diff --git a/.github/test/model.cue b/.github/test/model.cue index 68dcc4b94..db4d77bd3 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/aws-bedrock-mantle/deepseek.v3.1.yaml b/providers/aws-bedrock-mantle/deepseek.v3.1.yaml index f80e02ec8..683c287c5 100644 --- a/providers/aws-bedrock-mantle/deepseek.v3.1.yaml +++ b/providers/aws-bedrock-mantle/deepseek.v3.1.yaml @@ -1,36 +1,101 @@ canonical_model: deepseek/v3-1 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 2a0072370..af121fa7d 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml @@ -1,16 +1,40 @@ canonical_model: google/gemma-4-26b-a4b 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 external_ids: artificial_analysis_id: 6e1b44ff-c227-496b-aef4-19b70cd18c76 diff --git a/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml b/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml index 599e4ac12..24f2bf2b4 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-31b.yaml @@ -1,16 +1,40 @@ canonical_model: google/gemma-4-31b 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 external_ids: artificial_analysis_id: cd26a386-4873-46ff-b853-d239050025a2 diff --git a/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml b/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml index 48b12cdfb..46a41b0b3 100644 --- a/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml +++ b/providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml @@ -1,16 +1,40 @@ canonical_model: google/gemma-4-e2b 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 external_ids: artificial_analysis_id: b07aef0a-b192-46a1-b1c9-40b06d1b9061 diff --git a/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml b/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml index acebbffc0..f209810ef 100644 --- a/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml +++ b/providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml @@ -1,35 +1,101 @@ canonical_model: kimi/kimi-k2-thinking 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 external_ids: artificial_analysis_id: bddebfd3-0a8d-47f5-b722-bc4c2ca5a5dc diff --git a/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml b/providers/aws-bedrock-mantle/openai.gpt-6-astra.yaml index 6bcc2148e..41da77138 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 4e92cfbc4..8a6bb6d41 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-6.1-sol.yaml @@ -1,24 +1,43 @@ canonical_model: openai/gpt-6-1-sol 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 external_ids: artificial_analysis_id: b25ac058-1e33-4c31-bbc9-a20c3ad0717a artificial_analysis_slug: gpt-6-1-sol diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml index 2a8c6f128..51a3998d1 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-120b.yaml @@ -1,49 +1,139 @@ canonical_model: openai/gpt-oss-120b 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 external_ids: artificial_analysis_id: f0083258-8646-45b8-8082-7aaf6c2ea82a diff --git a/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml b/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml index 1e54af504..91de7b269 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-20b.yaml @@ -1,45 +1,123 @@ canonical_model: openai/gpt-oss-20b 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 external_ids: artificial_analysis_id: 36f73aaf-d38a-4b56-a2b3-d04d17186910 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 3382213f7..4e89a9ae4 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-120b.yaml @@ -1,44 +1,128 @@ canonical_model: openai/gpt-oss-safeguard-120b 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 b88f91961..2c925715b 100644 --- a/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml +++ b/providers/aws-bedrock-mantle/openai.gpt-oss-safeguard-20b.yaml @@ -1,44 +1,128 @@ canonical_model: openai/gpt-oss-safeguard-20b 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 bcb8b7913..747baa414 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-235b-a22b-2507.yaml @@ -1,44 +1,128 @@ canonical_model: alibaba/qwen3-235b-a22b-2507 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 a3decdc34..6e3d682b3 100644 --- a/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml +++ b/providers/aws-bedrock-mantle/qwen.qwen3-32b.yaml @@ -1,46 +1,130 @@ canonical_model: alibaba/qwen3-32b 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 ae4ba835f..717353293 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 @@ -1,44 +1,128 @@ canonical_model: alibaba/qwen3-coder-30b-a3b-instruct 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 external_ids: artificial_analysis_id: da9fe224-8af3-46d7-a8c4-6220779c3f35 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 3276f4f67..96246b7f7 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 @@ -1,35 +1,101 @@ canonical_model: alibaba/qwen3-coder-480b-a35b-instruct 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 external_ids: artificial_analysis_id: 093883ed-f5fc-443b-8e18-afbfb166699e 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 9ec24c768..fa16a366c 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 @@ -1,43 +1,121 @@ canonical_model: alibaba/qwen3-next-80b-a3b-instruct 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: 6e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-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: 6e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-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: 6e-7 + input_cost_per_token: 1.5e-7 + output_cost_per_token: 1.2e-6 + priority_pricing: + input_cost_per_token: 2.625e-7 + output_cost_per_token: 2.1e-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: 7.25e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.5375e-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: 9.3e-7 + input_cost_per_token: 2.3e-7 + output_cost_per_token: 1.86e-6 + priority_pricing: + input_cost_per_token: 4.025e-7 + output_cost_per_token: 3.255e-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: 7.05e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-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: 7.05e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-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: 2.94e-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: 2.94e-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: 2.94e-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: 6.18e-7 + input_cost_per_token: 1.545e-7 + output_cost_per_token: 1.236e-6 + priority_pricing: + input_cost_per_token: 2.70375e-7 + output_cost_per_token: 2.163e-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: 7.05e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.41e-6 + priority_pricing: + input_cost_per_token: 3.15e-7 + output_cost_per_token: 2.4675e-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: 7.25e-7 + input_cost_per_token: 1.8e-7 + output_cost_per_token: 1.45e-6 + priority_pricing: + 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-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml b/providers/aws-bedrock-mantle/qwen.qwen3-vl-235b-a22b-instruct.yaml index 8a68d7f54..87a1695da 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 @@ -1,43 +1,121 @@ canonical_model: alibaba/qwen3-vl-235b-a22b-instruct 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 external_ids: artificial_analysis_id: d58cf573-1bd3-4d1f-9182-5482a460f570 diff --git a/providers/aws-bedrock-mantle/xai.grok-4.3.yaml b/providers/aws-bedrock-mantle/xai.grok-4.3.yaml index da3522dd7..97f8cef65 100644 --- a/providers/aws-bedrock-mantle/xai.grok-4.3.yaml +++ b/providers/aws-bedrock-mantle/xai.grok-4.3.yaml @@ -1,20 +1,52 @@ canonical_model: xai/grok-4-3 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 external_ids: artificial_analysis_id: 948892b5-db03-4118-a4a8-ccd51ed871ea diff --git a/providers/aws-bedrock-mantle/xai.grok-4.6.yaml b/providers/aws-bedrock-mantle/xai.grok-4.6.yaml index 3581d8388..e596534be 100644 --- a/providers/aws-bedrock-mantle/xai.grok-4.6.yaml +++ b/providers/aws-bedrock-mantle/xai.grok-4.6.yaml @@ -1,12 +1,28 @@ canonical_model: xai/grok-4-6 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 external_ids: artificial_analysis_id: c8adc5cf-fd5a-407b-af51-dc3bede3e49c diff --git a/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml b/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml index 39d012ee5..12f3191fe 100644 --- a/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/amazon.nova-pro-v1:0.yaml @@ -1,98 +1,266 @@ canonical_model: amazon/nova-pro 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 external_ids: