scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 86

feat(pricing): add AWS GovCloud and Azure Government pricing for missing models

Browse source 
Adds GovCloud (us-gov-west-1 / us-gov-east-1) pricing entries for Claude
Sonnet 5, Claude Opus 4.8, Nemotron Nano 3 30B, Nemotron Nano 12B v2,
Nemotron Super 3 120B, gpt-oss-20b, gpt-oss-120b, GPT-5.6 Terra, GPT-5.6
Luna, GPT-5.4, and grok-4.3 (west only), plus Azure Government entries
for gpt-5.1, o3-mini, text-embedding-3-large, and text-embedding-3-small.

Also fixes the existing gov llama3-8b entries, which carried the 70B
output rate ($2.65/MTok) instead of the $0.60/MTok the AWS offer file
publishes.
This commit is contained in:
mateo-berri 2026-08-29 12:02:52 -07:00
parent 06852ca290
commit 041a19d519
3 changed files with 1444 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

633
litellm/model_prices_and_context_window_backup.json
View file

@ -8479,6 +8479,15 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"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/text-embedding-3-small": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 2e-08,
@ -8488,6 +8497,15 @@
"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
},
"azure/text-embedding-ada-002": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1e-07,
@ -8883,6 +8901,42 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none"
},
"azure/us-gov/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.71875e-07,
"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_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,
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none"
},
"azure/us/gpt-5.1-chat": {
"cache_read_input_token_cost": 1.4e-07,
"deprecation_date": "2026-06-29",
@ -9074,6 +9128,22 @@
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us-gov/o3-mini": {
"deprecation_date": "2026-10-01",
"cache_read_input_token_cost": 7.57e-07,
"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/o4-mini-2025-04-16": {
"cache_read_input_token_cost": 3.1e-07,
"deprecation_date": "2026-10-16",
@ -11656,6 +11726,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 4.5e-06,
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
@ -11698,9 +11842,74 @@
"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-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,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_native_structured_output": 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-west-1/amazon.nova-pro-v1:0": {
"input_cost_per_token": 9.6e-07,
"litellm_provider": "bedrock",
@ -11840,6 +12049,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 4.5e-06,
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
@ -11882,9 +12165,74 @@
"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-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,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_native_structured_output": 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-west-1/meta.llama3-70b-instruct-v1:0": {
"input_cost_per_token": 2.65e-06,
"litellm_provider": "bedrock",
@ -39555,6 +39903,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"us-gov.anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"us-gov.anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"au.anthropic.claude-haiku-4-5-20251001-v1:0": {
"cache_creation_input_token_cost": 1.375e-06,
"cache_creation_input_token_cost_above_1hr": 2.2e-06,
@ -50004,6 +50426,72 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": {
"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,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.6-terra": {
"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,
"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
},
"bedrock_mantle/openai.gpt-5.6-cyber": {
"input_cost_per_token": 1.375e-05,
"cache_creation_input_token_cost": 1.71875e-05,
@ -50065,6 +50553,72 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
"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,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.6-luna": {
"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,
"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
},
"us.openai.gpt-5.6-sol": {
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
@ -50281,6 +50835,60 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05,
"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
},
"bedrock_mantle/google.gemma-4-31b": {
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 4e-07,
@ -50359,6 +50967,27 @@
"supports_vision": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
"use_openai_responses_path": true,
"input_cost_per_token": 1.5e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 2.4e-07,
"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/"
},
"bedrock_mantle/xai.grok-4.6": {
"use_openai_responses_path": true,
"input_cost_per_token": 2.2e-06,

