast1 - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: asia-northeast1 features: - function_calling diff --git a/providers/google-vertex/gemini-3.6-flash.yaml b/providers/google-vertex/gemini-3.6-flash.yaml index 2ddc51304b..99825a2c9b 100644 --- a/providers/google-vertex/gemini-3.6-flash.yaml +++ b/providers/google-vertex/gemini-3.6-flash.yaml @@ -1,10 +1,18 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: global features: - function_calling diff --git a/providers/google-vertex/google/gemini-2.5-flash-image.yaml b/providers/google-vertex/google/gemini-2.5-flash-image.yaml index 9d59e12180..9c7e453bb0 100644 --- a/providers/google-vertex/google/gemini-2.5-flash-image.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash-image.yaml @@ -1,83 +1,125 @@ costs: - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-west4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-west1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-south1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east5 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-east1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: us-central1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: global - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west8 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west4 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-west1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-southwest1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 region: europe-north1 - - input_cost_per_token: 3e-7 + - flex_pricing: + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_image_token: 3e-5 output_cost_per_token: 2.5e-6 diff --git a/providers/google-vertex/google/gemini-2.5-flash-lite.yaml b/providers/google-vertex/google/gemini-2.5-flash-lite.yaml index 94408a40d1..f7bcaeb817 100644 --- a/providers/google-vertex/google/gemini-2.5-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash-lite.yaml @@ -2,137 +2,272 @@ costs: - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-west4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-west1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-south1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east5 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-east1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: us-central1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: global - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west9 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west8 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west4 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-west1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-southwest1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-north1 - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 3e-8 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 5e-8 + output_cost_per_token: 2e-7 input_cost_per_audio_token: 3e-7 input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 1.8e-8 + input_cost_per_audio_token: 5.4e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.2e-7 region: europe-central2 features: - function_calling diff --git a/providers/google-vertex/google/gemini-2.5-flash.yaml b/providers/google-vertex/google/gemini-2.5-flash.yaml index 903649db37..de1d851eb1 100644 --- a/providers/google-vertex/google/gemini-2.5-flash.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash.yaml @@ -1,12 +1,21 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 3e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + cache_read_input_token_cost: 3e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 - output_cost_per_token: 0.0000025 - output_cost_per_token_batches: 0.00000125 + output_cost_per_token: 2.5e-6 + output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: global features: - function_calling diff --git a/providers/google-vertex/google/gemini-2.5-pro.yaml b/providers/google-vertex/google/gemini-2.5-pro.yaml index 5c0703f14f..93a1e6ac92 100644 --- a/providers/google-vertex/google/gemini-2.5-pro.yaml +++ b/providers/google-vertex/google/gemini-2.5-pro.yaml @@ -1,308 +1,631 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-west4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-west1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-south1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east5 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-east1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: us-central1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: northamerica-northeast1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west9 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west8 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west4 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-west1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-southwest1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-north1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: europe-central2 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.25e-7 + input_cost_per_token: 2.25e-6 + output_cost_per_token: 1.8e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.5e-7 + from: 200000 + input: + - cost_per_token: 4.5e-6 + from: 200000 + output: + - cost_per_token: 2.7e-5 + from: 200000 + pricing_mode: cumulative region: asia-northeast1 tiered_pricing: cache_read: - cost_per_token: 2.5e-7 from: 200000 input: - - cost_per_token: 0.0000025 + - cost_per_token: 2.5e-6 from: 200000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-vertex/google/gemini-3-flash-preview.yaml b/providers/google-vertex/google/gemini-3-flash-preview.yaml index bd16b17832..f19424fd99 100644 --- a/providers/google-vertex/google/gemini-3-flash-preview.yaml +++ b/providers/google-vertex/google/gemini-3-flash-preview.yaml @@ -1,12 +1,20 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 1e-7 cache_read_input_token_cost: 5e-8 - input_cost_per_audio_token: 0.000001 + flex_pricing: + input_cost_per_token: 2.5e-7 + output_cost_per_token: 1.5e-6 + input_cost_per_audio_token: 1e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_token: 0.000003 - output_cost_per_token_batches: 0.0000015 + output_cost_per_token: 3e-6 + output_cost_per_token_batches: 1.5e-6 + priority_pricing: + cache_read_input_token_cost: 9e-8 + input_cost_per_audio_token: 1.8e-6 + input_cost_per_token: 9e-7 + output_cost_per_token: 5.4e-6 region: global features: - function_calling diff --git a/providers/google-vertex/google/gemini-3-pro-image-preview.yaml b/providers/google-vertex/google/gemini-3-pro-image-preview.yaml index 94e7063814..ccfb19a7c0 100644 --- a/providers/google-vertex/google/gemini-3-pro-image-preview.yaml +++ b/providers/google-vertex/google/gemini-3-pro-image-preview.yaml @@ -4,6 +4,21 @@ costs: output_cost_per_image_token: 0.00012 output_cost_per_token: 1.2e-5 output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global features: - system_messages diff --git a/providers/google-vertex/google/gemini-3-pro-image.yaml b/providers/google-vertex/google/gemini-3-pro-image.yaml index ce96e14717..f3728d99d6 100644 --- a/providers/google-vertex/google/gemini-3-pro-image.yaml +++ b/providers/google-vertex/google/gemini-3-pro-image.yaml @@ -1,11 +1,30 @@ costs: - cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 input_cost_per_image: 0.00112 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 output_cost_per_image_token: 0.00012 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global features: - system_messages diff --git a/providers/google-vertex/google/gemini-3.1-flash-image.yaml b/providers/google-vertex/google/gemini-3.1-flash-image.yaml index 039dd9d4fa..4dcc193de6 100644 --- a/providers/google-vertex/google/gemini-3.1-flash-image.yaml +++ b/providers/google-vertex/google/gemini-3.1-flash-image.yaml @@ -1,25 +1,49 @@ costs: - cache_read_input_token_cost: 5.5e-8 + flex_pricing: + cache_read_input_token_cost: 2.75e-8 + input_cost_per_token: 2.75e-7 + output_cost_per_token: 1.65e-6 input_cost_per_token: 5.5e-7 input_cost_per_token_batches: 2.75e-7 - output_cost_per_image_token: 0.000066 - output_cost_per_token: 0.0000033 - output_cost_per_token_batches: 0.00000165 + output_cost_per_image_token: 6.6e-5 + output_cost_per_token: 3.3e-6 + output_cost_per_token_batches: 1.65e-6 + priority_pricing: + cache_read_input_token_cost: 9.9e-8 + input_cost_per_token: 9.9e-7 + output_cost_per_token: 5.94e-6 region: us - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 5e-8 + flex_pricing: + cache_read_input_token_cost: 2.5e-8 + input_cost_per_token: 2.5e-7 + output_cost_per_token: 1.5e-6 input_cost_per_token: 5e-7 input_cost_per_token_batches: 2.5e-7 - output_cost_per_image_token: 0.00006 - output_cost_per_token: 0.000003 - output_cost_per_token_batches: 0.0000015 + output_cost_per_image_token: 6e-5 + output_cost_per_token: 3e-6 + output_cost_per_token_batches: 1.5e-6 + priority_pricing: + cache_read_input_token_cost: 9e-8 + input_cost_per_token: 9e-7 + output_cost_per_token: 5.4e-6 region: global - cache_read_input_token_cost: 5.5e-8 + flex_pricing: + cache_read_input_token_cost: 2.75e-8 + input_cost_per_token: 2.75e-7 + output_cost_per_token: 1.65e-6 input_cost_per_token: 5.5e-7 input_cost_per_token_batches: 2.75e-7 - output_cost_per_image_token: 0.000066 - output_cost_per_token: 0.0000033 - output_cost_per_token_batches: 0.00000165 + output_cost_per_image_token: 6.6e-5 + output_cost_per_token: 3.3e-6 + output_cost_per_token_batches: 1.65e-6 + priority_pricing: + cache_read_input_token_cost: 9.9e-8 + input_cost_per_token: 9.9e-7 + output_cost_per_token: 5.94e-6 region: eu features: - system_messages diff --git a/providers/google-vertex/google/gemini-3.1-flash-lite-image.yaml b/providers/google-vertex/google/gemini-3.1-flash-lite-image.yaml index f5bf92372c..32d14c4715 100644 --- a/providers/google-vertex/google/gemini-3.1-flash-lite-image.yaml +++ b/providers/google-vertex/google/gemini-3.1-flash-lite-image.yaml @@ -1,11 +1,19 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 7.5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_image_token: 0.00003 - output_cost_per_token: 0.0000015 + output_cost_per_image_token: 3e-5 + output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 2.7e-6 region: global features: - system_messages diff --git a/providers/google-vertex/google/gemini-3.1-flash-lite.yaml b/providers/google-vertex/google/gemini-3.1-flash-lite.yaml index 533626f9ba..41caed7693 100644 --- a/providers/google-vertex/google/gemini-3.1-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-3.1-flash-lite.yaml @@ -1,30 +1,57 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_audio_token_cost: 5.5e-8 cache_read_input_token_cost: 2.75e-8 + flex_pricing: + cache_read_input_token_cost: 1.375e-8 + input_cost_per_token: 1.375e-7 + output_cost_per_token: 8.25e-7 input_cost_per_audio_token: 5.5e-7 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.00000165 + output_cost_per_token: 1.65e-6 output_cost_per_token_batches: 8.25e-7 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_audio_token: 9.9e-7 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 2.97e-6 region: us - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_audio_token_cost: 5e-8 cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 7.5e-7 input_cost_per_audio_token: 5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.0000015 + output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_audio_token: 9e-7 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 2.7e-6 region: global - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_audio_token_cost: 5.5e-8 cache_read_input_token_cost: 2.75e-8 + flex_pricing: + cache_read_input_token_cost: 1.375e-8 + input_cost_per_token: 1.375e-7 + output_cost_per_token: 8.25e-7 input_cost_per_audio_token: 5.5e-7 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.00000165 + output_cost_per_token: 1.65e-6 output_cost_per_token_batches: 8.25e-7 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_audio_token: 9.9e-7 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 2.97e-6 region: eu features: - function_calling diff --git a/providers/google-vertex/google/gemini-3.1-pro-preview.yaml b/providers/google-vertex/google/gemini-3.1-pro-preview.yaml index f715004fd1..0bc148ae6f 100644 --- a/providers/google-vertex/google/gemini-3.1-pro-preview.yaml +++ b/providers/google-vertex/google/gemini-3.1-pro-preview.yaml @@ -1,20 +1,38 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000045 + - cache_creation_input_token_cost_per_hour: 4.