scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

fix(models): absorb open registry PRs: govcloud bedrock and mantle, azure gov, openai tiered long-context, scaleway, together qwen3.8, azure ai cache and kimi k2.7 code, azure mai deprecations

Browse source 
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
mateo 2026-09-02 14:48:51 +00:00
parent 23977fc290
commit a7836ede15
5 changed files with 1341 additions and 45 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

605
litellm/model_prices_and_context_window_backup.json
View file

@ -9643,7 +9643,8 @@
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
]
],
"deprecation_date": "2026-10-01"
},
"azure_ai/MAI-Image-2.5-Flash": {
"input_cost_per_image_token": 1.75e-06,
@ -9656,7 +9657,8 @@
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
]
],
"deprecation_date": "2026-10-01"
},
"azure_ai/MAI-Image-2e": {
"deprecation_date": "2026-08-15",
@ -10155,7 +10157,9 @@
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.45e-07,
"supports_prompt_caching": true
},
"azure_ai/deepseek-v4-flash": {
"deprecation_date": "2028-02-20",
@ -10169,18 +10173,20 @@
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 2.8e-08,
"supports_prompt_caching": true
},
"azure_ai/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 2.8e-08,
"cache_read_input_token_cost": 1.4e-08,
"deprecation_date": "2026-12-03",
"input_cost_per_token": 1.9e-07,
"input_cost_per_token": 4.4e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.1e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -10400,11 +10406,13 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_video_input": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1e-07,
"supports_prompt_caching": true
},
"azure_ai/kimi-k2.6": {
"deprecation_date": "2027-04-16",
@ -10415,7 +10423,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
@ -10426,7 +10434,9 @@
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1.6e-07,
"supports_prompt_caching": true
},
"azure_ai/ministral-3b": {
"input_cost_per_token": 4e-08,
@ -12110,7 +12120,7 @@
"max_output_tokens": 2048,
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2.65e-06,
"output_cost_per_token": 6e-07,
"supports_pdf_input": true
},
"bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": {
@ -29098,16 +29108,19 @@
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
"cache_creation_input_token_cost_flex": 2.5e-06,
"cache_creation_input_token_cost_priority": 1e-05,
"cache_read_input_token_cost": 4e-07,
"cache_read_input_token_cost_above_272k_tokens": 8e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"cache_read_input_token_cost_priority": 8e-07,
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"input_cost_per_token_batches": 2e-06,
"input_cost_per_token_flex": 2e-06,
"input_cost_per_token_priority": 8e-06,
@ -29119,6 +29132,7 @@
"output_cost_per_token": 2e-05,
"output_cost_per_token_above_272k_tokens": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"output_cost_per_token_batches": 1e-05,
"output_cost_per_token_flex": 1e-05,
"output_cost_per_token_priority": 4e-05,
@ -29161,16 +29175,19 @@
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
"cache_creation_input_token_cost_flex": 2.5e-06,
"cache_creation_input_token_cost_priority": 1e-05,
"cache_read_input_token_cost": 4e-07,
"cache_read_input_token_cost_above_272k_tokens": 8e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"cache_read_input_token_cost_priority": 8e-07,
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"input_cost_per_token_batches": 2e-06,
"input_cost_per_token_flex": 2e-06,
"input_cost_per_token_priority": 8e-06,
@ -29182,6 +29199,7 @@
"output_cost_per_token": 2e-05,
"output_cost_per_token_above_272k_tokens": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"output_cost_per_token_batches": 1e-05,
"output_cost_per_token_flex": 1e-05,
"output_cost_per_token_priority": 4e-05,
@ -29225,16 +29243,19 @@
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
@ -29246,6 +29267,7 @@
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_above_272k_tokens_flex": 9e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
@ -29288,16 +29310,19 @@
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
@ -29309,6 +29334,7 @@
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_above_272k_tokens_flex": 9e-07,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
@ -29548,7 +29574,10 @@
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
"supports_minimal_reasoning_effort": false,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
@ -29602,7 +29631,10 @@
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
"supports_minimal_reasoning_effort": false,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
@ -29751,7 +29783,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-2026-03-05": {
"cache_read_input_token_cost": 2.5e-07,
@ -29800,7 +29835,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
@ -29849,7 +29887,9 @@
