Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .github/test/model.cue
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down
109 changes: 87 additions & 22 deletions providers/aws-bedrock-mantle/deepseek.v3.1.yaml
Original file line number Diff line number Diff line change
@@ -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
Comment thread
Archit-Kumar-16 marked this conversation as resolved.
- 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
Expand Down
32 changes: 28 additions & 4 deletions providers/aws-bedrock-mantle/google.gemma-4-26b-a4b.yaml
Original file line number Diff line number Diff line change
@@ -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
Expand Down
32 changes: 28 additions & 4 deletions providers/aws-bedrock-mantle/google.gemma-4-31b.yaml
Original file line number Diff line number Diff line change
@@ -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
Expand Down
32 changes: 28 additions & 4 deletions providers/aws-bedrock-mantle/google.gemma-4-e2b.yaml
Original file line number Diff line number Diff line change
@@ -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
Expand Down
108 changes: 87 additions & 21 deletions providers/aws-bedrock-mantle/moonshotai.kimi-k2-thinking.yaml
Original file line number Diff line number Diff line change
@@ -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
Expand Down
Loading
Loading