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.000012 - output_cost_per_token_batches: 0.000006 + flex_pricing: + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1.2e-5 + output_cost_per_token_batches: 6e-6 + priority_pricing: + cache_read_input_token_cost: 3.6e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 2.16e-5 + tiered_pricing: + cache_read: + - cost_per_token: 7.2e-7 + from: 200000 + input: + - cost_per_token: 7.2e-6 + from: 200000 + output: + - cost_per_token: 3.24e-5 + from: 200000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 200000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-vertex/google/gemini-3.5-flash-lite.yaml b/providers/google-vertex/google/gemini-3.5-flash-lite.yaml index 6fa5ef12e2..fb4d0f7622 100644 --- a/providers/google-vertex/google/gemini-3.5-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-3.5-flash-lite.yaml @@ -1,24 +1,48 @@ costs: - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 3.3e-8 + flex_pricing: + cache_read_input_token_cost: 1.65e-8 + input_cost_per_token: 1.65e-7 + output_cost_per_token: 1.375e-6 input_cost_per_token: 3.3e-7 input_cost_per_token_batches: 1.65e-7 output_cost_per_token: 2.75e-6 output_cost_per_token_batches: 1.375e-6 + priority_pricing: + cache_read_input_token_cost: 5.94e-8 + input_cost_per_token: 5.94e-7 + output_cost_per_token: 4.95e-6 region: us - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 3e-8 + flex_pricing: + cache_read_input_token_cost: 1.5e-8 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.25e-6 input_cost_per_token: 3e-7 input_cost_per_token_batches: 1.5e-7 output_cost_per_token: 2.5e-6 output_cost_per_token_batches: 1.25e-6 + priority_pricing: + cache_read_input_token_cost: 5.4e-8 + input_cost_per_token: 5.4e-7 + output_cost_per_token: 4.5e-6 region: global - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 3.3e-8 + flex_pricing: + cache_read_input_token_cost: 1.65e-8 + input_cost_per_token: 1.65e-7 + output_cost_per_token: 1.375e-6 input_cost_per_token: 3.3e-7 input_cost_per_token_batches: 1.65e-7 output_cost_per_token: 2.75e-6 output_cost_per_token_batches: 1.375e-6 + priority_pricing: + cache_read_input_token_cost: 5.94e-8 + input_cost_per_token: 5.94e-7 + output_cost_per_token: 4.95e-6 region: eu features: - function_calling diff --git a/providers/google-vertex/google/gemini-3.5-flash.yaml b/providers/google-vertex/google/gemini-3.5-flash.yaml index 4260b44c60..f5d7212550 100644 --- a/providers/google-vertex/google/gemini-3.5-flash.yaml +++ b/providers/google-vertex/google/gemini-3.5-flash.yaml @@ -1,52 +1,115 @@ costs: - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: us - - cache_creation_input_token_cost_per_hour: 0.000001 + - cache_creation_input_token_cost_per_hour: 1e-6 cache_read_input_token_cost: 1.5e-7 - input_cost_per_token: 0.0000015 + flex_pricing: + cache_read_input_token_cost: 7.5e-8 + input_cost_per_token: 7.5e-7 + output_cost_per_token: 4.5e-6 + input_cost_per_token: 1.5e-6 input_cost_per_token_batches: 7.5e-7 - output_cost_per_token: 0.000009 - output_cost_per_token_batches: 0.0000045 + output_cost_per_token: 9e-6 + output_cost_per_token_batches: 4.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.7e-7 + input_cost_per_audio_token: 2.7e-6 + input_cost_per_token: 2.7e-6 + output_cost_per_token: 1.62e-5 region: global - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: europe-west2 - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: eu - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: asia-southeast1 - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: asia-south1 - - cache_creation_input_token_cost_per_hour: 0.0000011 + - cache_creation_input_token_cost_per_hour: 1.1e-6 cache_read_input_token_cost: 1.65e-7 - input_cost_per_token: 0.00000165 + flex_pricing: + cache_read_input_token_cost: 8.25e-8 + input_cost_per_token: 8.25e-7 + output_cost_per_token: 4.95e-6 + input_cost_per_token: 1.65e-6 input_cost_per_token_batches: 8.25e-7 - output_cost_per_token: 0.0000099 - output_cost_per_token_batches: 0.00000495 + output_cost_per_token: 9.9e-6 + output_cost_per_token_batches: 4.95e-6 + priority_pricing: + cache_read_input_token_cost: 2.97e-7 + input_cost_per_audio_token: 2.97e-6 + input_cost_per_token: 2.97e-6 + output_cost_per_token: 1.782e-5 region: asia-northeast1 features: - function_calling diff --git a/providers/google-vertex/google/gemini-3.6-flash.yaml b/providers/google-vertex/google/gemini-3.6-flash.yaml index 913aed287b..8b6651385f 100644 --- a/providers/google-vertex/google/gemini-3.6-flash.yaml +++ b/providers/google-vertex/google/gemini-3.6-flash.yaml @@ -1,24 +1,48 @@ costs: - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: us - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: global - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: eu features: - function_calling diff --git a/providers/google-vertex/google/gemini-3.7-flash.yaml b/providers/google-vertex/google/gemini-3.7-flash.yaml index 998d0b53dc..f47726cb6b 100644 --- a/providers/google-vertex/google/gemini-3.7-flash.yaml +++ b/providers/google-vertex/google/gemini-3.7-flash.yaml @@ -1,24 +1,48 @@ costs: - cache_creation_input_token_cost_per_hour: 5.5e-7 cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.0625e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.125e-6 output_cost_per_token_batches: 2.0625e-6 + priority_pricing: + cache_read_input_token_cost: 1.485e-7 + input_cost_per_token: 1.485e-6 + output_cost_per_token: 7.425e-6 region: us - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: global - cache_creation_input_token_cost_per_hour: 5.5e-7 cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.0625e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.125e-6 output_cost_per_token_batches: 2.0625e-6 + priority_pricing: + cache_read_input_token_cost: 1.485e-7 + input_cost_per_token: 1.485e-6 + output_cost_per_token: 7.425e-6 region: eu features: - function_calling diff --git a/providers/google-vertex/google/gemini-3.8-flash.yaml b/providers/google-vertex/google/gemini-3.8-flash.yaml index fe34e17b81..a65cba5216 100644 --- a/providers/google-vertex/google/gemini-3.8-flash.yaml +++ b/providers/google-vertex/google/gemini-3.8-flash.yaml @@ -1,24 +1,48 @@ costs: - cache_creation_input_token_cost_per_hour: 5.5e-7 cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.0625e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.125e-6 output_cost_per_token_batches: 2.0625e-6 + priority_pricing: + cache_read_input_token_cost: 1.485e-7 + input_cost_per_token: 1.485e-6 + output_cost_per_token: 7.425e-6 region: us - cache_creation_input_token_cost_per_hour: 5e-7 cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 1.875e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 output_cost_per_token: 3.75e-6 output_cost_per_token_batches: 1.875e-6 + priority_pricing: + cache_read_input_token_cost: 1.35e-7 + input_cost_per_token: 1.35e-6 + output_cost_per_token: 6.75e-6 region: global - cache_creation_input_token_cost_per_hour: 5.5e-7 cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.0625e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 output_cost_per_token: 4.125e-6 output_cost_per_token_batches: 2.0625e-6 + priority_pricing: + cache_read_input_token_cost: 1.485e-7 + input_cost_per_token: 1.485e-6 + output_cost_per_token: 7.425e-6 region: eu features: - function_calling diff --git a/providers/google-vertex/google/gemini-4-argon.yaml b/providers/google-vertex/google/gemini-4-argon.yaml index f5b1b622df..c230ae08e9 100644 --- a/providers/google-vertex/google/gemini-4-argon.yaml +++ b/providers/google-vertex/google/gemini-4-argon.yaml @@ -1,53 +1,80 @@ costs: - cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - input_cost_per_token_batches: 0.0000011 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + flex_pricing: + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 + input_cost_per_token: 2.2e-6 + input_cost_per_token_batches: 1.1e-6 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.98e-7 + input_cost_per_audio_token: 3.96e-6 + input_cost_per_token: 3.96e-6 + output_cost_per_token: 1.98e-5 region: us tiered_pricing: cache_read: - cost_per_token: 1.98e-7 from: 200000 input: - - cost_per_token: 0.00000396 + - cost_per_token: 3.96e-6 from: 200000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 200000 pricing_mode: cumulative - cache_read_input_token_cost: 1e-7 - input_cost_per_token: 0.000002 - input_cost_per_token_batches: 0.000001 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + flex_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 1e-6 + output_cost_per_token: 5e-6 + input_cost_per_token: 2e-6 + input_cost_per_token_batches: 1e-6 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 1.8e-7 + input_cost_per_audio_token: 3.6e-6 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 1.8e-5 region: global tiered_pricing: cache_read: - cost_per_token: 1.8e-7 from: 200000 input: - - cost_per_token: 0.0000036 + - cost_per_token: 3.6e-6 from: 200000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 200000 pricing_mode: cumulative - cache_read_input_token_cost: 1.1e-7 - input_cost_per_token: 0.0000022 - input_cost_per_token_batches: 0.0000011 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + flex_pricing: + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 + input_cost_per_token: 2.2e-6 + input_cost_per_token_batches: 1.1e-6 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.98e-7 + input_cost_per_audio_token: 3.96e-6 + input_cost_per_token: 3.96e-6 + output_cost_per_token: 1.98e-5 region: eu tiered_pricing: cache_read: - cost_per_token: 1.98e-7 from: 200000 input: - - cost_per_token: 0.00000396 + - cost_per_token: 3.96e-6 from: 200000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 200000 pricing_mode: cumulative features: diff --git a/providers/google-vertex/google/gemini-nano-banana-2.1.yaml b/providers/google-vertex/google/gemini-nano-banana-2.1.yaml index 9c4524c3fd..ea51c5de76 100644 --- a/providers/google-vertex/google/gemini-nano-banana-2.1.yaml +++ b/providers/google-vertex/google/gemini-nano-banana-2.1.yaml @@ -5,6 +5,10 @@ costs: output_cost_per_image_token: 3e-5 output_cost_per_token: 7.5e-6 output_cost_per_token_batches: 3.75e-6 + priority_pricing: + cache_read_input_token_cost: 2.7e-7 + input_cost_per_token: 2.7e-6 + output_cost_per_token: 1.35e-5 region: global features: - system_messages diff --git a/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml b/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml index a2fc3012e0..e5bb997ad1 100644 --- a/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml +++ b/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_us - cache_read_input_token_cost: 5e-7 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-4.1-mini-2025-04-14.yaml b/providers/microsoft-foundry/gpt-4.1-mini-2025-04-14.yaml index 538dce0613..b014759816 100644 --- a/providers/microsoft-foundry/gpt-4.1-mini-2025-04-14.yaml +++ b/providers/microsoft-foundry/gpt-4.1-mini-2025-04-14.