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
@ -29898,7 +29938,9 @@
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
@ -41350,13 +41392,13 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/Qwen/Qwen3.8-2.4T-A95B": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2.5e-06,
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1010000,
"max_tokens": 1010000,
"mode": "chat",
"output_cost_per_token": 6.25e-06,
"output_cost_per_token": 6e-06,
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
@ -57558,5 +57600,526 @@
"supported_endpoints": [
"/v1/audio/transcriptions"
]
},
"scaleway/glm-5.2": {
"input_cost_per_token": 1.8e-06,
"litellm_provider": "scaleway",
"max_input_tokens": 256000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 5.5e-06,
"source": "https://www.scaleway.com/en/pricing/model-as-a-service/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": false
},
"scaleway/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 8e-08,
"input_cost_per_token": 4e-07,
"litellm_provider": "scaleway",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://www.scaleway.com/en/pricing/model-as-a-service/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": false
},
"azure_ai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"deprecation_date": "2026-10-03",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": {
"input_cost_per_token": 7.2e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.88e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2.4e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_system_messages": true,
"supports_vision": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7.8e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": {
"input_cost_per_token": 8.4e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.6e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_1hr": 4.8e-06,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": false,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 7.5e-06,
"cache_creation_input_token_cost_above_1hr": 1.2e-05,
"cache_read_input_token_cost": 6e-07,
"input_cost_per_token": 6e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": {
"input_cost_per_token": 7.2e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.88e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2.4e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_system_messages": true,
"supports_vision": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7.8e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": {
"input_cost_per_token": 8.4e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.6e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_1hr": 4.8e-06,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": false,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-east-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 7.5e-06,
"cache_creation_input_token_cost_above_1hr": 1.2e-05,
"cache_read_input_token_cost": 6e-07,
"input_cost_per_token": 6e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 2.64e-06,
"input_cost_per_token_above_272k_tokens": 5.28e-06,
"cache_creation_input_token_cost": 3.3e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.6e-06,
"cache_read_input_token_cost": 2.64e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.28e-07,
"output_cost_per_token": 1.584e-05,
"output_cost_per_token_above_272k_tokens": 2.376e-05
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 2.64e-07,
"input_cost_per_token_above_272k_tokens": 5.28e-07,
"cache_creation_input_token_cost": 3.3e-07,
"cache_creation_input_token_cost_above_272k_tokens": 6.6e-07,
"cache_read_input_token_cost": 2.64e-08,
"cache_read_input_token_cost_above_272k_tokens": 5.28e-08,
"output_cost_per_token": 1.584e-06,
"output_cost_per_token_above_272k_tokens": 2.376e-06
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05
},
"bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
"use_openai_responses_path": true,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"input_cost_per_token": 1.5e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 2.4e-07
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05
},
"azure/us-gov/gpt-5.1": {
"cache_read_input_token_cost": 1.71875e-07,
"default_reasoning_effort": "none",
"deprecation_date": "2027-05-15",
"input_cost_per_token": 1.71875e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us-gov/o3-mini": {
"cache_read_input_token_cost": 7.57e-07,
"deprecation_date": "2026-10-01",
"input_cost_per_token": 1.513e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.05e-06,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us-gov/text-embedding-3-large": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1.63e-07,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"azure/us-gov/text-embedding-3-small": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 2.5e-08,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
}
}

605
model_prices_and_context_window.json
