From 7bcc46246bb977aa206f23860b6aefc0d0101e23 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 10 Nov 2026 13:31:56 +0000 Subject: [PATCH] feat(cost-map): rolling registry update (claude-mythos-5-2, Azure Mythos 5.2, Friendli GLM-5.1 date, GovCloud Fable 5.2 token counting) (#50777) * fix(cost-map): drop unsupported Mantle token_count_model from the Bedrock GovCloud Claude Fable 5.2 row * feat(cost-map): add claude-mythos-5-2, absorb Azure Mythos 5.2 rows and Friendli GLM-5.1 deprecation Co-authored-by: Lee-Si-Yoon <76679207+Lee-Si-Yoon@users.noreply.github.com> Co-authored-by: Emerson Gomes Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: Lee-Si-Yoon <76679207+Lee-Si-Yoon@users.noreply.github.com> Co-authored-by: Emerson Gomes --- ...odel_prices_and_context_window_backup.json | 163 +++++++++++++++--- model_prices_and_context_window.json | 163 +++++++++++++++--- ...azure_ai_foundry_catalog_model_metadata.py | 5 + 3 files changed, 283 insertions(+), 48 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 37a5c5a2437..1bf985cd134 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -29393,7 +29393,8 @@ "supports_video_input": false, "mode": "chat", "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", - "source": "https://api.friendli.ai/serverless/v1/models" + "source": "https://api.friendli.ai/serverless/v1/models", + "deprecation_date": "2026-11-20" }, "ft:babbage-002": { "deprecation_date": "2026-09-28", @@ -65004,6 +65005,53 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-mythos-5-2": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 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, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "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_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2, + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_fast_mode": true, + "supports_speed": true + }, "claude-mythos-preview": { "deprecation_date": "2026-06-09", "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", @@ -70011,6 +70059,7 @@ } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, @@ -70020,13 +70069,19 @@ "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "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, @@ -70035,18 +70090,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_bedrock_native_structured_output": false, - "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": 512, - "token_count_model": { - "model": "anthropic.claude-fable-5-2", - "litellm_provider": "bedrock_mantle", - "region": "us-gov-west-1" - } + "thinking_always_on": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -70357,6 +70401,7 @@ "prompt_cache_min_tokens": 512 }, "bedrock/us-gov-east-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, @@ -70366,13 +70411,19 @@ "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "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, @@ -70381,13 +70432,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_bedrock_native_structured_output": false, - "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": 512 + "thinking_always_on": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { "litellm_provider": "bedrock_mantle", @@ -87967,6 +88012,76 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, + "azure_ai/claude-mythos-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": 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, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": 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, + "thinking_always_on": true + }, "azure_ai/claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 37a5c5a2437..1bf985cd134 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -29393,7 +29393,8 @@ "supports_video_input": false, "mode": "chat", "comment": "Strong GLM coding model for agentic engineering, terminals, and repository generation", - "source": "https://api.friendli.ai/serverless/v1/models" + "source": "https://api.friendli.ai/serverless/v1/models", + "deprecation_date": "2026-11-20" }, "ft:babbage-002": { "deprecation_date": "2026-09-28", @@ -65004,6 +65005,53 @@ "supports_native_structured_output": true, "source": "https://platform.claude.com/docs/en/about-claude/pricing" }, + "claude-mythos-5-2": { + "supports_anthropic_compaction": true, + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_creation_input_token_cost_batches": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_batches": 1e-07, + "input_cost_per_token": 8e-06, + "input_cost_per_token_batches": 4e-06, + "litellm_provider": "anthropic", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "output_cost_per_token_batches": 