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 2.2e-7 output_cost_per_token: 1.76e-6 output_cost_per_token_batches: 8.8e-7 + priority_pricing: + cache_read_input_token_cost: 1.925e-7 + input_cost_per_token: 7.7e-7 + output_cost_per_token: 3.08e-6 region: datazone_us - cache_read_input_token_cost: 1e-7 input_cost_per_token: 4e-7 input_cost_per_token_batches: 2e-7 output_cost_per_token: 1.6e-6 output_cost_per_token_batches: 8e-7 + priority_pricing: + cache_read_input_token_cost: 1.75e-7 + input_cost_per_token: 7e-7 + output_cost_per_token: 2.8e-6 region: "*" deprecationDate: "2026-10-14" features: diff --git a/providers/microsoft-foundry/gpt-4.1-mini.yaml b/providers/microsoft-foundry/gpt-4.1-mini.yaml index 9fb9a0e91a..8dec1bb98d 100644 --- a/providers/microsoft-foundry/gpt-4.1-mini.yaml +++ b/providers/microsoft-foundry/gpt-4.1-mini.yaml @@ -4,12 +4,20 @@ costs: input_cost_per_token_batches: 2.2e-7 output_cost_per_token: 1.76e-6 output_cost_per_token_batches: 8.8e-7 + priority_pricing: + cache_read_input_token_cost: 1.925e-7 + input_cost_per_token: 7.7e-7 + output_cost_per_token: 3.08e-6 region: datazone_us - cache_read_input_token_cost: 1e-7 input_cost_per_token: 4e-7 input_cost_per_token_batches: 2e-7 output_cost_per_token: 1.6e-6 output_cost_per_token_batches: 8e-7 + priority_pricing: + cache_read_input_token_cost: 1.75e-7 + input_cost_per_token: 7e-7 + output_cost_per_token: 2.8e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-4.1.yaml b/providers/microsoft-foundry/gpt-4.1.yaml index ec8c46f368..6496fa929d 100644 --- a/providers/microsoft-foundry/gpt-4.1.yaml +++ b/providers/microsoft-foundry/gpt-4.1.yaml @@ -4,18 +4,30 @@ costs: input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: global - cache_read_input_token_cost: 5.5e-7 input_cost_per_token: 2.2e-6 input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_us - cache_read_input_token_cost: 5.5e-7 input_cost_per_token: 2.2e-6 input_cost_per_token_batches: 1.1e-6 output_cost_per_token: 8.8e-6 output_cost_per_token_batches: 4.4e-6 + priority_pricing: + cache_read_input_token_cost: 9.625e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 1.54e-5 region: datazone_eu deprecationDate: "2026-10-14" features: diff --git a/providers/microsoft-foundry/gpt-5-2025-08-07.yaml b/providers/microsoft-foundry/gpt-5-2025-08-07.yaml index 1b992b779f..b9ccbebe94 100644 --- a/providers/microsoft-foundry/gpt-5-2025-08-07.yaml +++ b/providers/microsoft-foundry/gpt-5-2025-08-07.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml b/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml index 9189cffe02..b7587862d4 100644 --- a/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml +++ b/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml @@ -2,26 +2,42 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5-mini.yaml b/providers/microsoft-foundry/gpt-5-mini.yaml index 9aea6e0596..f789f12034 100644 --- a/providers/microsoft-foundry/gpt-5-mini.yaml +++ b/providers/microsoft-foundry/gpt-5-mini.yaml @@ -2,26 +2,42 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 input_cost_per_token_batches: 1.375e-7 - output_cost_per_token: 0.0000022 - output_cost_per_token_batches: 0.0000011 + output_cost_per_token: 2.2e-6 + output_cost_per_token_batches: 1.1e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml b/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml index 6d40aaf71d..5d255648cb 100644 --- a/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml +++ b/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml @@ -1,27 +1,43 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.1-codex-2025-11-13.yaml b/providers/microsoft-foundry/gpt-5.1-codex-2025-11-13.yaml index 1116373d5f..d080643677 100644 --- a/providers/microsoft-foundry/gpt-5.1-codex-2025-11-13.yaml +++ b/providers/microsoft-foundry/gpt-5.1-codex-2025-11-13.yaml @@ -1,19 +1,35 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.00001 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 - output_cost_per_token: 0.000011 + input_cost_per_token: 1.375e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 - output_cost_per_token: 0.000011 + input_cost_per_token: 1.375e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 - output_cost_per_token: 0.00001 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.1-codex-mini-2025-11-13.yaml b/providers/microsoft-foundry/gpt-5.1-codex-mini-2025-11-13.yaml index 9addd0fb53..904aaac8cd 100644 --- a/providers/microsoft-foundry/gpt-5.1-codex-mini-2025-11-13.yaml +++ b/providers/microsoft-foundry/gpt-5.1-codex-mini-2025-11-13.yaml @@ -1,19 +1,35 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 - output_cost_per_token: 0.000002 + output_cost_per_token: 2e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: global - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 - output_cost_per_token: 0.0000022 + output_cost_per_token: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_us - cache_read_input_token_cost: 2.75e-8 input_cost_per_token: 2.75e-7 - output_cost_per_token: 0.0000022 + output_cost_per_token: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 4.95e-8 + input_cost_per_token: 4.95e-7 + output_cost_per_token: 3.96e-6 region: datazone_eu - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 2.5e-7 - output_cost_per_token: 0.000002 + output_cost_per_token: 2e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.1.yaml b/providers/microsoft-foundry/gpt-5.1.yaml index ca05a76205..02a431f76b 100644 --- a/providers/microsoft-foundry/gpt-5.1.yaml +++ b/providers/microsoft-foundry/gpt-5.1.yaml @@ -1,27 +1,43 @@ costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: global - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml b/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml index ed3c549f44..c8a12cae89 100644 --- a/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml +++ b/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml @@ -1,9 +1,13 @@ costs: - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.2.yaml b/providers/microsoft-foundry/gpt-5.2.yaml index bd0472e965..49e78e31a7 100644 --- a/providers/microsoft-foundry/gpt-5.2.yaml +++ b/providers/microsoft-foundry/gpt-5.2.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_us - cache_read_input_token_cost: 1.925e-7 - input_cost_per_token: 0.000001925 + input_cost_per_token: 1.925e-6 input_cost_per_token_batches: 9.625e-7 - output_cost_per_token: 0.0000154 - output_cost_per_token_batches: 0.0000077 + output_cost_per_token: 1.54e-5 + output_cost_per_token_batches: 7.7e-6 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_eu - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.3-codex.yaml b/providers/microsoft-foundry/gpt-5.3-codex.yaml index f3e817ef5c..43c96f7a47 100644 --- a/providers/microsoft-foundry/gpt-5.3-codex.yaml +++ b/providers/microsoft-foundry/gpt-5.3-codex.yaml @@ -2,14 +2,26 @@ costs: - cache_read_input_token_cost: 1.925e-7 input_cost_per_token: 1.925e-6 output_cost_per_token: 1.54e-5 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_us - cache_read_input_token_cost: 1.925e-7 input_cost_per_token: 1.925e-6 output_cost_per_token: 1.54e-5 + priority_pricing: + cache_read_input_token_cost: 3.85e-7 + input_cost_per_token: 3.85e-6 + output_cost_per_token: 3.08e-5 region: datazone_eu - cache_read_input_token_cost: 1.75e-7 input_cost_per_token: 1.75e-6 output_cost_per_token: 1.4e-5 + priority_pricing: + cache_read_input_token_cost: 3.5e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml b/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml index 7720263bce..12ee53d9e6 100644 --- a/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml +++ b/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml @@ -1,25 +1,112 @@ costs: - cache_read_input_token_cost: 2.8e-7 - input_cost_per_token: 0.00000275 - output_cost_per_token: 0.0000165 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.75e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us - cache_read_input_token_cost: 2.8e-7 - input_cost_per_token: 0.00000275 - output_cost_per_token: 0.0000165 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.75e-6 + output_cost_per_token: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu - cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - output_cost_per_token: 0.000015 + flex_pricing: + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.5e-6 + output_cost_per_token: 1.5e-5 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 1e-5 + from: 272000 + output: + - cost_per_token: 4.5e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 5e-7 from: 272000 input: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 output: - - cost_per_token: 0.0000225 + - cost_per_token: 2.25e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/microsoft-foundry/gpt-5.4-mini-2026-03-17.yaml b/providers/microsoft-foundry/gpt-5.4-mini-2026-03-17.yaml index d7c673e05c..f2baa5665e 100644 --- a/providers/microsoft-foundry/gpt-5.4-mini-2026-03-17.yaml +++ b/providers/microsoft-foundry/gpt-5.4-mini-2026-03-17.yaml @@ -1,21 +1,45 @@ costs: - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 - output_cost_per_token: 0.00000495 - output_cost_per_token_batches: 0.000002475 + output_cost_per_token: 4.95e-6 + output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_us - cache_read_input_token_cost: 8.25e-8 + flex_pricing: + cache_read_input_token_cost: 4.125e-8 + input_cost_per_token: 4.125e-7 + output_cost_per_token: 2.475e-6 input_cost_per_token: 8.25e-7 input_cost_per_token_batches: 4.125e-7 - output_cost_per_token: 0.00000495 - output_cost_per_token_batches: 0.000002475 + output_cost_per_token: 4.95e-6 + output_cost_per_token_batches: 2.475e-6 + priority_pricing: + cache_read_input_token_cost: 1.65e-7 + input_cost_per_token: 1.65e-6 + output_cost_per_token: 9.9e-6 region: datazone_eu - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.0000045 - output_cost_per_token_batches: 0.00000225 + output_cost_per_token: 4.5e-6 + output_cost_per_token_batches: 2.25e-6 + priority_pricing: + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.4-mini.yaml b/providers/microsoft-foundry/gpt-5.4-mini.yaml index 84d8ee4fb3..0a03850652 100644 --- a/providers/microsoft-foundry/gpt-5.4-mini.yaml +++ b/providers/microsoft-foundry/gpt-5.4-mini.yaml @@ -1,7 +1,15 @@ costs: - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 output_cost_per_token: 4.5e-6 + priority_pricing: + cache_read_input_token_cost: 1.5e-7 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-5.4-nano-2026-03-17.yaml b/providers/microsoft-foundry/gpt-5.4-nano-2026-03-17.yaml index 718e63cf30..d0308d4456 100644 --- a/providers/microsoft-foundry/gpt-5.4-nano-2026-03-17.yaml +++ b/providers/microsoft-foundry/gpt-5.4-nano-2026-03-17.yaml @@ -1,20 +1,32 @@ costs: - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 - output_cost_per_token: 0.000001375 + output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_us - cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.875e-7 input_cost_per_token: 2.2e-7 input_cost_per_token_batches: 1.1e-7 - output_cost_per_token: 0.000001375 + output_cost_per_token: 1.375e-6 output_cost_per_token_batches: 6.875e-7 region: datazone_eu - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 - output_cost_per_token: 0.00000125 + output_cost_per_token: 1.25e-6 output_cost_per_token_batches: 6.25e-7 region: "*" features: diff --git a/providers/microsoft-foundry/gpt-5.4-nano.yaml b/providers/microsoft-foundry/gpt-5.4-nano.yaml