View file

@ -9643,7 +9643,8 @@
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
]
],
"deprecation_date": "2026-10-01"
},
"azure_ai/MAI-Image-2.5-Flash": {
"input_cost_per_image_token": 1.75e-06,
@ -9656,7 +9657,8 @@
"supported_endpoints": [
"/v1/images/generations",
"/v1/images/edits"
]
],
"deprecation_date": "2026-10-01"
},
"azure_ai/MAI-Image-2e": {
"deprecation_date": "2026-08-15",
@ -10155,7 +10157,9 @@
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 1.45e-07,
"supports_prompt_caching": true
},
"azure_ai/deepseek-v4-flash": {
"deprecation_date": "2028-02-20",
@ -10169,18 +10173,20 @@
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true
"supports_tool_choice": true,
"cache_read_input_token_cost": 2.8e-08,
"supports_prompt_caching": true
},
"azure_ai/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 2.8e-08,
"cache_read_input_token_cost": 1.4e-08,
"deprecation_date": "2026-12-03",
"input_cost_per_token": 1.9e-07,
"input_cost_per_token": 4.4e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 5.1e-07,
"output_cost_per_token": 1.32e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/deepseek/",
"supports_function_calling": true,
"supports_prompt_caching": true,
@ -10400,11 +10406,13 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 3e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/kimi-k2-5-now-in-microsoft-foundry/4492321",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supports_function_calling": true,
"supports_tool_choice": true,
"supports_video_input": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1e-07,
"supports_prompt_caching": true
},
"azure_ai/kimi-k2.6": {
"deprecation_date": "2027-04-16",
@ -10415,7 +10423,7 @@
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/introducing-kimi-k2-6-in-microsoft-foundry/4513125",
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
@ -10426,7 +10434,9 @@
"supports_function_calling": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
"supports_vision": true,
"cache_read_input_token_cost": 1.6e-07,
"supports_prompt_caching": true
},
"azure_ai/ministral-3b": {
"input_cost_per_token": 4e-08,
@ -12110,7 +12120,7 @@
"max_output_tokens": 2048,
"max_tokens": 2048,
"mode": "chat",
"output_cost_per_token": 2.65e-06,
"output_cost_per_token": 6e-07,
"supports_pdf_input": true
},
"bedrock/us-west-1/meta.llama3-70b-instruct-v1:0": {
@ -29098,16 +29108,19 @@
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
"cache_creation_input_token_cost_flex": 2.5e-06,
"cache_creation_input_token_cost_priority": 1e-05,
"cache_read_input_token_cost": 4e-07,
"cache_read_input_token_cost_above_272k_tokens": 8e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"cache_read_input_token_cost_priority": 8e-07,
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"input_cost_per_token_batches": 2e-06,
"input_cost_per_token_flex": 2e-06,
"input_cost_per_token_priority": 8e-06,
@ -29119,6 +29132,7 @@
"output_cost_per_token": 2e-05,
"output_cost_per_token_above_272k_tokens": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"output_cost_per_token_batches": 1e-05,
"output_cost_per_token_flex": 1e-05,
"output_cost_per_token_priority": 4e-05,
@ -29161,16 +29175,19 @@
"cache_creation_input_token_cost": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 1e-05,
"cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
"cache_creation_input_token_cost_flex": 2.5e-06,
"cache_creation_input_token_cost_priority": 1e-05,
"cache_read_input_token_cost": 4e-07,
"cache_read_input_token_cost_above_272k_tokens": 8e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_read_input_token_cost_flex": 2e-07,
"cache_read_input_token_cost_priority": 8e-07,
"input_cost_per_token": 4e-06,
"input_cost_per_token_above_272k_tokens": 8e-06,
"input_cost_per_token_above_272k_tokens_flex": 4e-06,
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"input_cost_per_token_batches": 2e-06,
"input_cost_per_token_flex": 2e-06,
"input_cost_per_token_priority": 8e-06,
@ -29182,6 +29199,7 @@
"output_cost_per_token": 2e-05,
"output_cost_per_token_above_272k_tokens": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"output_cost_per_token_batches": 1e-05,
"output_cost_per_token_flex": 1e-05,
"output_cost_per_token_priority": 4e-05,
@ -29225,16 +29243,19 @@
"cache_creation_input_token_cost": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens": 5e-06,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
"cache_creation_input_token_cost_flex": 1.25e-06,
"cache_creation_input_token_cost_priority": 5e-06,
"cache_read_input_token_cost": 2e-07,
"cache_read_input_token_cost_above_272k_tokens": 4e-07,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_read_input_token_cost_flex": 1e-07,
"cache_read_input_token_cost_priority": 4e-07,
"input_cost_per_token": 2e-06,
"input_cost_per_token_above_272k_tokens": 4e-06,
"input_cost_per_token_above_272k_tokens_flex": 2e-06,
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"input_cost_per_token_batches": 1e-06,
