diff --git a/.github/scripts/sdk-live-test/src/index.ts b/.github/scripts/sdk-live-test/src/index.ts index edc66cf20..ddf3c74ee 100644 --- a/.github/scripts/sdk-live-test/src/index.ts +++ b/.github/scripts/sdk-live-test/src/index.ts @@ -126,6 +126,10 @@ function targetsFromFilesList(listPath: string): Target[] { console.warn(`skip (no model: field): ${filePath}`); continue; } + if (modelId.endsWith(':batch')) { + console.warn(`skip (batch variant, not callable via chat/completions): ${filePath}`); + continue; + } out.push({ provider: parsed.provider, modelId }); } return out; diff --git a/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml index 4df14f969..37dd14b9d 100644 --- a/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml @@ -1,440 +1,440 @@ canonical_model: openai/gpt-6-1-terra costs: - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: us-west-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: us-west-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: us-east-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: us-east-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-west-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-west-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-south-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-south-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-north-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-central-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: eu-central-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ca-central-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-7 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-6 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-5 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-4 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-southeast-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-south-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-northeast-3 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-northeast-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: ap-east-2 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.25e-06 - cache_read_input_token_cost: 5e-08 - input_cost_per_token: 1e-06 - output_cost_per_token: 5e-06 + - 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 region: af-south-1 tiered_pricing: cache_read: - - cost_per_token: 1e-07 + - cost_per_token: 1e-7 from: 272000 cache_write: - - cost_per_token: 2.5e-06 + - cost_per_token: 2.5e-6 from: 272000 input: - - cost_per_token: 2e-06 + - cost_per_token: 2e-6 from: 272000 output: - - cost_per_token: 7.5e-06 + - cost_per_token: 7.5e-6 from: 272000 pricing_mode: cumulative features: @@ -470,6 +470,9 @@ params: - max type: string provisioning: serverless +removeParams: + - temperature + - top_p sources: - https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html - https://developers.openai.com/api/docs/models/gpt-6.1-terra diff --git a/providers/aws-bedrock/us.openai.gpt-6.1-terra.yaml b/providers/aws-bedrock/us.openai.gpt-6.1-terra.yaml index 3f1fde237..0f5cc29e5 100644 --- a/providers/aws-bedrock/us.openai.gpt-6.1-terra.yaml +++ b/providers/aws-bedrock/us.openai.gpt-6.1-terra.yaml @@ -1,98 +1,98 @@ canonical_model: openai/gpt-6-1-terra costs: - - cache_creation_input_token_cost: 1.375e-06 - cache_read_input_token_cost: 5.5e-08 - input_cost_per_token: 1.1e-06 - output_cost_per_token: 5.5e-06 + - cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 region: us-west-2 tiered_pricing: cache_read: - - cost_per_token: 1.1e-07 + - cost_per_token: 1.1e-7 from: 272000 cache_write: - - cost_per_token: 2.75e-06 + - cost_per_token: 2.75e-6 from: 272000 input: - - cost_per_token: 2.2e-06 + - cost_per_token: 2.2e-6 from: 272000 output: - - cost_per_token: 8.25e-06 + - cost_per_token: 8.25e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.375e-06 - cache_read_input_token_cost: 5.5e-08 - input_cost_per_token: 1.1e-06 - output_cost_per_token: 5.5e-06 + - cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 region: us-west-1 tiered_pricing: cache_read: - - cost_per_token: 1.1e-07 + - cost_per_token: 1.1e-7 from: 272000 cache_write: - - cost_per_token: 2.75e-06 + - cost_per_token: 2.75e-6 from: 272000 input: - - cost_per_token: 2.2e-06 + - cost_per_token: 2.2e-6 from: 272000 output: - - cost_per_token: 8.25e-06 + - cost_per_token: 8.25e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.375e-06 - cache_read_input_token_cost: 5.5e-08 - input_cost_per_token: 1.1e-06 - output_cost_per_token: 5.5e-06 + - cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 region: us-east-2 tiered_pricing: cache_read: - - cost_per_token: 1.1e-07 + - cost_per_token: 1.1e-7 from: 272000 cache_write: - - cost_per_token: 2.75e-06 + - cost_per_token: 2.75e-6 from: 272000 input: - - cost_per_token: 2.2e-06 + - cost_per_token: 2.2e-6 from: 272000 output: - - cost_per_token: 8.25e-06 + - cost_per_token: 8.25e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.375e-06 - cache_read_input_token_cost: 5.5e-08 - input_cost_per_token: 1.1e-06 - output_cost_per_token: 5.5e-06 + - cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 region: us-east-1 tiered_pricing: cache_read: - - cost_per_token: 1.1e-07 + - cost_per_token: 1.1e-7 from: 272000 cache_write: - - cost_per_token: 2.75e-06 + - cost_per_token: 2.75e-6 from: 272000 input: - - cost_per_token: 2.2e-06 + - cost_per_token: 2.2e-6 from: 272000 output: - - cost_per_token: 8.25e-06 + - cost_per_token: 8.25e-6 from: 272000 pricing_mode: cumulative - - cache_creation_input_token_cost: 1.375e-06 - cache_read_input_token_cost: 5.5e-08 - input_cost_per_token: 1.1e-06 - output_cost_per_token: 5.5e-06 + - cache_creation_input_token_cost: 1.375e-6 + cache_read_input_token_cost: 5.5e-8 + input_cost_per_token: 1.1e-6 + output_cost_per_token: 5.5e-6 region: ca-central-1 tiered_pricing: cache_read: - - cost_per_token: 1.1e-07 + - cost_per_token: 1.1e-7 from: 272000 cache_write: - - cost_per_token: 2.75e-06 + - cost_per_token: 2.75e-6 from: 272000 input: - - cost_per_token: 2.2e-06 + - cost_per_token: 2.2e-6 from: 272000 output: - - cost_per_token: 8.25e-06 + - cost_per_token: 8.25e-6 from: 272000 pricing_mode: cumulative features: @@ -128,6 +128,9 @@ params: - max type: string provisioning: serverless +removeParams: + - temperature + - top_p sources: - https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html - https://developers.openai.com/api/docs/models/gpt-6.1-terra