index 90abc3d006..307bc1d3f6 100644 --- a/providers/microsoft-foundry/gpt-5.4-nano.yaml +++ b/providers/microsoft-foundry/gpt-5.4-nano.yaml @@ -1,5 +1,9 @@ costs: - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 output_cost_per_token: 1.25e-6 region: "*" diff --git a/providers/microsoft-foundry/gpt-5.4-pro-2026-03-05.yaml b/providers/microsoft-foundry/gpt-5.4-pro-2026-03-05.yaml index dc5ccb94a0..86c54b57cc 100644 --- a/providers/microsoft-foundry/gpt-5.4-pro-2026-03-05.yaml +++ b/providers/microsoft-foundry/gpt-5.4-pro-2026-03-05.yaml @@ -1,14 +1,25 @@ costs: - - cache_read_input_token_cost: 0.000003 - input_cost_per_token: 0.00003 + - cache_read_input_token_cost: 3e-6 + flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 output_cost_per_token: 0.00018 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/microsoft-foundry/gpt-5.4-pro.yaml b/providers/microsoft-foundry/gpt-5.4-pro.yaml index 62860c5de9..8295ded59f 100644 --- a/providers/microsoft-foundry/gpt-5.4-pro.yaml +++ b/providers/microsoft-foundry/gpt-5.4-pro.yaml @@ -1,14 +1,25 @@ costs: - - cache_read_input_token_cost: 0.000003 - input_cost_per_token: 0.00003 + - cache_read_input_token_cost: 3e-6 + flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 output_cost_per_token: 0.00018 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/microsoft-foundry/gpt-5.4.yaml b/providers/microsoft-foundry/gpt-5.4.yaml index 120ccb1770..34f79d2ff7 100644 --- a/providers/microsoft-foundry/gpt-5.4.yaml +++ b/providers/microsoft-foundry/gpt-5.4.yaml @@ -1,15 +1,102 @@ costs: - cache_read_input_token_cost: 2.8e-7 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.75e-6 output_cost_per_token: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us - cache_read_input_token_cost: 2.8e-7 + flex_pricing: + input_cost_per_token: 1.375e-6 + output_cost_per_token: 8.25e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.75e-6 + from: 272000 + output: + - cost_per_token: 1.2375e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.75e-6 output_cost_per_token: 1.65e-5 + priority_pricing: + cache_read_input_token_cost: 5.5e-7 + input_cost_per_token: 5.5e-6 + output_cost_per_token: 3.3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 1.1e-5 + from: 272000 + output: + - cost_per_token: 4.95e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu - cache_read_input_token_cost: 2.5e-7 + flex_pricing: + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.5e-6 output_cost_per_token: 1.5e-5 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 1e-5 + from: 272000 + output: + - cost_per_token: 4.5e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml b/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml index 7d1ddcb389..50393a53c6 100644 --- a/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml +++ b/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml @@ -1,7 +1,30 @@ costs: - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 output_cost_per_token: 3.3e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -15,8 +38,31 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 output_cost_per_token: 3.3e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -30,8 +76,31 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + tiered_pricing: + input: + - cost_per_token: 5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5e-6 output_cost_per_token: 3e-5 + priority_pricing: + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2e-6 + from: 272000 + input: + - cost_per_token: 2e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.5.yaml b/providers/microsoft-foundry/gpt-5.5.yaml index 740966f833..a7e0940472 100644 --- a/providers/microsoft-foundry/gpt-5.5.yaml +++ b/providers/microsoft-foundry/gpt-5.5.yaml @@ -1,7 +1,30 @@ costs: - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 output_cost_per_token: 3.3e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -15,8 +38,31 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5.5e-7 + flex_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + tiered_pricing: + input: + - cost_per_token: 5.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5.5e-6 output_cost_per_token: 3.3e-5 + priority_pricing: + cache_read_input_token_cost: 1.375e-6 + input_cost_per_token: 1.375e-5 + output_cost_per_token: 8.25e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-6 + from: 272000 + input: + - cost_per_token: 2.2e-5 + from: 272000 + output: + - cost_per_token: 9.9e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -30,8 +76,31 @@ costs: from: 272000 pricing_mode: cumulative - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + tiered_pricing: + input: + - cost_per_token: 5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 5e-6 output_cost_per_token: 3e-5 + priority_pricing: + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 2e-6 + from: 272000 + input: + - cost_per_token: 2e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.6-luna-2026-07-09.yaml b/providers/microsoft-foundry/gpt-5.6-luna-2026-07-09.yaml index bdbefe35d0..ee9075b81a 100644 --- a/providers/microsoft-foundry/gpt-5.6-luna-2026-07-09.yaml +++ b/providers/microsoft-foundry/gpt-5.6-luna-2026-07-09.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 - output_cost_per_token: 0.00000132 + output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -15,13 +53,51 @@ costs: - cost_per_token: 4.4e-7 from: 272000 output: - - cost_per_token: 0.00000198 + - cost_per_token: 1.98e-6 from: 272000 pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 - output_cost_per_token: 0.00000132 + output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -34,13 +110,51 @@ costs: - cost_per_token: 4.4e-7 from: 272000 output: - - cost_per_token: 0.00000198 + - cost_per_token: 1.98e-6 from: 272000 pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 - output_cost_per_token: 0.0000012 + output_cost_per_token: 1.2e-6 + priority_pricing: + cache_creation_input_token_cost: 5e-7 + cache_read_input_token_cost: 4e-8 + input_cost_per_token: 4e-7 + output_cost_per_token: 2.4e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 3.6e-6 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: @@ -53,7 +167,7 @@ costs: - cost_per_token: 4e-7 from: 272000 output: - - cost_per_token: 0.0000018 + - cost_per_token: 1.8e-6 from: 272000 pricing_mode: cumulative features: diff --git a/providers/microsoft-foundry/gpt-5.6-luna.yaml b/providers/microsoft-foundry/gpt-5.6-luna.yaml index 9ea96802df..d6356d3e05 100644 --- a/providers/microsoft-foundry/gpt-5.6-luna.yaml +++ b/providers/microsoft-foundry/gpt-5.6-luna.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + cache_creation_input_token_cost: 5e-7 + cache_read_input_token_cost: 4e-8 + input_cost_per_token: 4e-7 + output_cost_per_token: 2.4e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 3.6e-6 + from: 272000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-7 cache_read_input_token_cost: 2.2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.375e-7 + cache_read_input_token_cost: 1.1e-8 + input_cost_per_token: 1.1e-7 + output_cost_per_token: 6.6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.75e-7 + from: 272000 + input: + - cost_per_token: 2.2e-7 + from: 272000 + output: + - cost_per_token: 9.9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-7 output_cost_per_token: 1.32e-6 + priority_pricing: + cache_creation_input_token_cost: 5.5e-7 + cache_read_input_token_cost: 4.4e-8 + input_cost_per_token: 4.4e-7 + output_cost_per_token: 2.64e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-8 + from: 272000 + cache_write: + - cost_per_token: 1.1e-6 + from: 272000 + input: + - cost_per_token: 8.8e-7 + from: 272000 + output: + - cost_per_token: 3.96e-6 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -58,8 +172,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_creation_input_token_cost: 1.25e-7 + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6e-7 + tiered_pricing: + cache_read: + - cost_per_token: 2e-8 + from: 272000 + cache_write: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2e-7 + from: 272000 + output: + - cost_per_token: 9e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-7 output_cost_per_token: 1.2e-6 + priority_pricing: + cache_creation_input_token_cost: 5e-7 + cache_read_input_token_cost: 4e-8 + input_cost_per_token: 4e-7 + output_cost_per_token: 2.4e-6 + tiered_pricing: + cache_read: + - cost_per_token: 8e-8 + from: 272000 + cache_write: + - cost_per_token: 1e-6 + from: 272000 + input: + - cost_per_token: 8e-7 + from: 272000 + output: + - cost_per_token: 3.6e-6 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.6-sol-2026-07-09.yaml b/providers/microsoft-foundry/gpt-5.6-sol-2026-07-09.yaml index 6ba4c3c221..fd09d53007 100644 --- a/providers/microsoft-foundry/gpt-5.6-sol-2026-07-09.yaml +++ b/providers/microsoft-foundry/gpt-5.6-sol-2026-07-09.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5e-6 cache_read_input_token_cost: 4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.5e-6 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 5e-6 + from: 272000 + input: + - cost_per_token: 4e-6 + from: 272000 + output: + - cost_per_token: 1.5e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4e-6 output_cost_per_token: 2e-5 + priority_pricing: + cache_creation_input_token_cost: 1e-5 + cache_read_input_token_cost: 8e-7 + input_cost_per_token: 8e-6 + output_cost_per_token: 4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.6e-6 + from: 272000 + cache_write: + - cost_per_token: 2e-5 + from: 272000 + input: + - cost_per_token: 1.6e-5 + from: 272000 + output: + - cost_per_token: 6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.6-sol.yaml b/providers/microsoft-foundry/gpt-5.6-sol.yaml index bb09d1f1e2..2652cc908f 100644 --- a/providers/microsoft-foundry/gpt-5.6-sol.yaml +++ b/providers/microsoft-foundry/gpt-5.6-sol.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5.5e-6 cache_read_input_token_cost: 4.4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.75e-6 + cache_read_input_token_cost: 2.2e-7 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4.4e-7 + from: 272000 + cache_write: + - cost_per_token: 5.5e-6 + from: 272000 + input: + - cost_per_token: 4.4e-6 + from: 272000 + output: + - cost_per_token: 1.65e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4.4e-6 output_cost_per_token: 2.2e-5 + priority_pricing: + cache_creation_input_token_cost: 1.1e-5 + cache_read_input_token_cost: 8.8e-7 + input_cost_per_token: 8.8e-6 + output_cost_per_token: 4.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.76e-6 + from: 272000 + cache_write: + - cost_per_token: 2.2e-5 + from: 272000 + input: + - cost_per_token: 1.76e-5 + from: 272000 + output: + - cost_per_token: 6.