artificial_analysis_id: 546ec53f-273c-4af7-b13f-b88c41f45905 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 9b4b2f9e3..9daa4e9a4 100644 --- a/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/apac.amazon.nova-pro-v1:0.yaml @@ -1,38 +1,82 @@ canonical_model: amazon/nova-pro 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 external_ids: artificial_analysis_id: 546ec53f-273c-4af7-b13f-b88c41f45905 artificial_analysis_slug: nova-pro diff --git a/providers/aws-bedrock/deepseek.v3.2.yaml b/providers/aws-bedrock/deepseek.v3.2.yaml index 968c68639..3b5b6d2a9 100644 --- a/providers/aws-bedrock/deepseek.v3.2.yaml +++ b/providers/aws-bedrock/deepseek.v3.2.yaml @@ -1,33 +1,99 @@ canonical_model: deepseek/v3-2 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 feaa3bd40..702f2385b 100644 --- a/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/eu.amazon.nova-pro-v1:0.yaml @@ -1,42 +1,70 @@ canonical_model: amazon/nova-pro 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 external_ids: artificial_analysis_id: 546ec53f-273c-4af7-b13f-b88c41f45905 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 9e512d09d..f49d387cc 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 @@ -2,107 +2,211 @@ canonical_model: amazon/nova-2-lite 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 3df577c4c..b63c3e1ed 100644 --- a/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/global.moonshotai.kimi-k3.yaml @@ -1,164 +1,484 @@ canonical_model: kimi/kimi-k3 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 external_ids: artificial_analysis_id: f7d2fc3e-1f7b-405f-818c-07952a4af78f diff --git a/providers/aws-bedrock/global.openai.gpt-6-astra.yaml b/providers/aws-bedrock/global.openai.gpt-6-astra.yaml index 1525d8622..ac89356a1 100644 --- a/providers/aws-bedrock/global.openai.gpt-6-astra.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6-astra.yaml @@ -1,328 +1,651 @@ canonical_model: openai/gpt-6-astra 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 external_ids: artificial_analysis_id: 2f339a97-9a0d-499a-9cb5-e0db665bfa25 artificial_analysis_slug: gpt-6-astra 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 5a50ed116..9e87bd919 100644 --- a/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6.1-sol.yaml @@ -1,594 +1,1183 @@ canonical_model: openai/gpt-6-1-sol 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 external_ids: artificial_analysis_id: b25ac058-1e33-4c31-bbc9-a20c3ad0717a artificial_analysis_slug: gpt-6-1-sol diff --git a/providers/aws-bedrock/global.xai.grok-4.6.yaml b/providers/aws-bedrock/global.xai.grok-4.6.yaml index 76547e89c..d807eaf01 100644 --- a/providers/aws-bedrock/global.xai.grok-4.6.yaml +++ b/providers/aws-bedrock/global.xai.grok-4.6.yaml @@ -1,132 +1,388 @@ canonical_model: xai/grok-4-6 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 external_ids: artificial_analysis_id: c8adc5cf-fd5a-407b-af51-dc3bede3e49c diff --git a/providers/aws-bedrock/global.xai.grok-4.7.yaml b/providers/aws-bedrock/global.xai.grok-4.7.yaml index 8572616cf..37a6617b9 100644 --- a/providers/aws-bedrock/global.xai.grok-4.7.yaml +++ b/providers/aws-bedrock/global.xai.grok-4.7.yaml @@ -1,124 +1,364 @@ canonical_model: xai/grok-4-7 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 external_ids: artificial_analysis_id: 59627802-1546-422c-9a65-65b61c022d36 diff --git a/providers/aws-bedrock/global.zai.glm-5.3.yaml b/providers/aws-bedrock/global.zai.glm-5.3.yaml index cfc7a27cd..8033e9f3f 100644 --- a/providers/aws-bedrock/global.zai.glm-5.3.yaml +++ b/providers/aws-bedrock/global.zai.glm-5.3.yaml @@ -1,159 +1,469 @@ canonical_model: zai/glm-5-3 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 external_ids: artificial_analysis_id: cd684ea4-b475-4269-b001-d469d06d8a7a diff --git a/providers/aws-bedrock/google.gemma-3-12b-it.yaml b/providers/aws-bedrock/google.gemma-3-12b-it.yaml index 32162ce48..be9e91b7d 100644 --- a/providers/aws-bedrock/google.gemma-3-12b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-12b-it.yaml @@ -1,37 +1,103 @@ canonical_model: google/gemma-3-12b-it 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 b4e4d1688..188d97a89 100644 --- a/providers/aws-bedrock/google.gemma-3-27b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-27b-it.yaml @@ -1,37 +1,103 @@ canonical_model: google/gemma-3-27b-it 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 967a71781..849c9b9a7 100644 --- a/providers/aws-bedrock/google.gemma-3-4b-it.yaml +++ b/providers/aws-bedrock/google.gemma-3-4b-it.yaml @@ -1,37 +1,103 @@ canonical_model: google/gemma-3-4b-it 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 155ad9454..6d61aafca 100644 --- a/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/in.moonshotai.kimi-k3.yaml @@ -1,7 +1,27 @@ canonical_model: kimi/kimi-k3 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 external_ids: artificial_analysis_id: f7d2fc3e-1f7b-405f-818c-07952a4af78f artificial_analysis_slug: kimi-k3 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 6198d457c..5dd5c60bd 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 @@ -1,10 +1,18 @@ canonical_model: amazon/nova-2-lite 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 9ee82cc49..eca0b9085 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.1.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.1.yaml @@ -1,43 +1,121 @@ canonical_model: minimax/minimax-m2-1 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 external_ids: artificial_analysis_id: 272ff333-442f-4169-a804-ac9177bc99d7 diff --git a/providers/aws-bedrock/minimax.minimax-m2.5.yaml b/providers/aws-bedrock/minimax.minimax-m2.5.yaml index 977d4ed97..7ff106133 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.5.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.5.yaml @@ -1,43 +1,121 @@ canonical_model: minimax/minimax-m2-5 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 external_ids: artificial_analysis_id: 12adec16-19fe-4d92-aeff-5ef3eb7e780a diff --git a/providers/aws-bedrock/minimax.minimax-m2.yaml b/providers/aws-bedrock/minimax.minimax-m2.yaml index b61941093..a798cc044 100644 --- a/providers/aws-bedrock/minimax.minimax-m2.yaml +++ b/providers/aws-bedrock/minimax.minimax-m2.yaml @@ -1,44 +1,128 @@ canonical_model: minimax/minimax-m2 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 external_ids: artificial_analysis_id: f74ea286-cd29-4eb4-af14-1389b19c21e5 diff --git a/providers/aws-bedrock/mistral.devstral-2-123b.yaml b/providers/aws-bedrock/mistral.devstral-2-123b.yaml index 5fb6ee05f..551c76d1a 100644 --- a/providers/aws-bedrock/mistral.devstral-2-123b.yaml +++ b/providers/aws-bedrock/mistral.devstral-2-123b.yaml @@ -1,43 +1,121 @@ canonical_model: mistral/devstral-2-123b 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 a6976ab73..89e6114b7 100644 --- a/providers/aws-bedrock/mistral.magistral-small-2509.yaml +++ b/providers/aws-bedrock/mistral.magistral-small-2509.yaml @@ -1,34 +1,94 @@ canonical_model: mistral/magistral-small-2509 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 external_ids: artificial_analysis_id: 70152cb0-fb36-4732-a925-89ef40994be1 diff --git a/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml b/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml index a8dfb2c4a..4d6c3cc1d 100644 --- a/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-14b-instruct.yaml @@ -1,43 +1,121 @@ canonical_model: mistral/ministral-3-14b-instruct 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 d2e08966a..890e9be08 100644 --- a/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-3b-instruct.yaml @@ -1,43 +1,121 @@ canonical_model: mistral/ministral-3-3b-instruct 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 ab4a9a5ba..ef855966a 100644 --- a/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml +++ b/providers/aws-bedrock/mistral.ministral-3-8b-instruct.yaml @@ -1,43 +1,121 @@ canonical_model: mistral/ministral-3-8b-instruct 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 71c39dff1..276da271f 100644 --- a/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml +++ b/providers/aws-bedrock/mistral.mistral-large-3-675b-instruct.yaml @@ -1,28 +1,76 @@ canonical_model: mistral/mistral-large-3-675b-instruct 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 3a6d4a7f4..763dd8bad 100644 --- a/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml +++ b/providers/aws-bedrock/mistral.voxtral-mini-3b-2507.yaml @@ -1,34 +1,94 @@ canonical_model: mistral/voxtral-mini-3b-2507 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 523fc394f..99067a46b 100644 --- a/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml +++ b/providers/aws-bedrock/mistral.voxtral-small-24b-2507.yaml @@ -1,34 +1,94 @@ canonical_model: mistral/voxtral-small-24b-2507 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 124b957ef..47f6eb05e 100644 --- a/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml +++ b/providers/aws-bedrock/moonshot.kimi-k2-thinking.yaml @@ -1,31 +1,58 @@ canonical_model: kimi/kimi-k2-thinking 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 external_ids: artificial_analysis_id: bddebfd3-0a8d-47f5-b722-bc4c2ca5a5dc diff --git a/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml b/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml index 72736f7aa..283877df1 100644 --- a/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml +++ b/providers/aws-bedrock/moonshotai.kimi-k2.5.yaml @@ -1,34 +1,94 @@ canonical_model: kimi/kimi-k2-5 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 external_ids: artificial_analysis_id: a550ffca-f89e-4381-ade6-a85dc6a1fb4c diff --git a/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml b/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml index e25c80ca8..600709708 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-12b-v2.yaml @@ -1,46 +1,130 @@ canonical_model: nvidia/nemotron-nano-12b 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 e7811669f..7a7385d28 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-3-30b.yaml @@ -1,46 +1,130 @@ canonical_model: nvidia/nemotron-nano-3-30b 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 409d31ea1..0e402c07d 100644 --- a/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-nano-9b-v2.yaml @@ -1,37 +1,103 @@ canonical_model: nvidia/nemotron-nano-9b 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 85c04e7e3..5d7a7962f 100644 --- a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml @@ -1,37 +1,103 @@ canonical_model: nvidia/nemotron-super-3-120b 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 662a3d2ca..b69c56dd0 100644 --- a/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-120b-1:0.yaml @@ -1,43 +1,121 @@ canonical_model: openai/gpt-oss-120b-1 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 93a2ee233..9cc4f3bbb 100644 --- a/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-20b-1:0.yaml @@ -1,43 +1,121 @@ canonical_model: openai/gpt-oss-20b-1 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 215881a0a..ec32028e8 100644 --- a/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-safeguard-120b.yaml @@ -1,34 +1,94 @@ canonical_model: openai/gpt-oss-safeguard-120b 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 a11568c4b..ec4147c6f 100644 --- a/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml +++ b/providers/aws-bedrock/openai.gpt-oss-safeguard-20b.yaml @@ -1,34 +1,94 @@ canonical_model: openai/gpt-oss-safeguard-20b 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 8cf239539..8be77c758 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 @@ -1,34 +1,64 @@ canonical_model: alibaba/qwen3-235b-a22b-2507 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 a26e86f3e..c6fc4401b 100644 --- a/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml +++ b/providers/aws-bedrock/qwen.qwen3-32b-v1:0.yaml @@ -1,43 +1,121 @@ canonical_model: alibaba/qwen3-32b 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 d9f883066..92ff846c2 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 @@ -2,42 +2,81 @@ canonical_model: alibaba/qwen3-coder-30b-a3b 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 4db0e6ca5..1c0d2e92a 100644 --- a/providers/aws-bedrock/qwen.qwen3-coder-next.yaml +++ b/providers/aws-bedrock/qwen.qwen3-coder-next.yaml @@ -1,43 +1,121 @@ canonical_model: alibaba/qwen3-coder-next 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 external_ids: artificial_analysis_id: fc92f822-04b7-420d-9c07-a21af5e9aac7 diff --git a/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml b/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml index 31b3b8d11..f003f2e1e 100644 --- a/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml +++ b/providers/aws-bedrock/qwen.qwen3-vl-235b-a22b.yaml @@ -1,34 +1,64 @@ canonical_model: alibaba/qwen3-vl-235b-a22b 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 c7daa8a3b..96365e74d 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 @@ -1,28 +1,76 @@ canonical_model: amazon/nova-2-lite 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 a105863e8..51967fc0e 100644 --- a/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml +++ b/providers/aws-bedrock/us.amazon.nova-pro-v1:0.yaml @@ -1,19 +1,51 @@ canonical_model: amazon/nova-pro 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 external_ids: artificial_analysis_id: 546ec53f-273c-4af7-b13f-b88c41f45905 diff --git a/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml b/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml index 046189832..ee3a63d6f 100644 --- a/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml +++ b/providers/aws-bedrock/us.moonshotai.kimi-k3.yaml @@ -1,34 +1,94 @@ canonical_model: kimi/kimi-k3 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 external_ids: artificial_analysis_id: f7d2fc3e-1f7b-405f-818c-07952a4af78f diff --git a/providers/aws-bedrock/us.openai.gpt-6-astra.yaml b/providers/aws-bedrock/us.openai.gpt-6-astra.yaml index dddcfdf90..96a70f115 100644 --- a/providers/aws-bedrock/us.openai.gpt-6-astra.yaml +++ b/providers/aws-bedrock/us.openai.gpt-6-astra.yaml @@ -1,119 +1,233 @@ canonical_model: openai/gpt-6-astra 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 external_ids: artificial_analysis_id: 2f339a97-9a0d-499a-9cb5-e0db665bfa25 artificial_analysis_slug: gpt-6-astra 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 70ea86b8c..a60088d5b 100644 --- a/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml +++ b/providers/aws-bedrock/us.openai.gpt-6.1-sol.yaml @@ -1,119 +1,233 @@ canonical_model: openai/gpt-6-1-sol 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 external_ids: artificial_analysis_id: b25ac058-1e33-4c31-bbc9-a20c3ad0717a artificial_analysis_slug: gpt-6-1-sol diff --git a/providers/aws-bedrock/us.xai.grok-4.6.yaml b/providers/aws-bedrock/us.xai.grok-4.6.yaml index c346b3e0f..273b11f7e 100644 --- a/providers/aws-bedrock/us.xai.grok-4.6.yaml +++ b/providers/aws-bedrock/us.xai.grok-4.6.yaml @@ -1,20 +1,52 @@ canonical_model: xai/grok-4-6 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 external_ids: artificial_analysis_id: c8adc5cf-fd5a-407b-af51-dc3bede3e49c diff --git a/providers/aws-bedrock/us.xai.grok-4.7.yaml b/providers/aws-bedrock/us.xai.grok-4.7.yaml index 4ab98086b..5f3429d84 100644 --- a/providers/aws-bedrock/us.xai.grok-4.7.yaml +++ b/providers/aws-bedrock/us.xai.grok-4.7.yaml @@ -1,28 +1,76 @@ canonical_model: xai/grok-4-7 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 external_ids: artificial_analysis_id: 59627802-1546-422c-9a65-65b61c022d36 diff --git a/providers/aws-bedrock/us.zai.glm-5.3.yaml b/providers/aws-bedrock/us.zai.glm-5.3.yaml index 139432ed2..a38380a59 100644 --- a/providers/aws-bedrock/us.zai.glm-5.3.yaml +++ b/providers/aws-bedrock/us.zai.glm-5.3.yaml @@ -1,32 +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 - 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: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 + flex_pricing: + 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: 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 - 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: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 + flex_pricing: + 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: 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 - 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: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 + flex_pricing: + 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: 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 - 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: 2.31e-6 + cache_read_input_token_cost: 3.432e-7 + flex_pricing: + 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: 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/aws-bedrock/writer.palmyra-vision-7b.yaml b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml index f237020ba..078df5c19 100644 --- a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml +++ b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml @@ -1,46 +1,130 @@ canonical_model: writer/palmyra-vision-7b 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 ef1a46d32..6b376e02c 