"input_cost_per_token_flex": 1e-06,
"input_cost_per_token_priority": 4e-06,
@ -29246,6 +29267,7 @@
"output_cost_per_token": 1.2e-05,
"output_cost_per_token_above_272k_tokens": 1.8e-05,
"output_cost_per_token_above_272k_tokens_flex": 9e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
"output_cost_per_token_batches": 6e-06,
"output_cost_per_token_flex": 6e-06,
"output_cost_per_token_priority": 2.4e-05,
@ -29288,16 +29310,19 @@
"cache_creation_input_token_cost": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens": 5e-07,
"cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
"cache_creation_input_token_cost_flex": 1.25e-07,
"cache_creation_input_token_cost_priority": 5e-07,
"cache_read_input_token_cost": 2e-08,
"cache_read_input_token_cost_above_272k_tokens": 4e-08,
"cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_read_input_token_cost_flex": 1e-08,
"cache_read_input_token_cost_priority": 4e-08,
"input_cost_per_token": 2e-07,
"input_cost_per_token_above_272k_tokens": 4e-07,
"input_cost_per_token_above_272k_tokens_flex": 2e-07,
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"input_cost_per_token_batches": 1e-07,
"input_cost_per_token_flex": 1e-07,
"input_cost_per_token_priority": 4e-07,
@ -29309,6 +29334,7 @@
"output_cost_per_token": 1.2e-06,
"output_cost_per_token_above_272k_tokens": 1.8e-06,
"output_cost_per_token_above_272k_tokens_flex": 9e-07,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"output_cost_per_token_batches": 6e-07,
"output_cost_per_token_flex": 6e-07,
"output_cost_per_token_priority": 2.4e-06,
@ -29548,7 +29574,10 @@
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
"supports_minimal_reasoning_effort": false,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-2026-04-23": {
"cache_read_input_token_cost": 5e-07,
@ -29602,7 +29631,10 @@
"supports_web_search": true,
"supports_none_reasoning_effort": true,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": false
"supports_minimal_reasoning_effort": false,
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
},
"gpt-5.5-pro": {
"cache_read_input_token_cost": 3e-06,
@ -29751,7 +29783,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-2026-03-05": {
"cache_read_input_token_cost": 2.5e-07,
@ -29800,7 +29835,10 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none",
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
},
"gpt-5.4-pro": {
"cache_read_input_token_cost": 3e-06,
@ -29849,7 +29887,9 @@
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-pro-2026-03-05": {
"cache_read_input_token_cost": 3e-06,
@ -29898,7 +29938,9 @@
"supports_web_search": true,
"supports_none_reasoning_effort": false,
"supports_xhigh_reasoning_effort": true,
"supports_minimal_reasoning_effort": true
"supports_minimal_reasoning_effort": true,
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 0.000135
},
"gpt-5.4-mini": {
"cache_read_input_token_cost": 7.5e-08,
@ -41350,13 +41392,13 @@
"source": "https://docs.together.ai/docs/serverless-models"
},
"together_ai/Qwen/Qwen3.8-2.4T-A95B": {
"cache_read_input_token_cost": 5e-07,
"input_cost_per_token": 2.5e-06,
"cache_read_input_token_cost": 2.5e-07,
"input_cost_per_token": 2e-06,
"litellm_provider": "together_ai",
"max_input_tokens": 1010000,
"max_tokens": 1010000,
"mode": "chat",
"output_cost_per_token": 6.25e-06,
"output_cost_per_token": 6e-06,
"source": "https://docs.together.ai/docs/serverless-models",
"supports_prompt_caching": true
},
@ -57558,5 +57600,526 @@
"supported_endpoints": [
"/v1/audio/transcriptions"
]
},
"scaleway/glm-5.2": {
"input_cost_per_token": 1.8e-06,
"litellm_provider": "scaleway",
"max_input_tokens": 256000,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"output_cost_per_token": 5.5e-06,
"source": "https://www.scaleway.com/en/pricing/model-as-a-service/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_vision": false
},
"scaleway/deepseek-v4-flash-0731": {
"cache_read_input_token_cost": 8e-08,
"input_cost_per_token": 4e-07,
"litellm_provider": "scaleway",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 8e-07,
"source": "https://www.scaleway.com/en/pricing/model-as-a-service/",
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_vision": false
},
"azure_ai/kimi-k2.7-code": {
"cache_read_input_token_cost": 1.9e-07,
"deprecation_date": "2026-10-03",
"input_cost_per_token": 9.5e-07,
"litellm_provider": "azure_ai",
"max_input_tokens": 262144,
"max_output_tokens": 262144,
"max_tokens": 262144,
"mode": "chat",
"output_cost_per_token": 4e-06,
"source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/kimi/",
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b": {
"input_cost_per_token": 7.2e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.88e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2.4e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_system_messages": true,
"supports_vision": true
},
"bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7.8e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0": {
"input_cost_per_token": 8.4e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.6e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-west-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_1hr": 4.8e-06,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": false,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 7.5e-06,
"cache_creation_input_token_cost_above_1hr": 1.2e-05,
"cache_read_input_token_cost": 6e-07,
"input_cost_per_token": 6e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": {
"input_cost_per_token": 7.2e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 262144,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 2.88e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_native_structured_output": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2": {
"input_cost_per_token": 2.4e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 8192,
"max_tokens": 8192,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_system_messages": true,
"supports_vision": true
},
"bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 256000,
"max_output_tokens": 32768,
"max_tokens": 32768,
"mode": "chat",
"output_cost_per_token": 7.8e-07,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_function_calling": true,
"supports_reasoning": true,
"supports_system_messages": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0": {
"input_cost_per_token": 8.4e-08,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3.6e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0": {
"input_cost_per_token": 1.8e-07,
"litellm_provider": "bedrock",
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 7.2e-07,
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true
},
"bedrock/us-gov-east-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 3e-06,
"cache_creation_input_token_cost_above_1hr": 4.8e-06,
"cache_read_input_token_cost": 2.4e-07,
"input_cost_per_token": 2.4e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": false,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock/us-gov-east-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"bedrock_output_config_effort_ceiling": "xhigh",
"cache_creation_input_token_cost": 7.5e-06,
"cache_creation_input_token_cost_above_1hr": 1.2e-05,
"cache_read_input_token_cost": 6e-07,
"input_cost_per_token": 6e-06,
"litellm_provider": "bedrock",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"prompt_cache_min_tokens": 1024,
"supports_adaptive_thinking": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": true,
"supports_max_reasoning_effort": true,
"supports_mid_conversation_system": true,
"supports_native_structured_output": true,
"supports_output_config": true,
"supports_parallel_tool_use_config": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_sampling_params": false,
"supports_tool_choice": true,
"supports_vision": true,
"supports_xhigh_reasoning_effort": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 2.64e-06,
"input_cost_per_token_above_272k_tokens": 5.28e-06,
"cache_creation_input_token_cost": 3.3e-06,
"cache_creation_input_token_cost_above_272k_tokens": 6.6e-06,
"cache_read_input_token_cost": 2.64e-07,
"cache_read_input_token_cost_above_272k_tokens": 5.28e-07,
"output_cost_per_token": 1.584e-05,
"output_cost_per_token_above_272k_tokens": 2.376e-05
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 2.64e-07,
"input_cost_per_token_above_272k_tokens": 5.28e-07,
"cache_creation_input_token_cost": 3.3e-07,
"cache_creation_input_token_cost_above_272k_tokens": 6.6e-07,
"cache_read_input_token_cost": 2.64e-08,
"cache_read_input_token_cost_above_272k_tokens": 5.28e-08,
"output_cost_per_token": 1.584e-06,
"output_cost_per_token_above_272k_tokens": 2.376e-06
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05
},
"bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
"use_openai_responses_path": true,
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 131072,
"max_output_tokens": 16384,
"max_tokens": 16384,
"mode": "chat",
"supported_endpoints": [
"/v1/chat/completions",
"/v1/responses"
],
"supports_function_calling": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"input_cost_per_token": 1.5e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 2.4e-07
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
"litellm_provider": "bedrock_mantle",
"max_input_tokens": 1050000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "responses",
"use_openai_responses_path": true,
"supported_endpoints": [
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text"
],
"supports_function_calling": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": true,
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05
},
"azure/us-gov/gpt-5.1": {
"cache_read_input_token_cost": 1.71875e-07,
"default_reasoning_effort": "none",
"deprecation_date": "2027-05-15",
"input_cost_per_token": 1.71875e-06,