633
model_prices_and_context_window.json
View file

@ -8479,6 +8479,15 @@
"mode": "embedding",
"output_cost_per_token": 0.0
},
"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/text-embedding-3-small": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 2e-08,
@ -8488,6 +8497,15 @@
"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
},
"azure/text-embedding-ada-002": {
"deprecation_date": "2028-02-09",
"input_cost_per_token": 1e-07,
@ -8883,6 +8901,42 @@
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none"
},
"azure/us-gov/gpt-5.1": {
"deprecation_date": "2027-05-15",
"cache_read_input_token_cost": 1.71875e-07,
"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_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,
"supports_none_reasoning_effort": true,
"default_reasoning_effort": "none"
},
"azure/us/gpt-5.1-chat": {
"cache_read_input_token_cost": 1.4e-07,
"deprecation_date": "2026-06-29",
@ -9074,6 +9128,22 @@
"supports_tool_choice": true,
"supports_vision": false
},
"azure/us-gov/o3-mini": {
"deprecation_date": "2026-10-01",
"cache_read_input_token_cost": 7.57e-07,
"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/o4-mini-2025-04-16": {
"cache_read_input_token_cost": 3.1e-07,
"deprecation_date": "2026-10-16",
@ -11656,6 +11726,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 4.5e-06,
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
@ -11698,9 +11842,74 @@
"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-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,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_native_structured_output": 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-west-1/amazon.nova-pro-v1:0": {
"input_cost_per_token": 9.6e-07,
"litellm_provider": "bedrock",
@ -11840,6 +12049,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": {
"cache_creation_input_token_cost": 4.5e-06,
"cache_creation_input_token_cost_above_1hr": 7.2e-06,
@ -11882,9 +12165,74 @@
"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-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,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_tool_choice": true,
"source": "https://aws.amazon.com/bedrock/pricing/",
"supports_native_structured_output": 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-west-1/meta.llama3-70b-instruct-v1:0": {
"input_cost_per_token": 2.65e-06,
"litellm_provider": "bedrock",
@ -39555,6 +39903,80 @@
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"us-gov.anthropic.claude-opus-4-8": {
"bedrock_converse_supports_strict_tools": false,
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"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_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 3e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"us-gov.anthropic.claude-sonnet-5": {
"bedrock_converse_supports_strict_tools": false,
"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_converse",
"max_input_tokens": 1000000,
"max_output_tokens": 128000,
"max_tokens": 128000,
"mode": "chat",
"output_cost_per_token": 1.2e-05,
"search_context_cost_per_query": {
"search_context_size_high": 0.01,
"search_context_size_low": 0.01,
"search_context_size_medium": 0.01
},
"supports_adaptive_thinking": true,
"supports_mid_conversation_system": true,
"supports_assistant_prefill": false,
"supports_computer_use": true,
"supports_function_calling": 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,
"supports_native_structured_output": true,
"supports_max_reasoning_effort": true,
"supports_output_config": true,
"bedrock_output_config_effort_ceiling": "xhigh",
"supports_parallel_tool_use_config": true,
"prompt_cache_min_tokens": 1024
},
"au.anthropic.claude-haiku-4-5-20251001-v1:0": {
"cache_creation_input_token_cost": 1.375e-06,
"cache_creation_input_token_cost_above_1hr": 2.2e-06,
@ -50004,6 +50426,72 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": {
"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,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.6-terra": {
"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,
"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
},
"bedrock_mantle/openai.gpt-5.6-cyber": {
"input_cost_per_token": 1.375e-05,
"cache_creation_input_token_cost": 1.71875e-05,
@ -50065,6 +50553,72 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.6-luna": {
"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,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.6-luna": {
"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,
"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
},
"us.openai.gpt-5.6-sol": {
"input_cost_per_token": 4.4e-06,
"input_cost_per_token_above_272k_tokens": 8.8e-06,
@ -50281,6 +50835,60 @@
"supports_tool_choice": true,
"supports_vision": true
},
"bedrock_mantle/us-gov-west-1/openai.gpt-5.4": {
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05,
"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
},
"bedrock_mantle/us-gov-east-1/openai.gpt-5.4": {
"input_cost_per_token": 3.3e-06,
"cache_read_input_token_cost": 3.3e-07,
"output_cost_per_token": 1.98e-05,
"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
},
"bedrock_mantle/google.gemma-4-31b": {
"input_cost_per_token": 1.4e-07,
"output_cost_per_token": 4e-07,
@ -50359,6 +50967,27 @@
"supports_vision": true,
"source": "https://aws.amazon.com/bedrock/pricing/"
},
"bedrock_mantle/us-gov-west-1/xai.grok-4.3": {
"use_openai_responses_path": true,
"input_cost_per_token": 1.5e-06,
"output_cost_per_token": 3e-06,
"cache_read_input_token_cost": 2.4e-07,
"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/"
},
"bedrock_mantle/xai.grok-4.6": {
"use_openai_responses_path": true,
"input_cost_per_token": 2.2e-06,