100644 --- a/providers/aws-bedrock/zai.glm-4.7-flash.yaml +++ b/providers/aws-bedrock/zai.glm-4.7-flash.yaml @@ -1,43 +1,121 @@ canonical_model: zai/glm-4-7-flash 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 external_ids: artificial_analysis_id: 2c4394a2-b443-470a-908e-5c4a271b780c diff --git a/providers/aws-bedrock/zai.glm-4.7.yaml b/providers/aws-bedrock/zai.glm-4.7.yaml index 88b8504e3..93233a4cc 100644 --- a/providers/aws-bedrock/zai.glm-4.7.yaml +++ b/providers/aws-bedrock/zai.glm-4.7.yaml @@ -1,34 +1,94 @@ canonical_model: zai/glm-4-7 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 external_ids: artificial_analysis_id: 6fc35842-0165-44cf-8570-c484a92b3d8c diff --git a/providers/aws-bedrock/zai.glm-5.yaml b/providers/aws-bedrock/zai.glm-5.yaml index ddd619aa0..2deec6514 100644 --- a/providers/aws-bedrock/zai.glm-5.yaml +++ b/providers/aws-bedrock/zai.glm-5.yaml @@ -1,37 +1,70 @@ canonical_model: zai/glm-5 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 external_ids: artificial_analysis_id: 40663ad2-b218-471e-bdd4-a1e0c2360e2b 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 75c4da38a..02c3a9347 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 @@ -5,12 +5,20 @@ 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: "*" external_ids: artificial_analysis_id: 3b608b70-6434-4baa-99ad-45d499703c67 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 b5a7b4beb..09a5f763d 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 @@ -5,12 +5,20 @@ 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: "*" external_ids: artificial_analysis_id: 9f7c7566-a704-49a2-a383-cb3181da33a4 diff --git a/providers/azure-open-ai/gpt-4.1-mini.yaml b/providers/azure-open-ai/gpt-4.1-mini.yaml index c4abeadd7..95b845de4 100644 --- a/providers/azure-open-ai/gpt-4.1-mini.yaml +++ b/providers/azure-open-ai/gpt-4.1-mini.yaml @@ -5,12 +5,20 @@ 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: "*" external_ids: artificial_analysis_id: 9f7c7566-a704-49a2-a383-cb3181da33a4 diff --git a/providers/azure-open-ai/gpt-4.1.yaml b/providers/azure-open-ai/gpt-4.1.yaml index 9c4fb59e5..b63d9a10b 100644 --- a/providers/azure-open-ai/gpt-4.1.yaml +++ b/providers/azure-open-ai/gpt-4.1.yaml @@ -5,18 +5,30 @@ 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 external_ids: artificial_analysis_id: 3b608b70-6434-4baa-99ad-45d499703c67 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 0c0655800..41aa05dba 100644 --- a/providers/azure-open-ai/gpt-5-2025-08-07.yaml +++ b/providers/azure-open-ai/gpt-5-2025-08-07.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5 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: "*" external_ids: artificial_analysis_id: 48e50f00-1fd1-4acc-b337-61078aa341e6 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 4d98afa00..78f531442 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 @@ -3,26 +3,42 @@ 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: "*" external_ids: artificial_analysis_id: 29855680-7469-43eb-8b88-cd3fb1d99da3 diff --git a/providers/azure-open-ai/gpt-5-mini.yaml b/providers/azure-open-ai/gpt-5-mini.yaml index affa5b416..3fb1b08bd 100644 --- a/providers/azure-open-ai/gpt-5-mini.yaml +++ b/providers/azure-open-ai/gpt-5-mini.yaml @@ -3,26 +3,42 @@ 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: "*" external_ids: artificial_analysis_id: 29855680-7469-43eb-8b88-cd3fb1d99da3 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 48b064cf6..d9a0bdb81 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 @@ -1,28 +1,44 @@ canonical_model: openai/gpt-5-1 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: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 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 84e5b3761..94b927c28 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 150dbd464..b2d17a4f1 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 47fb746e2..3951aa7b3 100644 --- a/providers/azure-open-ai/gpt-5.1.yaml +++ b/providers/azure-open-ai/gpt-5.1.yaml @@ -1,28 +1,44 @@ canonical_model: openai/gpt-5-1 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: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 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 0a1dbc5fb..63c29a456 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 @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5-2 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: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/azure-open-ai/gpt-5.2.yaml b/providers/azure-open-ai/gpt-5.2.yaml index 0a8f5a331..f080dafb3 100644 --- a/providers/azure-open-ai/gpt-5.2.yaml +++ b/providers/azure-open-ai/gpt-5.2.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5-2 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: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/azure-open-ai/gpt-5.3-codex.yaml b/providers/azure-open-ai/gpt-5.3-codex.yaml index 2f3e9a413..f1f70a7c6 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 ab2991011..c8ea8cf78 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 @@ -1,54 +1,141 @@ canonical_model: openai/gpt-5-4 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 external_ids: 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 912e1f2f6..1ec5dbe51 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 @@ -1,22 +1,46 @@ canonical_model: openai/gpt-5-4-mini 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: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 diff --git a/providers/azure-open-ai/gpt-5.4-mini.yaml b/providers/azure-open-ai/gpt-5.4-mini.yaml index 06070ad10..b6818d1bd 100644 --- a/providers/azure-open-ai/gpt-5.4-mini.yaml +++ b/providers/azure-open-ai/gpt-5.4-mini.yaml @@ -1,22 +1,46 @@ canonical_model: openai/gpt-5-4-mini 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: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 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 c82fd579a..6cdca2c34 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 @@ -1,21 +1,33 @@ canonical_model: openai/gpt-5-4-nano 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: "*" external_ids: diff --git a/providers/azure-open-ai/gpt-5.4-nano.yaml b/providers/azure-open-ai/gpt-5.4-nano.yaml index 3bd364e96..a49eb0fa5 100644 --- a/providers/azure-open-ai/gpt-5.4-nano.yaml +++ b/providers/azure-open-ai/gpt-5.4-nano.yaml @@ -1,18 +1,30 @@ canonical_model: openai/gpt-5-4-nano 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 b00e86d64..a14524215 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 280eda622..83934f231 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 a3ecfc353..932f6e07e 100644 --- a/providers/azure-open-ai/gpt-5.4.yaml +++ b/providers/azure-open-ai/gpt-5.4.yaml @@ -1,10 +1,39 @@ canonical_model: openai/gpt-5-4 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: @@ -18,10 +47,39 @@ 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: @@ -35,10 +93,39 @@ 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 d8e67b982..6dc150014 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 @@ -1,10 +1,33 @@ canonical_model: openai/gpt-5-5 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: @@ -18,10 +41,33 @@ 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: @@ -35,10 +81,33 @@ 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 64808b183..f03de5c0c 100644 --- a/providers/azure-open-ai/gpt-5.5.yaml +++ b/providers/azure-open-ai/gpt-5.5.yaml @@ -1,10 +1,33 @@ canonical_model: openai/gpt-5-5 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: @@ -18,10 +41,33 @@ 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: @@ -35,10 +81,33 @@ 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 d3e1f7894..711d4ad70 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 @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-luna 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: @@ -16,13 +54,51 @@ 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: @@ -35,13 +111,51 @@ 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: @@ -54,7 +168,7 @@ 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 external_ids: diff --git a/providers/azure-open-ai/gpt-5.6-luna.yaml b/providers/azure-open-ai/gpt-5.6-luna.yaml index d3311cdbd..77b1da2ae 100644 --- a/providers/azure-open-ai/gpt-5.6-luna.yaml +++ b/providers/azure-open-ai/gpt-5.6-luna.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-luna 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 bbdd740ed..533927bea 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 @@ -1,60 +1,174 @@ canonical_model: openai/gpt-5-6-sol 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 external_ids: diff --git a/providers/azure-open-ai/gpt-5.6-sol.yaml b/providers/azure-open-ai/gpt-5.6-sol.yaml index e03ef152e..be865de5a 100644 --- a/providers/azure-open-ai/gpt-5.6-sol.yaml +++ b/providers/azure-open-ai/gpt-5.6-sol.