"litellm_provider": "azure",
"max_input_tokens": 272000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.375e-05,
"supported_endpoints": [
"/v1/chat/completions",
"/v1/batch",
"/v1/responses"
],
"supported_modalities": [
"text",
"image"
],
"supported_output_modalities": [
"text",
"image"
],
"supports_function_calling": true,
"supports_native_streaming": true,
"supports_none_reasoning_effort": true,
"supports_parallel_function_calling": true,
"supports_pdf_input": true,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"supports_vision": true
},
"azure/us-gov/o3-mini": {
"cache_read_input_token_cost": 7.57e-07,
"deprecation_date": "2026-10-01",
"input_cost_per_token": 1.513e-06,
"litellm_provider": "azure",
"max_input_tokens": 200000,
"max_output_tokens": 100000,
"max_tokens": 100000,
"mode": "chat",
"output_cost_per_token": 6.05e-06,
"supports_prompt_caching": true,
"supports_reasoning": true,
"supports_response_schema": true,
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us-gov/text-embedding-3-large": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1.63e-07,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
},
"azure/us-gov/text-embedding-3-small": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 2.5e-08,
"litellm_provider": "azure",
"max_input_tokens": 8191,
"max_tokens": 8191,
"mode": "embedding",
"output_cost_per_token": 0.0
}
}

6
tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
View file

@ -1522,7 +1522,7 @@ def test_gpt_5_6_alias_prices_match_sol(local_model_cost_map):
sol = litellm.model_cost["gpt-5.6-sol"]
cost_fields = sorted(field for field in sol if "cost" in field)
assert len(cost_fields) == 23
assert len(cost_fields) == 27
for field in cost_fields:
assert alias.get(field) == sol.get(field), field
@ -4039,8 +4039,8 @@ def test_fast_service_tier_matches_priority_above_the_context_threshold(_local_m
)
assert fast == priority
assert fast[0] == pytest.approx(300_000 * 8e-06, rel=1e-9)
assert fast[1] == pytest.approx(1_000 * 3e-05, rel=1e-9)
assert fast[0] == pytest.approx(300_000 * 1.6e-05, rel=1e-9)
assert fast[1] == pytest.approx(1_000 * 6e-05, rel=1e-9)
def test_priority_reasoning_tokens_bill_at_the_priority_output_rate(_local_model_cost_map):

156
tests/test_litellm/test_openai_service_tier_long_context_pricing.py Normal file
View file

@ -0,0 +1,156 @@
import json
from functools import lru_cache
from pathlib import Path
import pytest
import litellm
REPO_ROOT = Path(__file__).parents[2]
MAIN_PATH = REPO_ROOT / "model_prices_and_context_window.json"
BACKUP_PATH = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json"
FLEX_LONG_CONTEXT = {
"gpt-5.4": {
"input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
"output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
},
"gpt-5.4-pro": {
"input_cost_per_token_above_272k_tokens_flex": 3e-05,
"output_cost_per_token_above_272k_tokens_flex": 0.000135,
},
"gpt-5.5": {
"input_cost_per_token_above_272k_tokens_flex": 5e-06,
"output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
"cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
},
}
PRIORITY_LONG_CONTEXT = {
"gpt-5.6": {
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
},
"gpt-5.6-sol": {
"input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
"output_cost_per_token_above_272k_tokens_priority": 6e-05,
"cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
"cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05,
},
"gpt-5.6-terra": {
"input_cost_per_token_above_272k_tokens_priority": 8e-06,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05,
},
"gpt-5.6-luna": {
"input_cost_per_token_above_272k_tokens_priority": 8e-07,
"output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
"cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
"cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06,
},
}
EXPECTED = {**FLEX_LONG_CONTEXT, **PRIORITY_LONG_CONTEXT}
NO_PUBLISHED_PRIORITY_LONG_CONTEXT = ("gpt-5.4", "gpt-5.5")
@pytest.fixture(autouse=True)
def _local_model_cost_map(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
@lru_cache(maxsize=2)
def _load(path: Path) -> dict[str, dict[str, object]]:
with open(path) as f:
return json.load(f)
@pytest.mark.parametrize("path", [MAIN_PATH, BACKUP_PATH], ids=["main", "backup"])
@pytest.mark.parametrize("model", sorted(EXPECTED))
def test_service_tier_long_context_rates_are_published(model: str, path: Path) -> None:
"""Each tier must carry its own above-272K rates, in both price files."""
info = _load(path).get(model)
assert info is not None, f"{model} not found in {path.name}"
for key, expected in EXPECTED[model].items():
assert info.get(key) == pytest.approx(expected), f"{model}.{key} is {info.get(key)!r}, expected {expected!r}"
@pytest.mark.parametrize("model", sorted(EXPECTED))
def test_tier_long_context_rate_is_half_or_double_the_standard(model: str) -> None:
"""Flex is half the standard long-context rate; priority is double it."""