208
tests/test_litellm/test_bedrock_usgov_pricing.py
View file

@ -26,9 +26,7 @@ import pytest
@pytest.fixture(scope="module")
def model_data():
json_path = os.path.join(
os.path.dirname(__file__), "../../model_prices_and_context_window.json"
)
json_path = os.path.join(os.path.dirname(__file__), "../../model_prices_and_context_window.json")
with open(json_path) as f:
return json.load(f)
@ -51,21 +49,14 @@ def test_usgov_sonnet_4_5_pricing(model_data, model_key):
info = model_data[model_key]
assert info["input_cost_per_token"] == 3.6e-06, (
f"{model_key}: input_cost_per_token should be $3.60/MTok "
f"(got {info['input_cost_per_token']})"
f"{model_key}: input_cost_per_token should be $3.60/MTok (got {info['input_cost_per_token']})"
)
assert (
info["output_cost_per_token"] == 1.8e-05
), f"{model_key}: output_cost_per_token should be $18.00/MTok"
assert (
info["cache_creation_input_token_cost"] == 4.5e-06
), f"{model_key}: 5m cache write should be $4.50/MTok"
assert (
info["cache_creation_input_token_cost_above_1hr"] == 7.2e-06
), f"{model_key}: 1h cache write should be $7.20/MTok"
assert (
info["cache_read_input_token_cost"] == 3.6e-07
), f"{model_key}: cache read should be $0.36/MTok"
assert info["output_cost_per_token"] == 1.8e-05, f"{model_key}: output_cost_per_token should be $18.00/MTok"
assert info["cache_creation_input_token_cost"] == 4.5e-06, f"{model_key}: 5m cache write should be $4.50/MTok"
assert info["cache_creation_input_token_cost_above_1hr"] == 7.2e-06, (
f"{model_key}: 1h cache write should be $7.20/MTok"
)
assert info["cache_read_input_token_cost"] == 3.6e-07, f"{model_key}: cache read should be $0.36/MTok"
def test_usgov_carries_20_percent_premium_over_global(model_data):
@ -84,9 +75,7 @@ def test_usgov_carries_20_percent_premium_over_global(model_data):
"cache_read_input_token_cost",
):
ratio = usgov_info[field] / global_info[field]
assert (
abs(ratio - 1.2) < 1e-9
), f"{field}: us-gov / global ratio is {ratio}, expected 1.2"
assert abs(ratio - 1.2) < 1e-9, f"{field}: us-gov / global ratio is {ratio}, expected 1.2"
# The us-gov.anthropic.* cross-region inference profile is the only us-gov
@ -112,9 +101,7 @@ def test_usgov_cross_region_above_200k_carries_gov_premium(model_data, field, ex
"""
info = model_data[USGOV_CROSS_REGION_KEY]
assert field in info, f"{USGOV_CROSS_REGION_KEY}: missing field {field}"
assert (
info[field] == expected
), f"{USGOV_CROSS_REGION_KEY}: {field} should be {expected} (got {info[field]})"
assert info[field] == expected, f"{USGOV_CROSS_REGION_KEY}: {field} should be {expected} (got {info[field]})"
def test_usgov_cross_region_above_200k_ratio_to_global(model_data):
@ -127,6 +114,175 @@ def test_usgov_cross_region_above_200k_ratio_to_global(model_data):
usgov_info = model_data[USGOV_CROSS_REGION_KEY]
for field in EXPECTED_USGOV_ABOVE_200K:
ratio = usgov_info[field] / global_info[field]
assert (
abs(ratio - 1.2) < 1e-9
), f"{field}: us-gov / global ratio is {ratio}, expected 1.2"