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-sol 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 f7f55bc5d..051a070a9 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 @@ -1,60 +1,174 @@ canonical_model: openai/gpt-5-6-terra 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 external_ids: diff --git a/providers/azure-open-ai/gpt-5.6-terra.yaml b/providers/azure-open-ai/gpt-5.6-terra.yaml index e188af258..d5778ef37 100644 --- a/providers/azure-open-ai/gpt-5.6-terra.yaml +++ b/providers/azure-open-ai/gpt-5.6-terra.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-terra 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 ff8a1f678..816c3b2eb 100644 --- a/providers/azure-open-ai/gpt-5.yaml +++ b/providers/azure-open-ai/gpt-5.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5 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: "*" external_ids: artificial_analysis_id: 48e50f00-1fd1-4acc-b337-61078aa341e6 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 07783f3f7..3af29fb5a 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 @@ -1,60 +1,117 @@ canonical_model: openai/gpt-6-sol 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 external_ids: diff --git a/providers/azure-open-ai/gpt-6-sol.yaml b/providers/azure-open-ai/gpt-6-sol.yaml index 6cce91284..d397cfb2d 100644 --- a/providers/azure-open-ai/gpt-6-sol.yaml +++ b/providers/azure-open-ai/gpt-6-sol.yaml @@ -1,60 +1,117 @@ canonical_model: openai/gpt-6-sol 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 external_ids: diff --git a/providers/google-gemini/gemini-2.5-flash-image.yaml b/providers/google-gemini/gemini-2.5-flash-image.yaml index 894a718df..bcf0cb4f3 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 a852966cf..da68b222d 100644 --- a/providers/google-gemini/gemini-2.5-flash-lite.yaml +++ b/providers/google-gemini/gemini-2.5-flash-lite.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-2-5-flash-lite 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: "*" external_ids: artificial_analysis_id: 1d81aa1c-64c8-442a-9c41-81b37e407b91 diff --git a/providers/google-gemini/gemini-2.5-flash.yaml b/providers/google-gemini/gemini-2.5-flash.yaml index c6f63861b..65e884bb8 100644 --- a/providers/google-gemini/gemini-2.5-flash.yaml +++ b/providers/google-gemini/gemini-2.5-flash.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-2-5-flash 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: "*" external_ids: artificial_analysis_id: 6afbfb62-27e4-435e-9c85-d9fe1b92519e diff --git a/providers/google-gemini/gemini-2.5-pro.yaml b/providers/google-gemini/gemini-2.5-pro.yaml index 636dfc889..5d613a581 100644 --- a/providers/google-gemini/gemini-2.5-pro.yaml +++ b/providers/google-gemini/gemini-2.5-pro.yaml @@ -1,21 +1,40 @@ canonical_model: google/gemini-2-5-pro 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 external_ids: artificial_analysis_id: 27202e5f-c82d-4710-92e9-4317877d4883 diff --git a/providers/google-gemini/gemini-3-flash-preview.yaml b/providers/google-gemini/gemini-3-flash-preview.yaml index 9588d8ac5..fd324c8dd 100644 --- a/providers/google-gemini/gemini-3-flash-preview.yaml +++ b/providers/google-gemini/gemini-3-flash-preview.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-3-flash-preview 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 39f3b7411..cc0c74b9a 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 5933c69fb..3d95a8e28 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 0d381bd84..51a1507d1 100644 --- a/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml +++ b/providers/google-gemini/gemini-3.1-flash-lite-preview.yaml @@ -3,11 +3,19 @@ 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" external_ids: diff --git a/providers/google-gemini/gemini-3.1-flash-lite.yaml b/providers/google-gemini/gemini-3.1-flash-lite.yaml index 6c1a6c4bd..c176f6ddd 100644 --- a/providers/google-gemini/gemini-3.1-flash-lite.yaml +++ b/providers/google-gemini/gemini-3.1-flash-lite.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-3-1-flash-lite 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 31b94676e..ba3da1bd9 100644 --- a/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml +++ b/providers/google-gemini/gemini-3.1-pro-preview-customtools.yaml @@ -1,21 +1,40 @@ canonical_model: google/gemini-3-1-pro-preview-customtools 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 e9cc59124..7c1d3df53 100644 --- a/providers/google-gemini/gemini-3.1-pro-preview.yaml +++ b/providers/google-gemini/gemini-3.1-pro-preview.yaml @@ -1,21 +1,40 @@ canonical_model: google/gemini-3-1-pro-preview 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 external_ids: diff --git a/providers/google-gemini/gemini-3.5-flash-lite.yaml b/providers/google-gemini/gemini-3.5-flash-lite.yaml index 067f4b5b9..a87d23bb4 100644 --- a/providers/google-gemini/gemini-3.5-flash-lite.yaml +++ b/providers/google-gemini/gemini-3.5-flash-lite.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-3-5-flash-lite 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: "*" external_ids: artificial_analysis_id: 093b9df2-ebee-4309-943f-5a7e88360adf diff --git a/providers/google-gemini/gemini-3.5-flash.yaml b/providers/google-gemini/gemini-3.5-flash.yaml index db887df3e..546a458b6 100644 --- a/providers/google-gemini/gemini-3.5-flash.yaml +++ b/providers/google-gemini/gemini-3.5-flash.yaml @@ -1,11 +1,20 @@ canonical_model: google/gemini-3-5-flash 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: "*" external_ids: artificial_analysis_id: 0097ebf5-124f-42f6-9463-33b00e711f03 diff --git a/providers/google-gemini/gemini-3.6-flash.yaml b/providers/google-gemini/gemini-3.6-flash.yaml index d8dc6e29b..c229a3208 100644 --- a/providers/google-gemini/gemini-3.6-flash.yaml +++ b/providers/google-gemini/gemini-3.6-flash.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-3-6-flash 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: "*" external_ids: artificial_analysis_id: 78332c88-fe60-42c8-af9d-3617e44cf1f5 diff --git a/providers/google-gemini/gemini-3.7-flash.yaml b/providers/google-gemini/gemini-3.7-flash.yaml index 0fa6518d1..11499326b 100644 --- a/providers/google-gemini/gemini-3.7-flash.yaml +++ b/providers/google-gemini/gemini-3.7-flash.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-3-7-flash 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: "*" external_ids: artificial_analysis_id: b2331108-72ed-415a-82d1-188633875bbc 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 95ae8e5ab..6380c17d3 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 bfe0ce0a5..d8ccc4fad 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 7adbd1aff..b6a61449e 100644 --- a/providers/google-gemini/gemini-3.8-flash.yaml +++ b/providers/google-gemini/gemini-3.8-flash.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-3-8-flash 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: "*" external_ids: artificial_analysis_id: 8a999846-4c1d-4ce7-a8b7-1310a7166fd7 diff --git a/providers/google-gemini/gemini-4-argon.yaml b/providers/google-gemini/gemini-4-argon.yaml index 3f586c2af..2bb8f9f1c 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-latest.yaml b/providers/google-gemini/gemini-flash-latest.yaml index f79c2e50f..75bc1003f 100644 --- a/providers/google-gemini/gemini-flash-latest.yaml +++ b/providers/google-gemini/gemini-flash-latest.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-flash 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 98abcb25f..c9130e474 100644 --- a/providers/google-gemini/gemini-flash-lite-latest.yaml +++ b/providers/google-gemini/gemini-flash-lite-latest.