info = _load(MAIN_PATH)[model]
tier = "flex" if model in FLEX_LONG_CONTEXT else "priority"
ratio = 0.5 if tier == "flex" else 2.0
for base in ("input_cost_per_token", "output_cost_per_token"):
standard = info[f"{base}_above_272k_tokens"]
tiered = info[f"{base}_above_272k_tokens_{tier}"]
assert tiered == pytest.approx(standard * ratio), (
f"{model}.{base}_above_272k_tokens_{tier} is {tiered!r}, "
f"expected {ratio}x the standard long-context rate {standard!r}"
)
@pytest.mark.parametrize("model", NO_PUBLISHED_PRIORITY_LONG_CONTEXT)
def test_no_priority_long_context_rates_where_openai_publishes_none(model: str) -> None:
"""Guard against back-filling a rate OpenAI does not publish."""
info = _load(MAIN_PATH)[model]
assert "input_cost_per_token_above_272k_tokens_priority" not in info
LONG_CONTEXT_PROMPT_TOKENS = 300_000
COMPLETION_TOKENS = 1_000
TIERED_COST_CASES = [
("gpt-5.4", "flex", 2.5e-06, 1.125e-05),
("gpt-5.4-pro", "flex", 3e-05, 0.000135),
("gpt-5.5", "flex", 5e-06, 2.25e-05),
("gpt-5.6", "priority", 1.6e-05, 6e-05),
("gpt-5.6-sol", "priority", 1.6e-05, 6e-05),
("gpt-5.6-terra", "priority", 8e-06, 3.6e-05),
("gpt-5.6-luna", "priority", 8e-07, 3.6e-06),
]
@pytest.mark.parametrize("model,tier,input_rate,output_rate", TIERED_COST_CASES)
def test_cost_per_token_bills_long_context_at_the_tier_rate(
model: str, tier: str, input_rate: float, output_rate: float
) -> None:
"""A prompt over 272K on flex or priority must bill at that tier's long-context rate."""
input_cost, output_cost = litellm.cost_per_token(
model=model,
prompt_tokens=LONG_CONTEXT_PROMPT_TOKENS,
completion_tokens=COMPLETION_TOKENS,
service_tier=tier,
)
assert input_cost == pytest.approx(LONG_CONTEXT_PROMPT_TOKENS * input_rate)
assert output_cost == pytest.approx(COMPLETION_TOKENS * output_rate)
@pytest.mark.parametrize("model,tier,input_rate,output_rate", TIERED_COST_CASES)
def test_cost_per_token_tier_differs_from_the_standard_long_context_cost(
model: str, tier: str, input_rate: float, output_rate: float
) -> None:
"""Flex halves the standard long-context bill and priority doubles it."""
ratio = 0.5 if tier == "flex" else 2.0
standard = sum(
litellm.cost_per_token(
model=model,
prompt_tokens=LONG_CONTEXT_PROMPT_TOKENS,
completion_tokens=COMPLETION_TOKENS,
)
)
tiered = sum(
litellm.cost_per_token(
model=model,
prompt_tokens=LONG_CONTEXT_PROMPT_TOKENS,
completion_tokens=COMPLETION_TOKENS,
service_tier=tier,
)
)
assert tiered == pytest.approx(standard * ratio)

14
whitelisted_bedrock_models.txt
View file

@ -217,3 +217,17 @@ bedrock/us-east-1/zai.glm-5
bedrock/us-west-2/zai.glm-5
bedrock/us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0
bedrock/us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0
bedrock/us-gov-west-1/nvidia.nemotron-nano-3-30b
bedrock/us-gov-west-1/nvidia.nemotron-nano-12b-v2
bedrock/us-gov-west-1/nvidia.nemotron-super-3-120b
bedrock/us-gov-west-1/openai.gpt-oss-20b-1:0
bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0
bedrock/us-gov-west-1/anthropic.claude-sonnet-5
bedrock/us-gov-west-1/anthropic.claude-opus-4-8
bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b
bedrock/us-gov-east-1/nvidia.nemotron-nano-12b-v2
bedrock/us-gov-east-1/nvidia.nemotron-super-3-120b
bedrock/us-gov-east-1/openai.gpt-oss-20b-1:0
bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0
bedrock/us-gov-east-1/anthropic.claude-sonnet-5
bedrock/us-gov-east-1/anthropic.claude-opus-4-8