assert abs(ratio - 1.2) < 1e-9, f"{field}: us-gov / global ratio is {ratio}, expected 1.2"
CLAUDE_GOV_EXPECTED = {
"anthropic.claude-sonnet-5": {
"input_cost_per_token": 2.4e-06,
"output_cost_per_token": 1.2e-05,
"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,
},
"anthropic.claude-opus-4-8": {
"input_cost_per_token": 6e-06,
"output_cost_per_token": 3e-05,
"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,
},
}
CLAUDE_GOV_KEYS = [
(gov_key, base_key)
for base_key in CLAUDE_GOV_EXPECTED
for gov_key in (
f"bedrock/us-gov-east-1/{base_key}",
f"bedrock/us-gov-west-1/{base_key}",
f"us-gov.{base_key}",
)
]
@pytest.mark.parametrize("gov_key,base_key", CLAUDE_GOV_KEYS)
def test_usgov_claude_sonnet5_opus48_pricing(model_data, gov_key, base_key):
"""Sonnet 5 and Opus 4.8 gov entries must match the rates AWS publishes
for both GovCloud regions on the Bedrock pricing page (1.2x global).
"""
assert gov_key in model_data, f"Missing model entry: {gov_key}"
info = model_data[gov_key]
for field, expected in CLAUDE_GOV_EXPECTED[base_key].items():
assert info[field] == expected, f"{gov_key}: {field} should be {expected} (got {info[field]})"
ratio = info[field] / model_data[base_key][field]
assert abs(ratio - 1.2) < 1e-9, f"{gov_key}: {field} gov/global ratio is {ratio}, expected 1.2"
CONVERSE_GOV_EXPECTED = {
"nvidia.nemotron-nano-3-30b": (7.2e-08, 2.88e-07),
"nvidia.nemotron-nano-12b-v2": (2.4e-07, 7.2e-07),
"nvidia.nemotron-super-3-120b": (1.8e-07, 7.8e-07),
"openai.gpt-oss-20b-1:0": (8.4e-08, 3.6e-07),
"openai.gpt-oss-120b-1:0": (1.8e-07, 7.2e-07),
}
@pytest.mark.parametrize("base_key", CONVERSE_GOV_EXPECTED)
@pytest.mark.parametrize("region", ["us-gov-east-1", "us-gov-west-1"])
def test_usgov_converse_model_pricing(model_data, region, base_key):
"""Nemotron and gpt-oss gov entries must match the AWS offer file
(version 20260826181919), which prices both GovCloud regions identically
at 1.2x commercial.
"""
gov_key = f"bedrock/{region}/{base_key}"
assert gov_key in model_data, f"Missing model entry: {gov_key}"
info = model_data[gov_key]
expected_input, expected_output = CONVERSE_GOV_EXPECTED[base_key]
assert info["input_cost_per_token"] == expected_input
assert info["output_cost_per_token"] == expected_output
assert info["litellm_provider"] == "bedrock"
base = model_data[base_key]
assert abs(info["input_cost_per_token"] / base["input_cost_per_token"] - 1.2) < 1e-9
assert abs(info["output_cost_per_token"] / base["output_cost_per_token"] - 1.2) < 1e-9
@pytest.mark.parametrize("region", ["us-gov-east-1", "us-gov-west-1"])
def test_usgov_llama3_8b_output_price_fixed(model_data, region):
"""The gov llama3-8b entries carried the 70B output rate ($2.65/MTok);
the offer file prices output at $0.60/MTok.
"""
info = model_data[f"bedrock/{region}/meta.llama3-8b-instruct-v1:0"]
assert info["input_cost_per_token"] == 3e-07
assert info["output_cost_per_token"] == 6e-07
MANTLE_GOV_TIERED_EXPECTED = {