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-flash-lite 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: 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-pro-latest.yaml b/providers/google-gemini/gemini-pro-latest.yaml index de26fc66a..0b77876b8 100644 --- a/providers/google-gemini/gemini-pro-latest.yaml +++ b/providers/google-gemini/gemini-pro-latest.yaml @@ -1,21 +1,40 @@ canonical_model: google/gemini-pro 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 abbaa60db..d84e4c7f4 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 bb60d5723..2368c18db 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 9c2031462..700f6672d 100644 --- a/providers/google-vertex/gemini-2.5-flash-lite.yaml +++ b/providers/google-vertex/gemini-2.5-flash-lite.yaml @@ -3,137 +3,272 @@ 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 external_ids: artificial_analysis_id: 1d81aa1c-64c8-442a-9c41-81b37e407b91 diff --git a/providers/google-vertex/gemini-2.5-flash.yaml b/providers/google-vertex/gemini-2.5-flash.yaml index 466eb6c79..00ef4a78d 100644 --- a/providers/google-vertex/gemini-2.5-flash.yaml +++ b/providers/google-vertex/gemini-2.5-flash.yaml @@ -1,220 +1,436 @@ canonical_model: google/gemini-2-5-flash 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 external_ids: artificial_analysis_id: 6afbfb62-27e4-435e-9c85-d9fe1b92519e diff --git a/providers/google-vertex/gemini-2.5-pro.yaml b/providers/google-vertex/gemini-2.5-pro.yaml index 57120cbb7..c9f0f1c76 100644 --- a/providers/google-vertex/gemini-2.5-pro.yaml +++ b/providers/google-vertex/gemini-2.5-pro.yaml @@ -1,309 +1,632 @@ canonical_model: google/gemini-2-5-pro 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 external_ids: diff --git a/providers/google-vertex/gemini-3-flash-preview.yaml b/providers/google-vertex/gemini-3-flash-preview.yaml index 4152c5a20..7c7f49822 100644 --- a/providers/google-vertex/gemini-3-flash-preview.yaml +++ b/providers/google-vertex/gemini-3-flash-preview.yaml @@ -1,13 +1,21 @@ canonical_model: google/gemini-3-flash-preview 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 e8717eeff..4233871ed 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 1e54da5c5..0a08c2277 100644 --- a/providers/google-vertex/gemini-3-pro-preview.yaml +++ b/providers/google-vertex/gemini-3-pro-preview.yaml @@ -1,484 +1,934 @@ canonical_model: google/gemini-3-pro-preview 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 a07caf7e2..b1697a5ea 100644 --- a/providers/google-vertex/gemini-3.1-pro-preview.yaml +++ b/providers/google-vertex/gemini-3.1-pro-preview.yaml @@ -1,21 +1,39 @@ canonical_model: google/gemini-3-1-pro-preview 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 external_ids: diff --git a/providers/google-vertex/gemini-3.5-flash.yaml b/providers/google-vertex/gemini-3.5-flash.yaml index 4d8c4f2f0..ee509b436 100644 --- a/providers/google-vertex/gemini-3.5-flash.yaml +++ b/providers/google-vertex/gemini-3.5-flash.yaml @@ -1,46 +1,100 @@ canonical_model: google/gemini-3-5-flash 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 external_ids: artificial_analysis_id: 0097ebf5-124f-42f6-9463-33b00e711f03 diff --git a/providers/google-vertex/gemini-3.6-flash.yaml b/providers/google-vertex/gemini-3.6-flash.yaml index 597fa815e..b4e76041e 100644 --- a/providers/google-vertex/gemini-3.6-flash.yaml +++ b/providers/google-vertex/gemini-3.6-flash.yaml @@ -2,10 +2,18 @@ canonical_model: google/gemini-3-6-flash 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 external_ids: artificial_analysis_id: 78332c88-fe60-42c8-af9d-3617e44cf1f5 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 f0f4bd7bc..c5e3b157e 100644 --- a/providers/google-vertex/google/gemini-2.5-flash-image.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash-image.yaml @@ -1,84 +1,126 @@ canonical_model: google/gemini-2-5-flash-image 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 8b9620e6d..5233c8158 100644 --- a/providers/google-vertex/google/gemini-2.5-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash-lite.yaml @@ -3,137 +3,272 @@ 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 external_ids: artificial_analysis_id: 1d81aa1c-64c8-442a-9c41-81b37e407b91 diff --git a/providers/google-vertex/google/gemini-2.5-flash.yaml b/providers/google-vertex/google/gemini-2.5-flash.yaml index 6b591da2d..d56f5cfb1 100644 --- a/providers/google-vertex/google/gemini-2.5-flash.yaml +++ b/providers/google-vertex/google/gemini-2.5-flash.yaml @@ -1,13 +1,22 @@ canonical_model: google/gemini-2-5-flash 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 external_ids: artificial_analysis_id: 6afbfb62-27e4-435e-9c85-d9fe1b92519e diff --git a/providers/google-vertex/google/gemini-2.5-pro.yaml b/providers/google-vertex/google/gemini-2.5-pro.yaml index 1c1451768..119db5d04 100644 --- a/providers/google-vertex/google/gemini-2.5-pro.yaml +++ b/providers/google-vertex/google/gemini-2.5-pro.yaml @@ -1,309 +1,632 @@ canonical_model: google/gemini-2-5-pro 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 external_ids: diff --git a/providers/google-vertex/google/gemini-3-flash-preview.yaml b/providers/google-vertex/google/gemini-3-flash-preview.yaml index a7e56fd81..ee83d10e2 100644 --- a/providers/google-vertex/google/gemini-3-flash-preview.yaml +++ b/providers/google-vertex/google/gemini-3-flash-preview.yaml @@ -1,13 +1,21 @@ canonical_model: google/gemini-3-flash-preview 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 ba0019d22..e35dfb77e 100644 --- a/providers/google-vertex/google/gemini-3-pro-image-preview.yaml +++ b/providers/google-vertex/google/gemini-3-pro-image-preview.yaml @@ -5,6 +5,21 @@ 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 ce96e1471..f3728d99d 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 039dd9d4f..4dcc193de 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 f5bf92372..32d14c471 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 da6f36065..cd9dc065e 100644 --- a/providers/google-vertex/google/gemini-3.1-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-3.1-flash-lite.yaml @@ -1,31 +1,58 @@ canonical_model: google/gemini-3-1-flash-lite 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 5348d9cdc..029686ca2 100644 --- a/providers/google-vertex/google/gemini-3.1-pro-preview.yaml +++ b/providers/google-vertex/google/gemini-3.1-pro-preview.yaml @@ -1,21 +1,39 @@ canonical_model: google/gemini-3-1-pro-preview 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 external_ids: 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 1c4f94934..24f388f7b 100644 --- a/providers/google-vertex/google/gemini-3.5-flash-lite.yaml +++ b/providers/google-vertex/google/gemini-3.5-flash-lite.yaml @@ -2,24 +2,48 @@ canonical_model: google/gemini-3-5-flash-lite 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 external_ids: artificial_analysis_id: 093b9df2-ebee-4309-943f-5a7e88360adf diff --git a/providers/google-vertex/google/gemini-3.5-flash.yaml b/providers/google-vertex/google/gemini-3.5-flash.yaml index 269fb0551..f91b17e04 100644 --- a/providers/google-vertex/google/gemini-3.5-flash.yaml +++ b/providers/google-vertex/google/gemini-3.5-flash.yaml @@ -1,53 +1,116 @@ canonical_model: google/gemini-3-5-flash 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 external_ids: artificial_analysis_id: 0097ebf5-124f-42f6-9463-33b00e711f03 diff --git a/providers/google-vertex/google/gemini-3.6-flash.yaml b/providers/google-vertex/google/gemini-3.6-flash.yaml index e968aad8d..48bdefaf3 100644 --- a/providers/google-vertex/google/gemini-3.6-flash.yaml +++ b/providers/google-vertex/google/gemini-3.6-flash.yaml @@ -2,24 +2,48 @@ canonical_model: google/gemini-3-6-flash 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 external_ids: artificial_analysis_id: 78332c88-fe60-42c8-af9d-3617e44cf1f5 diff --git a/providers/google-vertex/google/gemini-3.7-flash.yaml b/providers/google-vertex/google/gemini-3.7-flash.yaml index d1dd6eade..f15c687dd 100644 --- a/providers/google-vertex/google/gemini-3.7-flash.yaml +++ b/providers/google-vertex/google/gemini-3.7-flash.yaml @@ -2,24 +2,48 @@ canonical_model: google/gemini-3-7-flash 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 external_ids: artificial_analysis_id: b2331108-72ed-415a-82d1-188633875bbc diff --git a/providers/google-vertex/google/gemini-3.8-flash.yaml b/providers/google-vertex/google/gemini-3.8-flash.yaml index 790d8d75a..3c19142bc 100644 --- a/providers/google-vertex/google/gemini-3.8-flash.yaml +++ b/providers/google-vertex/google/gemini-3.8-flash.yaml @@ -2,24 +2,48 @@ canonical_model: google/gemini-3-8-flash 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 external_ids: artificial_analysis_id: 8a999846-4c1d-4ce7-a8b7-1310a7166fd7 diff --git a/providers/google-vertex/google/gemini-4-argon.yaml b/providers/google-vertex/google/gemini-4-argon.yaml index 9f4831d39..0a9bd65ef 100644 --- a/providers/google-vertex/google/gemini-4-argon.yaml +++ b/providers/google-vertex/google/gemini-4-argon.yaml @@ -1,54 +1,81 @@ canonical_model: google/gemini-4-argon 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 external_ids: 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 9c4524c3f..ea51c5de7 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 9b1e01aea..dff42d4b3 100644 --- a/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml +++ b/providers/microsoft-foundry/gpt-4.1-2025-04-14.yaml @@ -5,12 +5,20 @@ 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: "*" external_ids: artificial_analysis_id: 3b608b70-6434-4baa-99ad-45d499703c67 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 6babde40e..4314fd8db 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 @@ -5,12 +5,20 @@ 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" external_ids: diff --git a/providers/microsoft-foundry/gpt-4.1-mini.yaml b/providers/microsoft-foundry/gpt-4.1-mini.yaml index c4abeadd7..95b845de4 100644 --- a/providers/microsoft-foundry/gpt-4.1-mini.yaml +++ b/providers/microsoft-foundry/gpt-4.1-mini.yaml @@ -5,12 +5,20 @@ 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: "*" external_ids: artificial_analysis_id: 9f7c7566-a704-49a2-a383-cb3181da33a4 diff --git a/providers/microsoft-foundry/gpt-4.1.yaml b/providers/microsoft-foundry/gpt-4.1.yaml index ae2fdb64d..ee8429b78 100644 --- a/providers/microsoft-foundry/gpt-4.1.yaml +++ b/providers/microsoft-foundry/gpt-4.1.yaml @@ -5,18 +5,30 @@ 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" external_ids: diff --git a/providers/microsoft-foundry/gpt-5-2025-08-07.yaml b/providers/microsoft-foundry/gpt-5-2025-08-07.yaml index 409f35743..57f565550 100644 --- a/providers/microsoft-foundry/gpt-5-2025-08-07.yaml +++ b/providers/microsoft-foundry/gpt-5-2025-08-07.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5 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: "*" external_ids: artificial_analysis_id: 48e50f00-1fd1-4acc-b337-61078aa341e6 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 4d98afa00..78f531442 100644 --- a/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml +++ b/providers/microsoft-foundry/gpt-5-mini-2025-08-07.yaml @@ -3,26 +3,42 @@ 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: "*" external_ids: artificial_analysis_id: 29855680-7469-43eb-8b88-cd3fb1d99da3 diff --git a/providers/microsoft-foundry/gpt-5-mini.yaml b/providers/microsoft-foundry/gpt-5-mini.yaml index affa5b416..3fb1b08bd 100644 --- a/providers/microsoft-foundry/gpt-5-mini.yaml +++ b/providers/microsoft-foundry/gpt-5-mini.yaml @@ -3,26 +3,42 @@ 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: "*" external_ids: artificial_analysis_id: 29855680-7469-43eb-8b88-cd3fb1d99da3 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 48b064cf6..d9a0bdb81 100644 --- a/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml +++ b/providers/microsoft-foundry/gpt-5.1-2025-11-13.yaml @@ -1,28 +1,44 @@ canonical_model: openai/gpt-5-1 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: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 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 1116373d5..d08064367 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 9addd0fb5..904aaac8c 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 1a2e4643d..64880d1d3 100644 --- a/providers/microsoft-foundry/gpt-5.1.yaml +++ b/providers/microsoft-foundry/gpt-5.1.yaml @@ -1,28 +1,44 @@ canonical_model: openai/gpt-5-1 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: "*" external_ids: artificial_analysis_id: 4dc12a38-b18f-4c43-8e1b-678f8434b5b1 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 7215e4fdb..cab49ba0e 100644 --- a/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml +++ b/providers/microsoft-foundry/gpt-5.2-2025-12-11.yaml @@ -1,10 +1,14 @@ canonical_model: openai/gpt-5-2 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: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/microsoft-foundry/gpt-5.2.yaml b/providers/microsoft-foundry/gpt-5.2.yaml index 6ecc85542..ad8c29d27 100644 --- a/providers/microsoft-foundry/gpt-5.2.yaml +++ b/providers/microsoft-foundry/gpt-5.2.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5-2 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: "*" external_ids: artificial_analysis_id: 498862c3-f9ac-49d2-852f-16a02bb0c38f diff --git a/providers/microsoft-foundry/gpt-5.3-codex.yaml b/providers/microsoft-foundry/gpt-5.3-codex.yaml index f3e817ef5..43c96f7a4 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 7c4db6d5a..8d894c096 100644 --- a/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml +++ b/providers/microsoft-foundry/gpt-5.4-2026-03-05.yaml @@ -1,26 +1,113 @@ canonical_model: openai/gpt-5-4 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 external_ids: 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 912e1f2f6..1ec5dbe51 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 @@ -1,22 +1,46 @@ canonical_model: openai/gpt-5-4-mini 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: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 diff --git a/providers/microsoft-foundry/gpt-5.4-mini.yaml b/providers/microsoft-foundry/gpt-5.4-mini.yaml index bdb7ce16d..f1d7e9eb9 100644 --- a/providers/microsoft-foundry/gpt-5.4-mini.yaml +++ b/providers/microsoft-foundry/gpt-5.4-mini.yaml @@ -1,8 +1,16 @@ 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 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: "*" external_ids: artificial_analysis_id: ba242e40-83b7-4cd3-a0e0-b56237984914 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 009962fee..18547b154 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 @@ -1,21 +1,33 @@ canonical_model: openai/gpt-5-4-nano 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: "*" external_ids: diff --git a/providers/microsoft-foundry/gpt-5.4-nano.yaml b/providers/microsoft-foundry/gpt-5.4-nano.yaml index d71d257de..9c07f93d9 100644 --- a/providers/microsoft-foundry/gpt-5.4-nano.yaml +++ b/providers/microsoft-foundry/gpt-5.4-nano.yaml @@ -1,6 +1,10 @@ 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 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 dc5ccb94a..86c54b57c 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 62860c5de..8295ded59 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 1a27b8b88..4fb51e733 100644 --- a/providers/microsoft-foundry/gpt-5.4.yaml +++ b/providers/microsoft-foundry/gpt-5.4.yaml @@ -1,16 +1,103 @@ canonical_model: openai/gpt-5-4 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 db35399b2..14499737e 100644 --- a/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml +++ b/providers/microsoft-foundry/gpt-5.5-2026-04-24.yaml @@ -1,8 +1,31 @@ canonical_model: openai/gpt-5-5 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: @@ -16,8 +39,31 @@ 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: @@ -31,8 +77,31 @@ 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 c74cb87cd..ce792cc99 100644 --- a/providers/microsoft-foundry/gpt-5.5.yaml +++ b/providers/microsoft-foundry/gpt-5.5.yaml @@ -1,8 +1,31 @@ canonical_model: openai/gpt-5-5 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: @@ -16,8 +39,31 @@ 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: @@ -31,8 +77,31 @@ 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 d3e1f7894..711d4ad70 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 @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-luna 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: @@ -16,13 +54,51 @@ 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: @@ -35,13 +111,51 @@ 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: @@ -54,7 +168,7 @@ 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 external_ids: diff --git a/providers/microsoft-foundry/gpt-5.6-luna.yaml b/providers/microsoft-foundry/gpt-5.6-luna.yaml index 1aa205479..a35de1fba 100644 --- a/providers/microsoft-foundry/gpt-5.6-luna.yaml +++ b/providers/microsoft-foundry/gpt-5.6-luna.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-luna 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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: @@ -59,8 +173,46 @@ 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 9f5cf182f..352ed80fc 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 @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-sol 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 0272bd6f1..c76a0eb72 100644 --- a/providers/microsoft-foundry/gpt-5.6-sol.yaml +++ b/providers/microsoft-foundry/gpt-5.6-sol.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-sol 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 a652ef48a..719c09004 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 @@ -1,60 +1,174 @@ canonical_model: openai/gpt-5-6-terra 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 external_ids: diff --git a/providers/microsoft-foundry/gpt-5.6-terra.yaml b/providers/microsoft-foundry/gpt-5.6-terra.yaml index 66fc74519..1e953e216 100644 --- a/providers/microsoft-foundry/gpt-5.6-terra.yaml +++ b/providers/microsoft-foundry/gpt-5.6-terra.yaml @@ -2,8 +2,46 @@ canonical_model: openai/gpt-5-6-terra 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: @@ -21,8 +59,46 @@ 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: @@ -40,8 +116,46 @@ 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 ff8a1f678..816c3b2eb 100644 --- a/providers/microsoft-foundry/gpt-5.yaml +++ b/providers/microsoft-foundry/gpt-5.yaml @@ -1,22 +1,34 @@ canonical_model: openai/gpt-5 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: "*" external_ids: artificial_analysis_id: 48e50f00-1fd1-4acc-b337-61078aa341e6 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 9787f2449..11b4b3569 100644 --- a/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml +++ b/providers/microsoft-foundry/gpt-6-sol-2026-09-22.yaml @@ -1,79 +1,155 @@ canonical_model: openai/gpt-6-sol 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 external_ids: diff --git a/providers/microsoft-foundry/gpt-6-sol.yaml b/providers/microsoft-foundry/gpt-6-sol.yaml index 7857276bc..f0b8943d4 100644 --- a/providers/microsoft-foundry/gpt-6-sol.yaml +++ b/providers/microsoft-foundry/gpt-6-sol.yaml @@ -1,79 +1,155 @@ canonical_model: openai/gpt-6-sol 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 external_ids: 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 c887f6a6a..0b22d2ad5 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 c38baa7ed..0198da9bf 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 ac1e1a1ae..92630027d 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 447dcabdc..40c5b70f9 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 a4de06e9d..8c1789623 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 b20e85c63..2fc9adacb 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 45029aa81..577398e4a 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 99365fc3c..d4cdecaaf 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 c88865920..332cce897 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 8c886cb44..57cefaa71 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 104b5db66..081d007b6 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 9c2b872ac..8a0808b24 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 c7cec0a80..661dd6af5 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 7ff76f940..f6aedf9ec 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 446f7c568..0700306ef 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 02aeb2c7b..c2a6285e3 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 293ea5672..f07ce7796 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 35aa7dd3e..d13c31f94 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 f6f8e9432..71974a27f 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 f8f8650f7..b1e430b3d 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 b9ab743ca..d656adc6b 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 83f5e9f6c..5ed5c67a5 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 a55a6da2b..5fc528d52 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 61a43da12..b0016ed4e 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 d09ed6e91..1106be3ff 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 700a437eb..dbd49e1d6 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-5.6-luna.yaml b/providers/openai/gpt-5.6-luna.yaml index 30e04fd62..3d449075f 100644 --- a/providers/openai/gpt-5.6-luna.yaml +++ b/providers/openai/gpt-5.6-luna.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-5-6-luna 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-sol.yaml b/providers/openai/gpt-5.6-sol.yaml index a1e95e669..b14f1dbdb 100644 --- a/providers/openai/gpt-5.6-sol.yaml +++ b/providers/openai/gpt-5.6-sol.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-5-6-sol 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.6-terra.yaml b/providers/openai/gpt-5.6-terra.yaml index 1a75b5970..fa600edd0 100644 --- a/providers/openai/gpt-5.6-terra.yaml +++ b/providers/openai/gpt-5.6-terra.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-5-6-terra 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-5.yaml b/providers/openai/gpt-5.yaml index 05cf9ff0f..9fcd31219 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/gpt-6-astra.yaml b/providers/openai/gpt-6-astra.yaml index 668381a9f..64edb73bb 100644 --- a/providers/openai/gpt-6-astra.yaml +++ b/providers/openai/gpt-6-astra.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-astra costs: - cache_creation_input_token_cost: 0.0000125 cache_read_input_token_cost: 0.000001 + 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 input_cost_per_token: 0.000010 input_cost_per_token_batches: 0.000005 output_cost_per_token: 0.000050 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: @@ -26,6 +59,25 @@ 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 external_ids: artificial_analysis_id: 2f339a97-9a0d-499a-9cb5-e0db665bfa25 artificial_analysis_slug: gpt-6-astra diff --git a/providers/openai/gpt-6-luna.yaml b/providers/openai/gpt-6-luna.yaml index eb1fc576d..415c92177 100644 --- a/providers/openai/gpt-6-luna.yaml +++ b/providers/openai/gpt-6-luna.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-luna 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6-sol.yaml b/providers/openai/gpt-6-sol.yaml index 58321eec0..88d622ab9 100644 --- a/providers/openai/gpt-6-sol.yaml +++ b/providers/openai/gpt-6-sol.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-sol 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/openai/gpt-6.1-sol.yaml b/providers/openai/gpt-6.1-sol.yaml index df72dcfcc..1e7dde80f 100644 --- a/providers/openai/gpt-6.1-sol.yaml +++ b/providers/openai/gpt-6.1-sol.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-1-sol costs: - cache_creation_input_token_cost: 0.0000025 cache_read_input_token_cost: 1e-7 + 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 input_cost_per_token: 0.000002 input_cost_per_token_batches: 0.000001 output_cost_per_token: 0.00001 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: @@ -26,6 +59,25 @@ 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 external_ids: artificial_analysis_id: b25ac058-1e33-4c31-bbc9-a20c3ad0717a artificial_analysis_slug: gpt-6-1-sol diff --git a/providers/openai/o3-2025-04-16.yaml b/providers/openai/o3-2025-04-16.yaml index e1b989716..d7acfdb07 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 3f8149468..0399e6fde 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 30e27f2ea..2195faae3 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 d15bde7a7..2c3a9e3e5 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: diff --git a/providers/openai/ra-gpt-5.6-sol.yaml b/providers/openai/ra-gpt-5.6-sol.yaml index 5ccd2d8a9..3564e90c7 100644 --- a/providers/openai/ra-gpt-5.6-sol.yaml +++ b/providers/openai/ra-gpt-5.6-sol.yaml @@ -2,6 +2,25 @@ canonical_model: openai/ra-gpt-5-6-sol 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 @@ -11,6 +30,20 @@ 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 region: "*" tiered_pricing: cache_read: diff --git a/providers/truefoundry-managed/gpt-6-astra.yaml b/providers/truefoundry-managed/gpt-6-astra.yaml index b2010f2fd..729bd9ba9 100644 --- a/providers/truefoundry-managed/gpt-6-astra.yaml +++ b/providers/truefoundry-managed/gpt-6-astra.yaml @@ -1,31 +1,83 @@ canonical_model: openai/gpt-6-astra 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 external_ids: artificial_analysis_id: 2f339a97-9a0d-499a-9cb5-e0db665bfa25 artificial_analysis_slug: gpt-6-astra diff --git a/providers/truefoundry-managed/gpt-6-luna.yaml b/providers/truefoundry-managed/gpt-6-luna.yaml index 21678b009..38d1617b0 100644 --- a/providers/truefoundry-managed/gpt-6-luna.yaml +++ b/providers/truefoundry-managed/gpt-6-luna.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-luna 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 @@ -10,7 +29,21 @@ 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 358aabdd7..87dde233d 100644 --- a/providers/truefoundry-managed/gpt-6.1-sol.yaml +++ b/providers/truefoundry-managed/gpt-6.1-sol.yaml @@ -2,6 +2,25 @@ canonical_model: openai/gpt-6-1-sol 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 @@ -11,6 +30,20 @@ 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: @@ -26,6 +59,25 @@ 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 external_ids: artificial_analysis_id: b25ac058-1e33-4c31-bbc9-a20c3ad0717a artificial_analysis_slug: gpt-6-1-sol