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 5e-6 cache_read_input_token_cost: 4e-7 + flex_pricing: + cache_creation_input_token_cost: 2.5e-6 + cache_read_input_token_cost: 2e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 5e-6 + from: 272000 + input: + - cost_per_token: 4e-6 + from: 272000 + output: + - cost_per_token: 1.5e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 4e-6 output_cost_per_token: 2e-5 + priority_pricing: + cache_creation_input_token_cost: 1e-5 + cache_read_input_token_cost: 8e-7 + input_cost_per_token: 8e-6 + output_cost_per_token: 4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.6e-6 + from: 272000 + cache_write: + - cost_per_token: 2e-5 + from: 272000 + input: + - cost_per_token: 1.6e-5 + from: 272000 + output: + - cost_per_token: 6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.6-terra-2026-07-09.yaml b/providers/microsoft-foundry/gpt-5.6-terra-2026-07-09.yaml index f1994d6666..c703d1bc68 100644 --- a/providers/microsoft-foundry/gpt-5.6-terra-2026-07-09.yaml +++ b/providers/microsoft-foundry/gpt-5.6-terra-2026-07-09.yaml @@ -1,59 +1,173 @@ costs: - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000132 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.0000132 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000198 + - cost_per_token: 1.98e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.000012 + flex_pricing: + cache_creation_input_token_cost: 1.25e-6 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.5e-6 + from: 272000 + input: + - cost_per_token: 2e-6 + from: 272000 + output: + - cost_per_token: 9e-6 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/microsoft-foundry/gpt-5.6-terra.yaml b/providers/microsoft-foundry/gpt-5.6-terra.yaml index 0fe4b59d76..993297ae51 100644 --- a/providers/microsoft-foundry/gpt-5.6-terra.yaml +++ b/providers/microsoft-foundry/gpt-5.6-terra.yaml @@ -1,8 +1,46 @@ costs: - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-6 output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: @@ -20,8 +58,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 1.1e-7 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 6.6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.75e-6 + from: 272000 + input: + - cost_per_token: 2.2e-6 + from: 272000 + output: + - cost_per_token: 9.9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2.2e-6 output_cost_per_token: 1.32e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.64e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.96e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: @@ -39,8 +115,46 @@ costs: pricing_mode: cumulative - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 + flex_pricing: + cache_creation_input_token_cost: 1.25e-6 + cache_read_input_token_cost: 1e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 6e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2e-7 + from: 272000 + cache_write: + - cost_per_token: 2.5e-6 + from: 272000 + input: + - cost_per_token: 2e-6 + from: 272000 + output: + - cost_per_token: 9e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-6 output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/microsoft-foundry/gpt-5.yaml b/providers/microsoft-foundry/gpt-5.yaml index 6f87f664e3..8c61bdb48c 100644 --- a/providers/microsoft-foundry/gpt-5.yaml +++ b/providers/microsoft-foundry/gpt-5.yaml @@ -1,21 +1,33 @@ costs: - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_us - cache_read_input_token_cost: 1.375e-7 - input_cost_per_token: 0.000001375 + input_cost_per_token: 1.375e-6 input_cost_per_token_batches: 6.875e-7 - output_cost_per_token: 0.000011 - output_cost_per_token_batches: 0.0000055 + output_cost_per_token: 1.1e-5 + output_cost_per_token_batches: 5.5e-6 + priority_pricing: + cache_read_input_token_cost: 2.75e-7 + input_cost_per_token: 2.75e-6 + output_cost_per_token: 2.2e-5 region: datazone_eu - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" features: - function_calling diff --git a/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml b/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml index eb0b2363c0..66695c7417 100644 --- a/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml +++ b/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml @@ -1,78 +1,154 @@ costs: - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.3e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.000003 + - cache_creation_input_token_cost: 3e-6 cache_read_input_token_cost: 2.4e-7 - input_cost_per_token: 0.0000024 - output_cost_per_token: 0.000012 + input_cost_per_token: 2.4e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 6e-6 + cache_read_input_token_cost: 4.8e-7 + input_cost_per_token: 4.8e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 9.6e-7 + from: 272000 + cache_write: + - cost_per_token: 1.2e-5 + from: 272000 + input: + - cost_per_token: 9.6e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.0000048 + - cost_per_token: 4.8e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/microsoft-foundry/gpt-6-sol.yaml b/providers/microsoft-foundry/gpt-6-sol.yaml index bc090cb7d7..892ae59b9f 100644 --- a/providers/microsoft-foundry/gpt-6-sol.yaml +++ b/providers/microsoft-foundry/gpt-6-sol.yaml @@ -1,78 +1,154 @@ costs: - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: global tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.00000275 + - cache_creation_input_token_cost: 2.75e-6 cache_read_input_token_cost: 2.2e-7 - input_cost_per_token: 0.0000022 - output_cost_per_token: 0.000011 + input_cost_per_token: 2.2e-6 + output_cost_per_token: 1.1e-5 + priority_pricing: + cache_creation_input_token_cost: 5.5e-6 + cache_read_input_token_cost: 4.4e-7 + input_cost_per_token: 4.4e-6 + output_cost_per_token: 2.2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8.8e-7 + from: 272000 + cache_write: + - cost_per_token: 1.1e-5 + from: 272000 + input: + - cost_per_token: 8.8e-6 + from: 272000 + output: + - cost_per_token: 3.3e-5 + from: 272000 + pricing_mode: cumulative region: datazone_us tiered_pricing: cache_read: - cost_per_token: 4.4e-7 from: 272000 cache_write: - - cost_per_token: 0.0000055 + - cost_per_token: 5.5e-6 from: 272000 input: - - cost_per_token: 0.0000044 + - cost_per_token: 4.4e-6 from: 272000 output: - - cost_per_token: 0.0000165 + - cost_per_token: 1.65e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.000003 + - cache_creation_input_token_cost: 3e-6 cache_read_input_token_cost: 2.4e-7 - input_cost_per_token: 0.0000024 - output_cost_per_token: 0.000012 + input_cost_per_token: 2.4e-6 + output_cost_per_token: 1.2e-5 + priority_pricing: + cache_creation_input_token_cost: 6e-6 + cache_read_input_token_cost: 4.8e-7 + input_cost_per_token: 4.8e-6 + output_cost_per_token: 2.4e-5 + tiered_pricing: + cache_read: + - cost_per_token: 9.6e-7 + from: 272000 + cache_write: + - cost_per_token: 1.2e-5 + from: 272000 + input: + - cost_per_token: 9.6e-6 + from: 272000 + output: + - cost_per_token: 3.6e-5 + from: 272000 + pricing_mode: cumulative region: datazone_eu tiered_pricing: cache_read: - cost_per_token: 4.8e-7 from: 272000 cache_write: - - cost_per_token: 0.000006 + - cost_per_token: 6e-6 from: 272000 input: - - cost_per_token: 0.0000048 + - cost_per_token: 4.8e-6 from: 272000 output: - - cost_per_token: 0.000018 + - cost_per_token: 1.8e-5 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 0.0000025 + - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 2e-7 - input_cost_per_token: 0.000002 - output_cost_per_token: 0.00001 + input_cost_per_token: 2e-6 + output_cost_per_token: 1e-5 + priority_pricing: + cache_creation_input_token_cost: 5e-6 + cache_read_input_token_cost: 4e-7 + input_cost_per_token: 4e-6 + output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 8e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - cost_per_token: 4e-7 from: 272000 cache_write: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 input: - - cost_per_token: 0.000004 + - cost_per_token: 4e-6 from: 272000 output: - - cost_per_token: 0.000015 + - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative features: diff --git a/providers/truefoundry-managed/gpt-6-astra.yaml b/providers/truefoundry-managed/gpt-6-astra.yaml index 87fd33d394..59a42e2bff 100644 --- a/providers/truefoundry-managed/gpt-6-astra.yaml +++ b/providers/truefoundry-managed/gpt-6-astra.yaml @@ -1,30 +1,82 @@ costs: - - cache_creation_input_token_cost: 0.0000125 + - cache_creation_input_token_cost: 1.25e-5 cache_read_input_token_cost: 1e-6 + flex_pricing: + cache_creation_input_token_cost: 6.25e-6 + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 5e-6 + output_cost_per_token: 2.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-6 + from: 272000 + cache_write: + - cost_per_token: 1.25e-5 + from: 272000 + input: + - cost_per_token: 1e-5 + from: 272000 + output: + - cost_per_token: 3.75e-5 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 1e-5 - input_cost_per_token_batches: 0.000005 + input_cost_per_token_batches: 5e-6 output_cost_per_token: 5e-5 - output_cost_per_token_batches: 0.000025 + output_cost_per_token_batches: 2.5e-5 priority_pricing: - cache_creation_input_token_cost: 0.000025 - cache_read_input_token_cost: 0.000002 - input_cost_per_token: 0.000020 - output_cost_per_token: 0.000100 + cache_creation_input_token_cost: 2.5e-5 + cache_read_input_token_cost: 2e-6 + input_cost_per_token: 2e-5 + output_cost_per_token: 0.0001 + tiered_pricing: + cache_read: + - cost_per_token: 4e-6 + from: 272000 + cache_write: + - cost_per_token: 5e-5 + from: 272000 + input: + - cost_per_token: 4e-5 + from: 272000 + output: + - cost_per_token: 0.00015 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000002 + - cost_per_token: 2e-6 from: 272000 cache_write: - - cost_per_token: 0.000025 + - cost_per_token: 2.5e-5 from: 272000 input: - - cost_per_token: 0.000020 + - cost_per_token: 2e-5 from: 272000 output: - - cost_per_token: 0.000075 + - cost_per_token: 7.5e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 7.5e-5 + cache_read_input_token_cost: 6e-6 + input_cost_per_token: 6e-5 + output_cost_per_token: 0.0003 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-5 + from: 272000 + cache_write: + - cost_per_token: 0.00015 + from: 272000 + input: + - cost_per_token: 0.00012 + from: 272000 + output: + - cost_per_token: 0.00045 + from: 272000 + pricing_mode: cumulative features: - function_calling - structured_output diff --git a/providers/truefoundry-managed/gpt-6-luna.yaml b/providers/truefoundry-managed/gpt-6-luna.yaml index ab643158f6..3cf984d72d 100644 --- a/providers/truefoundry-managed/gpt-6-luna.yaml +++ b/providers/truefoundry-managed/gpt-6-luna.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 1.25e-7 cache_read_input_token_cost: 1e-8 + flex_pricing: + cache_creation_input_token_cost: 6.25e-8 + cache_read_input_token_cost: 5e-9 + input_cost_per_token: 5e-8 + output_cost_per_token: 2.5e-7 + tiered_pricing: + cache_read: + - cost_per_token: 1e-8 + from: 272000 + cache_write: + - cost_per_token: 1.25e-7 + from: 272000 + input: + - cost_per_token: 1e-7 + from: 272000 + output: + - cost_per_token: 3.75e-7 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 1e-7 input_cost_per_token_batches: 5e-8 output_cost_per_token: 5e-7 @@ -9,7 +28,21 @@ costs: cache_creation_input_token_cost: 2.5e-7 cache_read_input_token_cost: 2e-8 input_cost_per_token: 2e-7 - output_cost_per_token: 0.000001 + output_cost_per_token: 1e-6 + tiered_pricing: + cache_read: + - cost_per_token: 4e-8 + from: 272000 + cache_write: + - cost_per_token: 5e-7 + from: 272000 + input: + - cost_per_token: 4e-7 + from: 272000 + output: + - cost_per_token: 1.5e-6 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: diff --git a/providers/truefoundry-managed/gpt-6.1-sol.yaml b/providers/truefoundry-managed/gpt-6.1-sol.yaml index 8e6e5dae55..1f01831094 100644 --- a/providers/truefoundry-managed/gpt-6.1-sol.yaml +++ b/providers/truefoundry-managed/gpt-6.1-sol.yaml @@ -1,6 +1,25 @@ costs: - cache_creation_input_token_cost: 2.5e-6 cache_read_input_token_cost: 1e-7 + flex_pricing: + cache_creation_input_token_cost: 1.25e-6 + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 1e-6 + output_cost_per_token: 5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 1e-7 + from: 272000 + cache_write: + - cost_per_token: 2.5e-6 + from: 272000 + input: + - cost_per_token: 2e-6 + from: 272000 + output: + - cost_per_token: 7.5e-6 + from: 272000 + pricing_mode: cumulative input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_token: 1e-5 @@ -10,6 +29,20 @@ costs: cache_read_input_token_cost: 2e-7 input_cost_per_token: 4e-6 output_cost_per_token: 2e-5 + tiered_pricing: + cache_read: + - cost_per_token: 4e-7 + from: 272000 + cache_write: + - cost_per_token: 1e-5 + from: 272000 + input: + - cost_per_token: 8e-6 + from: 272000 + output: + - cost_per_token: 3e-5 + from: 272000 + pricing_mode: cumulative region: "*" tiered_pricing: cache_read: @@ -25,6 +58,25 @@ costs: - cost_per_token: 1.5e-5 from: 272000 pricing_mode: cumulative + ultrafast_pricing: + cache_creation_input_token_cost: 1.5e-5 + cache_read_input_token_cost: 6e-7 + input_cost_per_token: 1.2e-5 + output_cost_per_token: 6e-5 + tiered_pricing: + cache_read: + - cost_per_token: 1.2e-6 + from: 272000 + cache_write: + - cost_per_token: 3e-5 + from: 272000 + input: + - cost_per_token: 2.4e-5 + from: 272000 + output: + - cost_per_token: 9e-5 + from: 272000 + pricing_mode: cumulative features: - function_calling - parallel_function_calling From 5fd748c11b95807e5d7d686ac01cfd3314f33b6b Mon Sep 17 00:00:00 2001 From: Archit Kumar <108719922+Archit-Kumar-16@users.noreply.github.com> Date: Thu, 22 Oct 2026 16:41:14 +0530 Subject: [PATCH 4/4] Fix Flex/Priority rates that did not match same-row Standard, and add missing OpenAI overlays from LiteLLM. Co-authored-by: Cursor --- .../qwen.qwen3-next-80b-a3b-instruct.yaml | 66 +++++------ providers/aws-bedrock/us.zai.glm-5.3.yaml | 112 +++++++++--------- providers/google-gemini/gemini-4-argon.yaml | 8 ++ .../gemini-flash-lite-latest.yaml | 9 +- providers/openai/gpt-4.1-nano-2025-04-14.yaml | 4 + providers/openai/gpt-4.1-nano.yaml | 4 + providers/openai/gpt-4o-2024-05-13.yaml | 3 + providers/openai/gpt-4o-2024-08-06.yaml | 4 + providers/openai/gpt-4o-mini-2024-07-18.yaml | 4 + providers/openai/gpt-5-2025-08-07.yaml | 8 ++ providers/openai/gpt-5-mini-2025-08-07.yaml | 8 ++ providers/openai/gpt-5-mini.yaml | 10 +- providers/openai/gpt-5-nano-2025-08-07.yaml | 4 + providers/openai/gpt-5-nano.yaml | 4 + providers/openai/gpt-5.1-2025-11-13.yaml | 14 ++- providers/openai/gpt-5.1.yaml | 14 ++- providers/openai/gpt-5.2-2025-12-11.yaml | 14 ++- providers/openai/gpt-5.2.yaml | 14 ++- providers/openai/gpt-5.4-2026-03-05.yaml | 31 +++-- providers/openai/gpt-5.4-mini-2026-03-17.yaml | 12 +- providers/openai/gpt-5.4-mini.yaml | 12 +- providers/openai/gpt-5.4-nano-2026-03-17.yaml | 6 +- providers/openai/gpt-5.4-nano.yaml | 6 +- providers/openai/gpt-5.4-pro-2026-03-05.yaml | 19 ++- providers/openai/gpt-5.4-pro.yaml | 19 ++- providers/openai/gpt-5.4.yaml | 31 +++-- providers/openai/gpt-5.5-2026-04-23.yaml | 35 ++++-- providers/openai/gpt-5.5-pro-2026-04-23.yaml | 11 +- providers/openai/gpt-5.5-pro.yaml | 11 +- providers/openai/gpt-5.5.yaml | 33 ++++-- providers/openai/gpt-5.yaml | 4 + providers/openai/o3-2025-04-16.yaml | 8 ++ providers/openai/o3.yaml | 8 ++ providers/openai/o4-mini-2025-04-16.yaml | 8 ++ providers/openai/o4-mini.yaml | 8 ++ 35 files changed, 391 insertions(+), 175 deletions(-) diff --git a/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml index 44cbc79e00..fa16a366c0 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-next-80b-a3b-instruct.yaml @@ -2,66 +2,66 @@ canonical_model: alibaba/qwen3-next-80b-a3b-instruct costs: - flex_pricing: input_cost_per_token: 7.5e-8 - output_cost_per_token: 6.42857142857143e-7 + output_cost_per_token: 6e-7 input_cost_per_token: 1.5e-7 output_cost_per_token: 1.2e-6 priority_pricing: - input_cost_per_token: 2.78571428571429e-7 - output_cost_per_token: 2.25e-6 + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-6 region: us-west-2 - flex_pricing: input_cost_per_token: 7.5e-8 - output_cost_per_token: 6.42857142857143e-7 + output_cost_per_token: 6e-7 input_cost_per_token: 1.5e-7 output_cost_per_token: 1.2e-6 priority_pricing: - input_cost_per_token: 2.78571428571429e-7 - output_cost_per_token: 2.25e-6 + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-6 region: us-east-2 - flex_pricing: input_cost_per_token: 7.5e-8 - output_cost_per_token: 6.42857142857143e-7 + output_cost_per_token: 6e-7 input_cost_per_token: 1.5e-7 output_cost_per_token: 1.2e-6 priority_pricing: - input_cost_per_token: 2.78571428571429e-7 - output_cost_per_token: 2.25e-6 + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-6 region: us-east-1 - flex_pricing: input_cost_per_token: 9e-8 - output_cost_per_token: 7.71428571428571e-7 + output_cost_per_token: 7.25e-7 input_cost_per_token: 1.8e-7 output_cost_per_token: 1.45e-6 priority_pricing: - input_cost_per_token: 3.34285714285714e-7 - output_cost_per_token: 2.7e-6 + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.5375e-6 region: sa-east-1 - flex_pricing: input_cost_per_token: 1.15e-7 - output_cost_per_token: 9.85714285714286e-7 + output_cost_per_token: 9.3e-7 input_cost_per_token: 2.3e-7 output_cost_per_token: 1.86e-6 priority_pricing: - input_cost_per_token: 4.27142857142857e-7 - output_cost_per_token: 3.45e-6 + input_cost_per_token: 4.025e-7 + output_cost_per_token: 3.255e-6 region: eu-west-2 - flex_pricing: input_cost_per_token: 9e-8 - output_cost_per_token: 7.71428571428571e-7 + output_cost_per_token: 7.05e-7 input_cost_per_token: 1.8e-7 output_cost_per_token: 1.41e-6 priority_pricing: - input_cost_per_token: 3.34285714285714e-7 - output_cost_per_token: 2.7e-6 + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-6 region: eu-west-1 - flex_pricing: input_cost_per_token: 9e-8 - output_cost_per_token: 7.71428571428571e-7 + output_cost_per_token: 7.05e-7 input_cost_per_token: 1.8e-7 output_cost_per_token: 1.41e-6 priority_pricing: - input_cost_per_token: 3.34285714285714e-7 - output_cost_per_token: 2.7e-6 + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-6 region: eu-south-1 - flex_pricing: input_cost_per_token: 8.4e-8 @@ -69,7 +69,7 @@ costs: input_cost_per_token: 1.68e-7 output_cost_per_token: 1.44e-6 priority_pricing: - input_cost_per_token: 3.12e-7 + input_cost_per_token: 2.94e-7 output_cost_per_token: 2.52e-6 region: eu-north-1 - flex_pricing: @@ -78,7 +78,7 @@ costs: input_cost_per_token: 1.68e-7 output_cost_per_token: 1.44e-6 priority_pricing: - input_cost_per_token: 3.12e-7 + input_cost_per_token: 2.94e-7 output_cost_per_token: 2.52e-6 region: eu-central-1 - flex_pricing: @@ -87,35 +87,35 @@ costs: input_cost_per_token: 1.68e-7 output_cost_per_token: 1.44e-6 priority_pricing: - input_cost_per_token: 3.12e-7 + input_cost_per_token: 2.94e-7 output_cost_per_token: 2.52e-6 region: ap-southeast-3 - flex_pricing: input_cost_per_token: 7.725e-8 - output_cost_per_token: 6.62142857142857e-7 + output_cost_per_token: 6.18e-7 input_cost_per_token: 1.545e-7 output_cost_per_token: 1.236e-6 priority_pricing: - input_cost_per_token: 2.86928571428571e-7 - output_cost_per_token: 2.3175e-6 + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 2.163e-6 region: ap-southeast-2 - flex_pricing: input_cost_per_token: 9e-8 - output_cost_per_token: 7.71428571428571e-7 + output_cost_per_token: 7.05e-7 input_cost_per_token: 1.8e-7 output_cost_per_token: 1.41e-6 priority_pricing: - input_cost_per_token: 3.34285714285714e-7 - output_cost_per_token: 2.7e-6 + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-6 region: ap-south-1 - flex_pricing: input_cost_per_token: 9e-8 - output_cost_per_token: 7.71428571428571e-7 + output_cost_per_token: 7.25e-7 input_cost_per_token: 1.8e-7 output_cost_per_token: 1.45e-6 priority_pricing: - input_cost_per_token: 3.34285714285714e-7 - output_cost_per_token: 2.7e-6 + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.5375e-6 region: ap-northeast-1 external_ids: artificial_analysis_id: 2698f6c6-e436-47ce-a583-dbc25596c571 diff --git a/providers/aws-bedrock/us.zai.glm-5.3.yaml b/providers/aws-bedrock/us.zai.glm-5.3.yaml index 50c77115fa..a38380a597 100644 --- a/providers/aws-bedrock/us.zai.glm-5.3.yaml +++ b/providers/aws-bedrock/us.zai.glm-5.3.yaml @@ -1,72 +1,72 @@ canonical_model: zai/glm-5-3 costs: - - cache_creation_input_token_cost: 4.125e-6 - cache_read_input_token_cost: 3.3e-7 + - cache_creation_input_token_cost: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 flex_pricing: - cache_creation_input_token_cost: 2.0625e-6 - cache_read_input_token_cost: 3.06428571428571e-7 - input_cost_per_token: 1.65e-6 - output_cost_per_token: 5.18571428571429e-6 - input_cost_per_token: 3.3e-6 - input_cost_per_token_batches: 1.65e-6 - output_cost_per_token: 1.65e-5 - output_cost_per_token_batches: 8.25e-6 + cache_creation_input_token_cost: 1.155e-6 + cache_read_input_token_cost: 1.716e-7 + input_cost_per_token: 9.24e-7 + output_cost_per_token: 2.904e-6 + input_cost_per_token: 1.848e-6 + input_cost_per_token_batches: 9.24e-7 + output_cost_per_token: 5.808e-6 + output_cost_per_token_batches: 2.904e-6 priority_pricing: - cache_creation_input_token_cost: 7.21875e-6 - cache_read_input_token_cost: 1.0725e-6 - input_cost_per_token: 5.775e-6 - output_cost_per_token: 1.815e-5 + cache_creation_input_token_cost: 4.0425e-6 + cache_read_input_token_cost: 6.006e-7 + input_cost_per_token: 3.234e-6 + output_cost_per_token: 1.0164e-5 region: us-west-2 - - cache_creation_input_token_cost: 4.125e-6 - cache_read_input_token_cost: 3.3e-7 + - cache_creation_input_token_cost: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 flex_pricing: - cache_creation_input_token_cost: 2.0625e-6 - cache_read_input_token_cost: 3.06428571428571e-7 - input_cost_per_token: 1.65e-6 - output_cost_per_token: 5.18571428571429e-6 - input_cost_per_token: 3.3e-6 - input_cost_per_token_batches: 1.65e-6 - output_cost_per_token: 1.65e-5 - output_cost_per_token_batches: 8.25e-6 + cache_creation_input_token_cost: 1.155e-6 + cache_read_input_token_cost: 1.716e-7 + input_cost_per_token: 9.24e-7 + output_cost_per_token: 2.904e-6 + input_cost_per_token: 1.848e-6 + input_cost_per_token_batches: 9.24e-7 + output_cost_per_token: 5.808e-6 + output_cost_per_token_batches: 2.904e-6 priority_pricing: - cache_creation_input_token_cost: 7.21875e-6 - cache_read_input_token_cost: 1.0725e-6 - input_cost_per_token: 5.775e-6 - output_cost_per_token: 1.815e-5 + cache_creation_input_token_cost: 4.0425e-6 + cache_read_input_token_cost: 6.006e-7 + input_cost_per_token: 3.234e-6 + output_cost_per_token: 1.0164e-5 region: us-west-1 - - cache_creation_input_token_cost: 4.125e-6 - cache_read_input_token_cost: 3.3e-7 + - cache_creation_input_token_cost: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 flex_pricing: - cache_creation_input_token_cost: 2.0625e-6 - cache_read_input_token_cost: 3.06428571428571e-7 - input_cost_per_token: 1.65e-6 - output_cost_per_token: 5.18571428571429e-6 - input_cost_per_token: 3.3e-6 - input_cost_per_token_batches: 1.65e-6 - output_cost_per_token: 1.65e-5 - output_cost_per_token_batches: 8.25e-6 + cache_creation_input_token_cost: 1.155e-6 + cache_read_input_token_cost: 1.716e-7 + input_cost_per_token: 9.24e-7 + output_cost_per_token: 2.904e-6 + input_cost_per_token: 1.848e-6 + input_cost_per_token_batches: 9.24e-7 + output_cost_per_token: 5.808e-6 + output_cost_per_token_batches: 2.904e-6 priority_pricing: - cache_creation_input_token_cost: 7.21875e-6 - cache_read_input_token_cost: 1.0725e-6 - input_cost_per_token: 5.775e-6 - output_cost_per_token: 1.815e-5 + cache_creation_input_token_cost: 4.0425e-6 + cache_read_input_token_cost: 6.006e-7 + input_cost_per_token: 3.234e-6 + output_cost_per_token: 1.0164e-5 region: us-east-2 - - cache_creation_input_token_cost: 4.125e-6 - cache_read_input_token_cost: 3.3e-7 + - cache_creation_input_token_cost: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 flex_pricing: - cache_creation_input_token_cost: 2.0625e-6 - cache_read_input_token_cost: 3.06428571428571e-7 - input_cost_per_token: 1.65e-6 - output_cost_per_token: 5.18571428571429e-6 - input_cost_per_token: 3.3e-6 - input_cost_per_token_batches: 1.65e-6 - output_cost_per_token: 1.65e-5 - output_cost_per_token_batches: 8.25e-6 + cache_creation_input_token_cost: 1.155e-6 + cache_read_input_token_cost: 1.716e-7 + input_cost_per_token: 9.24e-7 + output_cost_per_token: 2.904e-6 + input_cost_per_token: 1.848e-6 + input_cost_per_token_batches: 9.24e-7 + output_cost_per_token: 5.808e-6 + output_cost_per_token_batches: 2.904e-6 priority_pricing: - cache_creation_input_token_cost: 7.21875e-6 - cache_read_input_token_cost: 1.0725e-6 - input_cost_per_token: 5.775e-6 - output_cost_per_token: 1.815e-5 + cache_creation_input_token_cost: 4.0425e-6 + cache_read_input_token_cost: 6.006e-7 + input_cost_per_token: 3.234e-6 + output_cost_per_token: 1.0164e-5 region: us-east-1 external_ids: artificial_analysis_id: cd684ea4-b475-4269-b001-d469d06d8a7a diff --git a/providers/google-gemini/gemini-4-argon.yaml b/providers/google-gemini/gemini-4-argon.yaml index 3f586c2af8..2bb8f9f1cc 100644 --- a/providers/google-gemini/gemini-4-argon.yaml +++ b/providers/google-gemini/gemini-4-argon.yaml @@ -1,7 +1,15 @@ costs: - cache_read_input_token_cost: 1e-7 + flex_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 1e-6 + output_cost_per_token: 5e-6 input_cost_per_token: 2e-6 output_cost_per_token: 1e-5 + priority_pricing: + cache_read_input_token_cost: 1.8e-7 + input_cost_per_token: 3.6e-6 + output_cost_per_token: 1.8e-5 region: "*" features: - code_execution diff --git a/providers/google-gemini/gemini-flash-lite-latest.yaml b/providers/google-gemini/gemini-flash-lite-latest.yaml index a8a5264045..c9130e474f 100644 --- a/providers/google-gemini/gemini-flash-lite-latest.yaml +++ b/providers/google-gemini/gemini-flash-lite-latest.yaml @@ -4,18 +4,19 @@ costs: cache_read_input_audio_token_cost: 5e-8 cache_read_input_token_cost: 2.5e-8 flex_pricing: - cache_read_input_token_cost: 1.66666666666667e-8 + cache_read_input_token_cost: 1.25e-8 input_cost_per_token: 1.25e-7 - output_cost_per_token: 1.04166666666667e-6 + output_cost_per_token: 7.5e-7 input_cost_per_audio_token: 5e-7 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 output_cost_per_token: 1.5e-6 output_cost_per_token_batches: 7.5e-7 priority_pricing: - cache_read_input_token_cost: 4.16666666666667e-8 + cache_read_input_token_cost: 4.5e-8 + input_cost_per_audio_token: 9e-7 input_cost_per_token: 4.5e-7 - output_cost_per_token: 3.75e-6 + output_cost_per_token: 2.7e-6 region: "*" features: - function_calling diff --git a/providers/openai/gpt-4.1-nano-2025-04-14.yaml b/providers/openai/gpt-4.1-nano-2025-04-14.yaml index c887f6a6ad..0b22d2ad5a 100644 --- a/providers/openai/gpt-4.1-nano-2025-04-14.yaml +++ b/providers/openai/gpt-4.1-nano-2025-04-14.yaml @@ -5,6 +5,10 @@ costs: input_cost_per_token_batches: 5e-8 output_cost_per_token: 4e-7 output_cost_per_token_batches: 2e-7 + priority_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 2e-7 + output_cost_per_token: 8e-7 region: "*" deprecationDate: "2026-04-22" external_ids: diff --git a/providers/openai/gpt-4.1-nano.yaml b/providers/openai/gpt-4.1-nano.yaml index c38baa7ed5..0198da9bf5 100644 --- a/providers/openai/gpt-4.1-nano.yaml +++ b/providers/openai/gpt-4.1-nano.yaml @@ -3,6 +3,10 @@ costs: - cache_read_input_token_cost: 2.5e-8 input_cost_per_token: 1e-7 output_cost_per_token: 4e-7 + priority_pricing: + cache_read_input_token_cost: 5e-8 + input_cost_per_token: 2e-7 + output_cost_per_token: 8e-7 region: "*" deprecationDate: "2026-04-22" external_ids: diff --git a/providers/openai/gpt-4o-2024-05-13.yaml b/providers/openai/gpt-4o-2024-05-13.yaml index ac1e1a1ae4..92630027dc 100644 --- a/providers/openai/gpt-4o-2024-05-13.yaml +++ b/providers/openai/gpt-4o-2024-05-13.yaml @@ -3,6 +3,9 @@ costs: - cache_read_input_token_cost: 1.25e-6 input_cost_per_token: 2.5e-6 output_cost_per_token: 1e-5 + priority_pricing: + input_cost_per_token: 8.75e-6 + output_cost_per_token: 2.625e-5 region: "*" deprecationDate: "2026-04-22" external_ids: diff --git a/providers/openai/gpt-4o-2024-08-06.yaml b/providers/openai/gpt-4o-2024-08-06.yaml index 447dcabdc1..40c5b70f93 100644 --- a/providers/openai/gpt-4o-2024-08-06.yaml +++ b/providers/openai/gpt-4o-2024-08-06.yaml @@ -5,6 +5,10 @@ costs: input_cost_per_token_batches: 1.25e-6 output_cost_per_token: 1e-5 output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.125e-6 + input_cost_per_token: 4.25e-6 + output_cost_per_token: 1.7e-5 region: "*" external_ids: artificial_analysis_id: c1045dc0-4fd3-4adb-9548-18763e0d051f diff --git a/providers/openai/gpt-4o-mini-2024-07-18.yaml b/providers/openai/gpt-4o-mini-2024-07-18.yaml index a4de06e9d3..8c17896234 100644 --- a/providers/openai/gpt-4o-mini-2024-07-18.yaml +++ b/providers/openai/gpt-4o-mini-2024-07-18.yaml @@ -5,6 +5,10 @@ costs: input_cost_per_token_batches: 7.5e-8 output_cost_per_token: 6e-7 output_cost_per_token_batches: 3e-7 + priority_pricing: + cache_read_input_token_cost: 1.25e-7 + input_cost_per_token: 2.5e-7 + output_cost_per_token: 1e-6 region: "*" external_ids: artificial_analysis_id: b5c1c91a-7474-4409-9a9c-9c2ac45d9eb6 diff --git a/providers/openai/gpt-5-2025-08-07.yaml b/providers/openai/gpt-5-2025-08-07.yaml index b20e85c63c..2fc9adacb4 100644 --- a/providers/openai/gpt-5-2025-08-07.yaml +++ b/providers/openai/gpt-5-2025-08-07.yaml @@ -1,10 +1,18 @@ canonical_model: openai/gpt-5 costs: - cache_read_input_token_cost: 1.25e-7 + flex_pricing: + cache_read_input_token_cost: 6.25e-8 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 output_cost_per_token: 1e-5 output_cost_per_token_batches: 5e-6 + priority_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" deprecationDate: "2026-06-11" external_ids: diff --git a/providers/openai/gpt-5-mini-2025-08-07.yaml b/providers/openai/gpt-5-mini-2025-08-07.yaml index 45029aa81d..577398e4a4 100644 --- a/providers/openai/gpt-5-mini-2025-08-07.yaml +++ b/providers/openai/gpt-5-mini-2025-08-07.yaml @@ -1,10 +1,18 @@ canonical_model: openai/gpt-5-mini costs: - cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 1e-6 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 output_cost_per_token: 2e-6 output_cost_per_token_batches: 1e-6 + priority_pricing: + cache_read_input_token_cost: 4.5e-8 + input_cost_per_token: 4.5e-7 + output_cost_per_token: 3.6e-6 region: "*" deprecationDate: "2026-06-11" external_ids: diff --git a/providers/openai/gpt-5-mini.yaml b/providers/openai/gpt-5-mini.yaml index 99365fc3c9..d4cdecaaf7 100644 --- a/providers/openai/gpt-5-mini.yaml +++ b/providers/openai/gpt-5-mini.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-mini costs: - cache_read_input_token_cost: 2.5e-8 + flex_pricing: + cache_read_input_token_cost: 1.25e-8 + input_cost_per_token: 1.25e-7 + output_cost_per_token: 1e-6 input_cost_per_token: 2.5e-7 input_cost_per_token_batches: 1.25e-7 - output_cost_per_token: 0.000002 - output_cost_per_token_batches: 0.000001 + output_cost_per_token: 2e-6 + output_cost_per_token_batches: 1e-6 priority_pricing: cache_read_input_token_cost: 4.5e-8 input_cost_per_token: 4.5e-7 - output_cost_per_token: 0.0000036 + output_cost_per_token: 3.6e-6 region: "*" external_ids: artificial_analysis_id: 29855680-7469-43eb-8b88-cd3fb1d99da3 diff --git a/providers/openai/gpt-5-nano-2025-08-07.yaml b/providers/openai/gpt-5-nano-2025-08-07.yaml index c88865920b..332cce8970 100644 --- a/providers/openai/gpt-5-nano-2025-08-07.yaml +++ b/providers/openai/gpt-5-nano-2025-08-07.yaml @@ -1,6 +1,10 @@ canonical_model: openai/gpt-5-nano costs: - cache_read_input_token_cost: 5e-9 + flex_pricing: + cache_read_input_token_cost: 2.5e-9 + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2e-7 input_cost_per_token: 5e-8 input_cost_per_token_batches: 2.5e-8 output_cost_per_token: 4e-7 diff --git a/providers/openai/gpt-5-nano.yaml b/providers/openai/gpt-5-nano.yaml index 8c886cb44e..57cefaa71b 100644 --- a/providers/openai/gpt-5-nano.yaml +++ b/providers/openai/gpt-5-nano.yaml @@ -1,6 +1,10 @@ canonical_model: openai/gpt-5-nano costs: - cache_read_input_token_cost: 5e-9 + flex_pricing: + cache_read_input_token_cost: 2.5e-9 + input_cost_per_token: 2.5e-8 + output_cost_per_token: 2e-7 input_cost_per_token: 5e-8 input_cost_per_token_batches: 2.5e-8 output_cost_per_token: 4e-7 diff --git a/providers/openai/gpt-5.1-2025-11-13.yaml b/providers/openai/gpt-5.1-2025-11-13.yaml index 104b5db66e..081d007b60 100644 --- a/providers/openai/gpt-5.1-2025-11-13.yaml +++ b/providers/openai/gpt-5.1-2025-11-13.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-1 costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 6.25e-8 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 priority_pricing: cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - output_cost_per_token: 0.00002 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 diff --git a/providers/openai/gpt-5.1.yaml b/providers/openai/gpt-5.1.yaml index 9c2b872ac5..8a0808b240 100644 --- a/providers/openai/gpt-5.1.yaml +++ b/providers/openai/gpt-5.1.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-1 costs: - cache_read_input_token_cost: 1.25e-7 - input_cost_per_token: 0.00000125 + flex_pricing: + cache_read_input_token_cost: 6.25e-8 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 + input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 - output_cost_per_token: 0.00001 - output_cost_per_token_batches: 0.000005 + output_cost_per_token: 1e-5 + output_cost_per_token_batches: 5e-6 priority_pricing: cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - output_cost_per_token: 0.00002 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 2e-5 region: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 diff --git a/providers/openai/gpt-5.2-2025-12-11.yaml b/providers/openai/gpt-5.2-2025-12-11.yaml index c7cec0a80b..661dd6af5c 100644 --- a/providers/openai/gpt-5.2-2025-12-11.yaml +++ b/providers/openai/gpt-5.2-2025-12-11.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-2 costs: - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + flex_pricing: + cache_read_input_token_cost: 8.75e-8 + input_cost_per_token: 8.75e-7 + output_cost_per_token: 7e-6 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 priority_pricing: cache_read_input_token_cost: 3.5e-7 - input_cost_per_token: 0.0000035 - output_cost_per_token: 0.000028 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/openai/gpt-5.2.yaml b/providers/openai/gpt-5.2.yaml index 7ff76f940f..f6aedf9ec9 100644 --- a/providers/openai/gpt-5.2.yaml +++ b/providers/openai/gpt-5.2.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-2 costs: - cache_read_input_token_cost: 1.75e-7 - input_cost_per_token: 0.00000175 + flex_pricing: + cache_read_input_token_cost: 8.75e-8 + input_cost_per_token: 8.75e-7 + output_cost_per_token: 7e-6 + input_cost_per_token: 1.75e-6 input_cost_per_token_batches: 8.75e-7 - output_cost_per_token: 0.000014 - output_cost_per_token_batches: 0.000007 + output_cost_per_token: 1.4e-5 + output_cost_per_token_batches: 7e-6 priority_pricing: cache_read_input_token_cost: 3.5e-7 - input_cost_per_token: 0.0000035 - output_cost_per_token: 0.000028 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 2.8e-5 region: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/openai/gpt-5.4-2026-03-05.yaml b/providers/openai/gpt-5.4-2026-03-05.yaml index 446f7c5682..0700306efc 100644 --- a/providers/openai/gpt-5.4-2026-03-05.yaml +++ b/providers/openai/gpt-5.4-2026-03-05.yaml @@ -1,24 +1,39 @@ canonical_model: openai/gpt-5-4 costs: - cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - input_cost_per_token_batches: 0.00000125 - output_cost_per_token: 0.000015 - output_cost_per_token_batches: 0.0000075 + flex_pricing: + cache_read_input_token_cost: 1.3e-7 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.5e-6 + input_cost_per_token_batches: 1.25e-6 + output_cost_per_token: 1.5e-5 + output_cost_per_token_batches: 7.5e-6 priority_pricing: cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000005 - output_cost_per_token: 0.00003 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 region: "*" tiered_pricing: cache_read: - cost_per_token: 5e-7 from: 272000 input: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 output: - - cost_per_token: 0.0000225 + - cost_per_token: 2.25e-5 from: 272000 pricing_mode: cumulative external_ids: diff --git a/providers/openai/gpt-5.4-mini-2026-03-17.yaml b/providers/openai/gpt-5.4-mini-2026-03-17.yaml index 02aeb2c7b4..c2a6285e32 100644 --- a/providers/openai/gpt-5.4-mini-2026-03-17.yaml +++ b/providers/openai/gpt-5.4-mini-2026-03-17.