"openai.gpt-5.6-luna": {
"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,
},
"openai.gpt-5.6-terra": {
"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,
},
}
@pytest.mark.parametrize("model", MANTLE_GOV_TIERED_EXPECTED)
@pytest.mark.parametrize("region", ["us-gov-east-1", "us-gov-west-1"])
def test_usgov_mantle_terra_luna_pricing(model_data, region, model):
"""Terra and Luna are GA in both GovCloud regions (AWS announcement
2026-08-24) at 1.2x commercial across every tier.
"""
gov_key = f"bedrock_mantle/{region}/{model}"
assert gov_key in model_data, f"Missing model entry: {gov_key}"
info = model_data[gov_key]
for field, expected in MANTLE_GOV_TIERED_EXPECTED[model].items():
assert info[field] == expected, f"{gov_key}: {field} should be {expected} (got {info[field]})"
assert info["litellm_provider"] == "bedrock_mantle"
@pytest.mark.parametrize("region", ["us-gov-east-1", "us-gov-west-1"])
def test_usgov_mantle_gpt_5_4_pricing_has_no_long_context_tier(model_data, region):
"""gpt-5.4 gov rates come from the offer file, which publishes only the
standard tier in GovCloud: no long-context SKUs exist there, unlike
commercial.
"""
gov_key = f"bedrock_mantle/{region}/openai.gpt-5.4"
assert gov_key in model_data, f"Missing model entry: {gov_key}"
info = model_data[gov_key]
assert info["input_cost_per_token"] == 3.3e-06
assert info["cache_read_input_token_cost"] == 3.3e-07
assert info["output_cost_per_token"] == 1.98e-05
assert not any(field.endswith("_above_272k_tokens") for field in info)
def test_usgov_mantle_grok_4_3_west_only(model_data):
"""grok-4.3 is available in us-gov-west-1 only: the model card and the
east offer file (which carries grok-4.6 instead) both say so.
"""
info = model_data["bedrock_mantle/us-gov-west-1/xai.grok-4.3"]
assert info["input_cost_per_token"] == 1.5e-06
assert info["output_cost_per_token"] == 3e-06
assert info["cache_read_input_token_cost"] == 2.4e-07
assert "bedrock_mantle/us-gov-east-1/xai.grok-4.3" not in model_data
AZURE_GOV_EXPECTED = {
"azure/us-gov/gpt-5.1": {
"input_cost_per_token": 1.71875e-06,
"cache_read_input_token_cost": 1.71875e-07,
"output_cost_per_token": 1.375e-05,
},
"azure/us-gov/o3-mini": {
"input_cost_per_token": 1.513e-06,
"cache_read_input_token_cost": 7.57e-07,
"output_cost_per_token": 6.05e-06,
},
"azure/us-gov/text-embedding-3-large": {"input_cost_per_token": 1.63e-07},
"azure/us-gov/text-embedding-3-small": {"input_cost_per_token": 2.5e-08},
}
@pytest.mark.parametrize("gov_key", AZURE_GOV_EXPECTED)
def test_azure_usgov_pricing(model_data, gov_key):
"""Azure Government meters from the Azure retail prices API
(usgovvirginia/usgovarizona, serviceName 'Foundry Models').
"""
assert gov_key in model_data, f"Missing model entry: {gov_key}"
info = model_data[gov_key]
for field, expected in AZURE_GOV_EXPECTED[gov_key].items():
assert info[field] == expected, f"{gov_key}: {field} should be {expected} (got {info[field]})"
assert info["litellm_provider"] == "azure"