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, + "thinking_always_on": true, + "supports_mid_conversation_system": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "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_max_reasoning_effort": true, + "provider_specific_entry": { + "fast": 2, + "us": 1.1 + }, + "supports_output_config": true, + "prompt_cache_min_tokens": 512, + "supports_native_structured_output": true, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_fast_mode": true, + "supports_speed": true + }, "claude-mythos-preview": { "deprecation_date": "2026-06-09", "deprecation_source": "https://platform.claude.com/docs/en/about-claude/model-deprecations", @@ -70011,6 +70059,7 @@ } }, "bedrock/us-gov-west-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, @@ -70020,13 +70069,19 @@ "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "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, @@ -70035,18 +70090,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_bedrock_native_structured_output": false, - "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": 512, - "token_count_model": { - "model": "anthropic.claude-fable-5-2", - "litellm_provider": "bedrock_mantle", - "region": "us-gov-west-1" - } + "thinking_always_on": true }, "bedrock/us-gov-east-1/nvidia.nemotron-nano-3-30b": { "input_cost_per_token": 7.2e-08, @@ -70357,6 +70401,7 @@ "prompt_cache_min_tokens": 512 }, "bedrock/us-gov-east-1/anthropic.claude-fable-5-2": { + "bedrock_output_config_effort_ceiling": "xhigh", "cache_creation_input_token_cost": 1.2e-05, "cache_creation_input_token_cost_above_1hr": 1.92e-05, "cache_read_input_token_cost": 2.4e-07, @@ -70366,13 +70411,19 @@ "max_output_tokens": 128000, "mode": "chat", "output_cost_per_token": 4.8e-05, + "prompt_cache_min_tokens": 512.0, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrockFoundationModels/current/index.json", "supports_adaptive_thinking": true, - "thinking_always_on": true, - "supports_mid_conversation_system": true, "supports_assistant_prefill": false, + "supports_bedrock_native_structured_output": false, "supports_computer_use": true, "supports_forced_tool_use": false, "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, @@ -70381,13 +70432,7 @@ "supports_tool_choice": true, "supports_vision": true, "supports_xhigh_reasoning_effort": true, - "supports_native_structured_output": false, - "supports_bedrock_native_structured_output": false, - "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": 512 + "thinking_always_on": true }, "bedrock_mantle/us-gov-west-1/openai.gpt-5.6-terra": { "litellm_provider": "bedrock_mantle", @@ -87967,6 +88012,76 @@ "supports_xhigh_reasoning_effort": true, "thinking_always_on": true }, + "azure_ai/claude-mythos-5-2": { + "cache_creation_input_token_cost": 1e-05, + "cache_creation_input_token_cost_above_1hr": 1.6e-05, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 8e-06, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": 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, + "thinking_always_on": true + }, + "azure_ai/claude-mythos-5-2-fast": { + "cache_creation_input_token_cost": 2e-05, + "cache_creation_input_token_cost_above_1hr": 3.2e-05, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_token": 1.6e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 8e-05, + "prompt_cache_min_tokens": 512.0, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://platform.claude.com/docs/en/about-claude/pricing", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_computer_use": true, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_mid_conversation_system": true, + "supports_native_structured_output": 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, + "thinking_always_on": true + }, "azure_ai/claude-fable-5-2": { "cache_creation_input_token_cost": 1e-05, "cache_creation_input_token_cost_above_1hr": 1.6e-05, diff --git a/tests/unit/llms/azure_ai/test_azure_ai_foundry_catalog_model_metadata.py b/tests/unit/llms/azure_ai/test_azure_ai_foundry_catalog_model_metadata.py index a5b66efe7cd..404b3240399 100644 --- a/tests/unit/llms/azure_ai/test_azure_ai_foundry_catalog_model_metadata.py +++ b/tests/unit/llms/azure_ai/test_azure_ai_foundry_catalog_model_metadata.py @@ -23,6 +23,11 @@ TOKEN_PRICED_NAMES: Final = ( "grok-4-20-reasoning", "grok-4-20-non-reasoning", "claude-mythos-5-1", + "claude-mythos-5-2", + "claude-mythos-5-2-fast", + "claude-fable-5-2", + "claude-fable-5-2-fast", + "claude-opus-5-5-fast", ) GROK_4_20_NAMES: Final = ("grok-4-20-reasoning", "grok-4-20-non-reasoning") CATALOG_NAMES: Final = TOKEN_PRICED_NAMES + ("whisper",)