From 9a1c0145dab0a12b45a98526b4dbbbc4c592bee0 Mon Sep 17 00:00:00 2001 From: Yuta Saito Date: Sun, 5 Oct 2025 09:20:17 +0900 Subject: [PATCH 1/2] feat: add Global Cross-Region Inference --- litellm/llms/bedrock/common_utils.py | 2 +- ...odel_prices_and_context_window_backup.json | 78 +++++++++++++------ model_prices_and_context_window.json | 78 +++++++++++++------ 3 files changed, 109 insertions(+), 49 deletions(-) diff --git a/litellm/llms/bedrock/common_utils.py b/litellm/llms/bedrock/common_utils.py index 241359d937e..bd371414db5 100644 --- a/litellm/llms/bedrock/common_utils.py +++ b/litellm/llms/bedrock/common_utils.py @@ -440,7 +440,7 @@ class BedrockModelInfo(BaseLLMModelInfo): """ Abbreviations of regions AWS Bedrock supports for cross region inference """ - return ["us", "eu", "apac", "jp"] + return ["global", "us", "eu", "apac", "jp"] @staticmethod def get_bedrock_route( diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7ed04dc79c9..72ff60883b0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -7838,19 +7838,19 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_above_200k_tokens": 6.6e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11820,6 +11820,36 @@ "video" ] }, + "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-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": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "gpt-3.5-turbo": { "input_cost_per_token": 0.5e-06, "litellm_provider": "openai", @@ -14219,19 +14249,19 @@ "output_cost_per_token": 1.8e-08 }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_above_200k_tokens": 6.6e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -19848,19 +19878,19 @@ "tool_use_system_prompt_tokens": 159 }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 33e-07, + "input_cost_per_token": 33e-06, + "input_cost_per_token_above_200k_tokens": 66e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 66e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7ed04dc79c9..72ff60883b0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -7838,19 +7838,19 @@ "tool_use_system_prompt_tokens": 159 }, "eu.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_above_200k_tokens": 6.6e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -11820,6 +11820,36 @@ "video" ] }, + "global.anthropic.claude-sonnet-4-5-20250929-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 64000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 1.5e-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": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "gpt-3.5-turbo": { "input_cost_per_token": 0.5e-06, "litellm_provider": "openai", @@ -14219,19 +14249,19 @@ "output_cost_per_token": 1.8e-08 }, "jp.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, + "input_cost_per_token_above_200k_tokens": 6.6e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -19848,19 +19878,19 @@ "tool_use_system_prompt_tokens": 159 }, "us.anthropic.claude-sonnet-4-5-20250929-v1:0": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, - "input_cost_per_token_above_200k_tokens": 6e-06, - "output_cost_per_token_above_200k_tokens": 2.25e-05, - "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, - "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 33e-07, + "input_cost_per_token": 33e-06, + "input_cost_per_token_above_200k_tokens": 66e-06, + "output_cost_per_token_above_200k_tokens": 2.475e-05, + "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, + "cache_read_input_token_cost_above_200k_tokens": 66e-07, "litellm_provider": "bedrock_converse", "max_input_tokens": 200000, "max_output_tokens": 64000, "max_tokens": 200000, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.65e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, From ba0dcfc001587f823dd84e38a2bf54500ac5e2f6 Mon Sep 17 00:00:00 2001 From: Yuta Saito Date: Sun, 5 Oct 2025 09:25:39 +0900 Subject: [PATCH 2/2] feat: add Global Cross-Region Sonnet 4 --- ...odel_prices_and_context_window_backup.json | 30 +++++++++++++++++++ model_prices_and_context_window.json | 30 +++++++++++++++++++ 2 files changed, 60 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 72ff60883b0..4328149b655 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -11850,6 +11850,36 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, + "global.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-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": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "gpt-3.5-turbo": { "input_cost_per_token": 0.5e-06, "litellm_provider": "openai", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 72ff60883b0..4328149b655 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -11850,6 +11850,36 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, + "global.anthropic.claude-sonnet-4-20250514-v1:0": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 1000000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 1.5e-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": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "gpt-3.5-turbo": { "input_cost_per_token": 0.5e-06, "litellm_provider": "openai",