From 7a1b15930e38c70ad3340418f9a5767e21d26594 Mon Sep 17 00:00:00 2001 From: Truefoundry Models Bot Date: Mon, 26 Oct 2026 18:21:00 +0000 Subject: [PATCH 1/3] feat(aws-bedrock/global.openai.gpt-6.1-terra): add new models [bot] --- .../global.openai.gpt-6.1-terra.yaml | 26 +++++++++++++++++++ 1 file changed, 26 insertions(+) create mode 100644 providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml diff --git a/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml new file mode 100644 index 000000000..60ce959ed --- /dev/null +++ b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml @@ -0,0 +1,26 @@ +costs: + - region: us-west-2 + - region: us-west-1 + - region: us-east-2 + - region: us-east-1 + - region: eu-west-2 + - region: eu-west-1 + - region: eu-south-2 + - region: eu-south-1 + - region: eu-north-1 + - region: eu-central-2 + - region: eu-central-1 + - region: ca-central-1 + - region: ap-southeast-7 + - region: ap-southeast-6 + - region: ap-southeast-5 + - region: ap-southeast-4 + - region: ap-southeast-2 + - region: ap-southeast-1 + - region: ap-south-1 + - region: ap-northeast-3 + - region: ap-northeast-1 + - region: ap-east-2 + - region: af-south-1 +mode: unknown +model: global.openai.gpt-6.1-terra From 26c58893d1a2bb8577a652e03f968896a53b497e Mon Sep 17 00:00:00 2001 From: Truefoundry Models Bot Date: Mon, 26 Oct 2026 18:23:02 +0000 Subject: [PATCH 2/3] feat(aws-bedrock): update model YAMLs [bot] --- .../global.openai.gpt-6.1-terra.yaml | 5 ++++- .../nvidia.nemotron-super-3-120b.yaml | 18 +++++++++--------- .../aws-bedrock/writer.palmyra-vision-7b.yaml | 12 ++++++------ 3 files changed, 19 insertions(+), 16 deletions(-) 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 60ce959ed..8744636dd 100644 --- a/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml @@ -22,5 +22,8 @@ costs: - region: ap-northeast-1 - region: ap-east-2 - region: af-south-1 -mode: unknown +mode: chat +# GPT-6.1 Terra is not on the AWS Bedrock model card index or the pricing page, so pricing, limits and features are not found in official docs. model: global.openai.gpt-6.1-terra +supportedModes: + - chat diff --git a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml index 8bbeb5225..ae0f61259 100644 --- a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml @@ -72,6 +72,15 @@ costs: input_cost_per_token: 3.15e-7 output_cost_per_token: 1.365e-6 region: eu-south-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: eu-north-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: eu-central-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: ap-southeast-3 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3.25e-7 @@ -99,15 +108,6 @@ costs: input_cost_per_token: 3.15e-7 output_cost_per_token: 1.365e-6 region: ap-northeast-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: eu-north-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: eu-central-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: ap-southeast-3 features: - function_calling - tool_choice diff --git a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml index b0a892e9b..988a23fe9 100644 --- a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml +++ b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml @@ -108,6 +108,9 @@ costs: 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 + output_cost_per_token: 6e-7 + region: ap-southeast-1 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3e-7 @@ -117,6 +120,9 @@ costs: 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 + output_cost_per_token: 6e-7 + region: ap-northeast-2 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3e-7 @@ -126,12 +132,6 @@ costs: input_cost_per_token: 2.625e-7 output_cost_per_token: 1.05e-6 region: ap-northeast-1 - - input_cost_per_token: 1.5e-7 - output_cost_per_token: 6e-7 - region: ap-southeast-1 - - input_cost_per_token: 1.5e-7 - output_cost_per_token: 6e-7 - region: ap-northeast-2 features: - system_messages - function_calling From 87cb2993980d336f161d331fabd6a72da7000157 Mon Sep 17 00:00:00 2001 From: Archit Kumar <108719922+Archit-Kumar-16@users.noreply.github.com> Date: Tue, 27 Oct 2026 11:43:13 +0530 Subject: [PATCH 3/3] Fix model config Co-Authored-By: Claude Opus 5 (1M context) --- .../global.openai.gpt-6.1-terra.yaml | 499 +++++++++++++++++- .../nvidia.nemotron-super-3-120b.yaml | 18 +- .../aws-bedrock/writer.palmyra-vision-7b.yaml | 12 +- 3 files changed, 490 insertions(+), 39 deletions(-) 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 8744636dd..4df14f969 100644 --- a/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml +++ b/providers/aws-bedrock/global.openai.gpt-6.1-terra.yaml @@ -1,29 +1,480 @@ +canonical_model: openai/gpt-6-1-terra costs: - - region: us-west-2 - - region: us-west-1 - - region: us-east-2 - - region: us-east-1 - - region: eu-west-2 - - region: eu-west-1 - - region: eu-south-2 - - region: eu-south-1 - - region: eu-north-1 - - region: eu-central-2 - - region: eu-central-1 - - region: ca-central-1 - - region: ap-southeast-7 - - region: ap-southeast-6 - - region: ap-southeast-5 - - region: ap-southeast-4 - - region: ap-southeast-2 - - region: ap-southeast-1 - - region: ap-south-1 - - region: ap-northeast-3 - - region: ap-northeast-1 - - region: ap-east-2 - - region: af-south-1 + - 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 + region: us-west-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: us-west-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: us-east-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: us-east-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-west-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-west-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-south-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-south-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-north-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-central-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: eu-central-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ca-central-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-7 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-6 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-5 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-4 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-southeast-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-south-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-northeast-3 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-northeast-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: ap-east-2 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + 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 + region: af-south-1 + tiered_pricing: + cache_read: + - cost_per_token: 1e-07 + from: 272000 + cache_write: + - cost_per_token: 2.5e-06 + from: 272000 + input: + - cost_per_token: 2e-06 + from: 272000 + output: + - cost_per_token: 7.5e-06 + from: 272000 + pricing_mode: cumulative +features: + - function_calling + - parallel_function_calling + - tool_choice + - system_messages + - json_output + - prompt_caching + - structured_output +limits: + context_window: 1050000 + max_input_tokens: 922000 + max_output_tokens: 128000 + max_tokens: 128000 +modalities: + input: + - text + - image + output: + - text mode: chat -# GPT-6.1 Terra is not on the AWS Bedrock model card index or the pricing page, so pricing, limits and features are not found in official docs. model: global.openai.gpt-6.1-terra +params: + - defaultValue: medium + key: reasoning_effort + supportedValues: + - none + - low + - medium + - high + - xhigh + - max + type: string +provisioning: serverless +sources: + - https://docs.aws.amazon.com/bedrock/latest/userguide/model-cards-openai.html + - https://developers.openai.com/api/docs/models/gpt-6.1-terra +status: active supportedModes: - chat + - responses +thinking: true diff --git a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml index ae0f61259..8bbeb5225 100644 --- a/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml +++ b/providers/aws-bedrock/nvidia.nemotron-super-3-120b.yaml @@ -72,15 +72,6 @@ costs: input_cost_per_token: 3.15e-7 output_cost_per_token: 1.365e-6 region: eu-south-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: eu-north-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: eu-central-1 - - input_cost_per_token: 1.8e-7 - output_cost_per_token: 7.8e-7 - region: ap-southeast-3 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3.25e-7 @@ -108,6 +99,15 @@ costs: input_cost_per_token: 3.15e-7 output_cost_per_token: 1.365e-6 region: ap-northeast-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: eu-north-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: eu-central-1 + - input_cost_per_token: 1.8e-7 + output_cost_per_token: 7.8e-7 + region: ap-southeast-3 features: - function_calling - tool_choice diff --git a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml index 988a23fe9..b0a892e9b 100644 --- a/providers/aws-bedrock/writer.palmyra-vision-7b.yaml +++ b/providers/aws-bedrock/writer.palmyra-vision-7b.yaml @@ -108,9 +108,6 @@ costs: 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 - output_cost_per_token: 6e-7 - region: ap-southeast-1 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3e-7 @@ -120,9 +117,6 @@ costs: 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 - output_cost_per_token: 6e-7 - region: ap-northeast-2 - flex_pricing: input_cost_per_token: 7.5e-8 output_cost_per_token: 3e-7 @@ -132,6 +126,12 @@ costs: input_cost_per_token: 2.625e-7 output_cost_per_token: 1.05e-6 region: ap-northeast-1 + - input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + region: ap-southeast-1 + - input_cost_per_token: 1.5e-7 + output_cost_per_token: 6e-7 + region: ap-northeast-2 features: - system_messages - function_calling