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-4-mini costs: - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.0000045 - output_cost_per_token_batches: 0.00000225 + output_cost_per_token: 4.5e-6 + output_cost_per_token_batches: 2.25e-6 priority_pricing: cache_read_input_token_cost: 1.5e-7 - input_cost_per_token: 0.0000015 - output_cost_per_token: 0.000009 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 diff --git a/providers/openai/gpt-5.4-mini.yaml b/providers/openai/gpt-5.4-mini.yaml index 293ea5672d..f07ce77969 100644 --- a/providers/openai/gpt-5.4-mini.yaml +++ b/providers/openai/gpt-5.4-mini.yaml @@ -1,14 +1,18 @@ canonical_model: openai/gpt-5-4-mini costs: - cache_read_input_token_cost: 7.5e-8 + flex_pricing: + cache_read_input_token_cost: 3.75e-8 + input_cost_per_token: 3.75e-7 + output_cost_per_token: 2.25e-6 input_cost_per_token: 7.5e-7 input_cost_per_token_batches: 3.75e-7 - output_cost_per_token: 0.0000045 - output_cost_per_token_batches: 0.00000225 + output_cost_per_token: 4.5e-6 + output_cost_per_token_batches: 2.25e-6 priority_pricing: cache_read_input_token_cost: 1.5e-7 - input_cost_per_token: 0.0000015 - output_cost_per_token: 0.000009 + input_cost_per_token: 1.5e-6 + output_cost_per_token: 9e-6 region: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 diff --git a/providers/openai/gpt-5.4-nano-2026-03-17.yaml b/providers/openai/gpt-5.4-nano-2026-03-17.yaml index 35aa7dd3e7..d13c31f94f 100644 --- a/providers/openai/gpt-5.4-nano-2026-03-17.yaml +++ b/providers/openai/gpt-5.4-nano-2026-03-17.yaml @@ -1,9 +1,13 @@ canonical_model: openai/gpt-5-4-nano costs: - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 - output_cost_per_token: 0.00000125 + output_cost_per_token: 1.25e-6 output_cost_per_token_batches: 6.25e-7 region: "*" external_ids: diff --git a/providers/openai/gpt-5.4-nano.yaml b/providers/openai/gpt-5.4-nano.yaml index f6f8e9432f..71974a27fc 100644 --- a/providers/openai/gpt-5.4-nano.yaml +++ b/providers/openai/gpt-5.4-nano.yaml @@ -1,9 +1,13 @@ canonical_model: openai/gpt-5-4-nano costs: - cache_read_input_token_cost: 2e-8 + flex_pricing: + cache_read_input_token_cost: 1e-8 + input_cost_per_token: 1e-7 + output_cost_per_token: 6.25e-7 input_cost_per_token: 2e-7 input_cost_per_token_batches: 1e-7 - output_cost_per_token: 0.00000125 + output_cost_per_token: 1.25e-6 output_cost_per_token_batches: 6.25e-7 region: "*" external_ids: diff --git a/providers/openai/gpt-5.4-pro-2026-03-05.yaml b/providers/openai/gpt-5.4-pro-2026-03-05.yaml index f8f8650f79..b1e430b3d8 100644 --- a/providers/openai/gpt-5.4-pro-2026-03-05.yaml +++ b/providers/openai/gpt-5.4-pro-2026-03-05.yaml @@ -1,12 +1,23 @@ costs: - - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/openai/gpt-5.4-pro.yaml b/providers/openai/gpt-5.4-pro.yaml index b9ab743ca7..d656adc6b0 100644 --- a/providers/openai/gpt-5.4-pro.yaml +++ b/providers/openai/gpt-5.4-pro.yaml @@ -1,12 +1,23 @@ costs: - - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + tiered_pricing: + input: + - cost_per_token: 3e-5 + from: 272000 + output: + - cost_per_token: 0.000135 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/openai/gpt-5.4.yaml b/providers/openai/gpt-5.4.yaml index 83f5e9f6c7..5ed5c67a5a 100644 --- a/providers/openai/gpt-5.4.yaml +++ b/providers/openai/gpt-5.4.yaml @@ -1,24 +1,39 @@ canonical_model: openai/gpt-5-4 costs: - cache_read_input_token_cost: 2.5e-7 - input_cost_per_token: 0.0000025 - input_cost_per_token_batches: 0.00000125 - output_cost_per_token: 0.000015 - output_cost_per_token_batches: 0.0000075 + flex_pricing: + cache_read_input_token_cost: 1.3e-7 + input_cost_per_token: 1.25e-6 + output_cost_per_token: 7.5e-6 + tiered_pricing: + cache_read: + - cost_per_token: 2.5e-7 + from: 272000 + input: + - cost_per_token: 2.5e-6 + from: 272000 + output: + - cost_per_token: 1.125e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 2.5e-6 + input_cost_per_token_batches: 1.25e-6 + output_cost_per_token: 1.5e-5 + output_cost_per_token_batches: 7.5e-6 priority_pricing: cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000005 - output_cost_per_token: 0.00003 + input_cost_per_token: 5e-6 + output_cost_per_token: 3e-5 region: "*" tiered_pricing: cache_read: - cost_per_token: 5e-7 from: 272000 input: - - cost_per_token: 0.000005 + - cost_per_token: 5e-6 from: 272000 output: - - cost_per_token: 0.0000225 + - cost_per_token: 2.25e-5 from: 272000 pricing_mode: cumulative external_ids: diff --git a/providers/openai/gpt-5.5-2026-04-23.yaml b/providers/openai/gpt-5.5-2026-04-23.yaml index a55a6da2be..5fc528d52b 100644 --- a/providers/openai/gpt-5.5-2026-04-23.yaml +++ b/providers/openai/gpt-5.5-2026-04-23.yaml @@ -1,24 +1,39 @@ canonical_model: openai/gpt-5-5 costs: - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000005 - input_cost_per_token_batches: 0.0000025 - output_cost_per_token: 0.00003 - output_cost_per_token_batches: 0.000015 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 1.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 5e-7 + from: 272000 + input: + - cost_per_token: 5e-6 + from: 272000 + output: + - cost_per_token: 2.25e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 5e-6 + input_cost_per_token_batches: 2.5e-6 + output_cost_per_token: 3e-5 + output_cost_per_token_batches: 1.5e-5 priority_pricing: - cache_read_input_token_cost: 0.00000125 - input_cost_per_token: 0.0000125 - output_cost_per_token: 0.000075 + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000001 + - cost_per_token: 1e-6 from: 272000 input: - - cost_per_token: 0.00001 + - cost_per_token: 1e-5 from: 272000 output: - - cost_per_token: 0.000045 + - cost_per_token: 4.5e-5 from: 272000 pricing_mode: cumulative external_ids: diff --git a/providers/openai/gpt-5.5-pro-2026-04-23.yaml b/providers/openai/gpt-5.5-pro-2026-04-23.yaml index 61a43da12b..b0016ed4e1 100644 --- a/providers/openai/gpt-5.5-pro-2026-04-23.yaml +++ b/providers/openai/gpt-5.5-pro-2026-04-23.yaml @@ -1,12 +1,15 @@ costs: - - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/openai/gpt-5.5-pro.yaml b/providers/openai/gpt-5.5-pro.yaml index d09ed6e913..1106be3ff3 100644 --- a/providers/openai/gpt-5.5-pro.yaml +++ b/providers/openai/gpt-5.5-pro.yaml @@ -1,12 +1,15 @@ costs: - - input_cost_per_token: 0.00003 - input_cost_per_token_batches: 0.000015 + - flex_pricing: + input_cost_per_token: 1.5e-5 + output_cost_per_token: 9e-5 + input_cost_per_token: 3e-5 + input_cost_per_token_batches: 1.5e-5 output_cost_per_token: 0.00018 - output_cost_per_token_batches: 0.00009 + output_cost_per_token_batches: 9e-5 region: "*" tiered_pricing: input: - - cost_per_token: 0.00006 + - cost_per_token: 6e-5 from: 272000 output: - cost_per_token: 0.00027 diff --git a/providers/openai/gpt-5.5.yaml b/providers/openai/gpt-5.5.yaml index 700a437eb4..dbd49e1d6f 100644 --- a/providers/openai/gpt-5.5.yaml +++ b/providers/openai/gpt-5.5.yaml @@ -1,20 +1,39 @@ canonical_model: openai/gpt-5-5 costs: - cache_read_input_token_cost: 5e-7 - input_cost_per_token: 0.000005 - input_cost_per_token_batches: 0.0000025 - output_cost_per_token: 0.00003 - output_cost_per_token_batches: 0.000015 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 2.5e-6 + output_cost_per_token: 1.5e-5 + tiered_pricing: + cache_read: + - cost_per_token: 5e-7 + from: 272000 + input: + - cost_per_token: 5e-6 + from: 272000 + output: + - cost_per_token: 2.25e-5 + from: 272000 + pricing_mode: cumulative + input_cost_per_token: 5e-6 + input_cost_per_token_batches: 2.5e-6 + output_cost_per_token: 3e-5 + output_cost_per_token_batches: 1.5e-5 + priority_pricing: + cache_read_input_token_cost: 1.25e-6 + input_cost_per_token: 1.25e-5 + output_cost_per_token: 7.5e-5 region: "*" tiered_pricing: cache_read: - - cost_per_token: 0.000001 + - cost_per_token: 1e-6 from: 272000 input: - - cost_per_token: 0.00001 + - cost_per_token: 1e-5 from: 272000 output: - - cost_per_token: 0.000045 + - cost_per_token: 4.5e-5 from: 272000 pricing_mode: cumulative external_ids: diff --git a/providers/openai/gpt-5.yaml b/providers/openai/gpt-5.yaml index 05cf9ff0ff..9fcd31219e 100644 --- a/providers/openai/gpt-5.yaml +++ b/providers/openai/gpt-5.yaml @@ -1,6 +1,10 @@ canonical_model: openai/gpt-5 costs: - cache_read_input_token_cost: 1.25e-7 + flex_pricing: + cache_read_input_token_cost: 6.25e-8 + input_cost_per_token: 6.25e-7 + output_cost_per_token: 5e-6 input_cost_per_token: 1.25e-6 input_cost_per_token_batches: 6.25e-7 output_cost_per_token: 1e-5 diff --git a/providers/openai/o3-2025-04-16.yaml b/providers/openai/o3-2025-04-16.yaml index e1b9897165..d7acfdb070 100644 --- a/providers/openai/o3-2025-04-16.yaml +++ b/providers/openai/o3-2025-04-16.yaml @@ -1,10 +1,18 @@ canonical_model: openai/o3 costs: - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 4e-6 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: "*" deprecationDate: "2026-06-11" external_ids: diff --git a/providers/openai/o3.yaml b/providers/openai/o3.yaml index 3f81494682..0399e6fdeb 100644 --- a/providers/openai/o3.yaml +++ b/providers/openai/o3.yaml @@ -1,10 +1,18 @@ canonical_model: openai/o3 costs: - cache_read_input_token_cost: 5e-7 + flex_pricing: + cache_read_input_token_cost: 2.5e-7 + input_cost_per_token: 1e-6 + output_cost_per_token: 4e-6 input_cost_per_token: 2e-6 input_cost_per_token_batches: 1e-6 output_cost_per_token: 8e-6 output_cost_per_token_batches: 4e-6 + priority_pricing: + cache_read_input_token_cost: 8.75e-7 + input_cost_per_token: 3.5e-6 + output_cost_per_token: 1.4e-5 region: "*" deprecationDate: "2026-06-11" external_ids: diff --git a/providers/openai/o4-mini-2025-04-16.yaml b/providers/openai/o4-mini-2025-04-16.yaml index 30e27f2ea3..2195faae32 100644 --- a/providers/openai/o4-mini-2025-04-16.yaml +++ b/providers/openai/o4-mini-2025-04-16.yaml @@ -1,10 +1,18 @@ canonical_model: openai/o4-mini costs: - cache_read_input_token_cost: 2.75e-7 + flex_pricing: + cache_read_input_token_cost: 1.38e-7 + input_cost_per_token: 5.5e-7 + output_cost_per_token: 2.2e-6 input_cost_per_token: 1.1e-6 input_cost_per_token_batches: 5.5e-7 output_cost_per_token: 4.4e-6 output_cost_per_token_batches: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 8e-6 region: "*" deprecationDate: "2026-04-22" external_ids: diff --git a/providers/openai/o4-mini.yaml b/providers/openai/o4-mini.yaml index d15bde7a7b..2c3a9e3e5f 100644 --- a/providers/openai/o4-mini.yaml +++ b/providers/openai/o4-mini.yaml @@ -1,10 +1,18 @@ canonical_model: openai/o4-mini costs: - cache_read_input_token_cost: 2.75e-7 + flex_pricing: + cache_read_input_token_cost: 1.38e-7 + input_cost_per_token: 5.5e-7 + output_cost_per_token: 2.2e-6 input_cost_per_token: 1.1e-6 input_cost_per_token_batches: 5.5e-7 output_cost_per_token: 4.4e-6 output_cost_per_token_batches: 2.2e-6 + priority_pricing: + cache_read_input_token_cost: 5e-7 + input_cost_per_token: 2e-6 + output_cost_per_token: 8e-6 region: "*" deprecationDate: "2026-04-22" external_ids: