From af7b0af52fa1383ceb5804b6c92a8e724b52947c Mon Sep 17 00:00:00 2001 From: bhumikadangayach <139267865+bhumikadangayach@users.noreply.github.com> Date: Wed, 24 Jun 2026 16:57:41 +0530 Subject: [PATCH] fix(sambanova): update pricing, deprecate retired models, and add missing models (#30016) * feat(bedrock): add amazon.titan-embed-g1-text-02 embedding model support - Add model to provider routing allowlist in embedding.py - Add request transformation using AmazonTitanG1Config - Add response transformation using AmazonTitanG1Config - Add pricing metadata to model_prices_and_context_window.json - Add unit tests for embedding and model info Fixes missing cost tracking reported in #29786 Related to VANDRANKI/litellm PR #29790 * style: fix syntax error, trailing whitespace and missing newline * style: apply black formatting to embedding.py * style: apply black formatting to test_bedrock_embedding.py * fix(sambanova): update pricing, fix context windows, add deprecation dates, and add missing models * fix(sambanova): sync model_prices_and_context_window_backup.json with primary * fix(sambanova): fix indentation on Meta-Llama-3.2-1B-Instruct deprecation_date * fix(bedrock): add amazon.titan-embed-g1-text-02 to unmapped model error message * style: apply black formatting to embedding.py * fix(sambanova): correct indentation on DeepSeek-V3.2 entry * fix(sambanova): replace gemma-3-12b-it with gemma-4-31B-it (verified pricing) --- litellm/llms/bedrock/embed/embedding.py | 10 + ...odel_prices_and_context_window_backup.json | 987 +++++++++++++----- model_prices_and_context_window.json | 57 +- .../llm_translation/test_bedrock_embedding.py | 15 + 4 files changed, 819 insertions(+), 250 deletions(-) diff --git a/litellm/llms/bedrock/embed/embedding.py b/litellm/llms/bedrock/embed/embedding.py index b6aa99842d7..98c2d87bfdb 100644 --- a/litellm/llms/bedrock/embed/embedding.py +++ b/litellm/llms/bedrock/embed/embedding.py @@ -224,6 +224,10 @@ class BedrockEmbedding(BaseAWSLLM): returned_response = AmazonTitanV2Config()._transform_response( response_list=response_list, model=model ) + elif model == "amazon.titan-embed-g1-text-02": + returned_response = AmazonTitanG1Config()._transform_response( + response_list=response_list, model=model + ) elif provider == "twelvelabs": returned_response = ( TwelveLabsMarengoEmbeddingConfig()._transform_response( @@ -447,6 +451,7 @@ class BedrockEmbedding(BaseAWSLLM): "amazon.titan-embed-image-v1", "amazon.titan-embed-text-v1", "amazon.titan-embed-text-v2:0", + "amazon.titan-embed-g1-text-02", ]: batch_data = [] for i in input: @@ -464,6 +469,10 @@ class BedrockEmbedding(BaseAWSLLM): transformed_request = AmazonTitanV2Config()._transform_request( input=i, inference_params=inference_params ) + elif model == "amazon.titan-embed-g1-text-02": + transformed_request = AmazonTitanG1Config()._transform_request( + input=i, inference_params=inference_params + ) else: raise Exception( "Unmapped model. Received={}. Expected={}".format( @@ -472,6 +481,7 @@ class BedrockEmbedding(BaseAWSLLM): "amazon.titan-embed-image-v1", "amazon.titan-embed-text-v1", "amazon.titan-embed-text-v2:0", + "amazon.titan-embed-g1-text-02", ], ) ) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6ebac7efc8d..452a33be695 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -570,6 +570,15 @@ "output_cost_per_token": 0.0, "output_vector_size": 1536 }, + "amazon.titan-embed-g1-text-02": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, "amazon.titan-embed-text-v2:0": { "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", @@ -14143,6 +14152,14 @@ "notes": "APISerpent deep search (/api/search), multi-engine (Google, Bing, Yahoo, DuckDuckGo). Pricing: $0.60/1k searches." } }, + "tinyfish/search": { + "input_cost_per_query": 0.0, + "litellm_provider": "tinyfish", + "mode": "search", + "metadata": { + "notes": "TinyFish Search API" + } + }, "elevenlabs/scribe_v1": { "input_cost_per_second": 6.11e-05, "litellm_provider": "elevenlabs", @@ -31357,13 +31374,13 @@ "output_cost_per_token": 0.0 }, "sambanova/MiniMax-M2.7": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -31380,6 +31397,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2026-03-20", "input_cost_per_token": 7e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, @@ -31390,6 +31408,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3-0324": { + "deprecation_date": "2026-04-14", "input_cost_per_token": 3e-06, "litellm_provider": "sambanova", "max_input_tokens": 32768, @@ -31420,6 +31439,7 @@ "supports_vision": true }, "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2025-06-19", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -31436,6 +31456,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-405B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31449,6 +31470,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-8B-Instruct": { + "deprecation_date": "2026-04-14", "input_cost_per_token": 1e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31462,6 +31484,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.2-1B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 4e-08, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31472,6 +31495,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Meta-Llama-3.2-3B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 8e-08, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -31495,6 +31519,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-Guard-3-8B": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 3e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31505,6 +31530,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/QwQ-32B": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31515,6 +31541,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Qwen2-Audio-7B-Instruct": { + "deprecation_date": "2025-06-19", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -31526,6 +31553,7 @@ "supports_audio_input": true }, "sambanova/Qwen3-32B": { + "deprecation_date": "2026-04-06", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -31539,9 +31567,9 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 3e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "sambanova", @@ -31555,8 +31583,8 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, - "input_cost_per_token": 3e-06, - "output_cost_per_token": 4.5e-06, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 5.9e-07, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, @@ -31564,21 +31592,55 @@ "supports_reasoning": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, - "snowflake/claude-3-5-sonnet": { - "litellm_provider": "snowflake", - "max_input_tokens": 18000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat", - "supports_computer_use": true - }, - "snowflake/deepseek-r1": { - "litellm_provider": "snowflake", + "sambanova/DeepSeek-V3.2": { + "max_tokens": 32768, "max_input_tokens": 32768, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 32768, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 4.5e-06, + "litellm_provider": "sambanova", "mode": "chat", - "supports_reasoning": true + "supports_function_calling": true, + "supports_tool_choice": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/gemma-4-31B-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.15e-06, + "litellm_provider": "sambanova", + "mode": "chat", + "supports_vision": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "snowflake/claude-3-5-sonnet": { + "litellm_provider": "snowflake", + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/deepseek-r1": { + "litellm_provider": "snowflake", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.00000135, + "output_cost_per_token": 0.0000054, + "supports_reasoning": true, + "supports_system_messages": true }, "snowflake/gemma-7b": { "litellm_provider": "snowflake", @@ -31632,23 +31694,34 @@ "snowflake/llama3.1-405b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.0000012, + "output_cost_per_token": 0.0000012, + "supports_function_calling": true, + "supports_system_messages": true }, "snowflake/llama3.1-70b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, + "supports_function_calling": true, + "supports_system_messages": true }, "snowflake/llama3.1-8b": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.00000024, + "output_cost_per_token": 0.00000024, + "supports_system_messages": true }, "snowflake/llama3.2-1b": { "litellm_provider": "snowflake", @@ -31664,13 +31737,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/llama3.3-70b": { - "litellm_provider": "snowflake", + "snowflake/llama3.3-70b": { + "max_tokens": 16384, "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, "snowflake/mistral-7b": { "litellm_provider": "snowflake", "max_input_tokens": 32000, @@ -31685,12 +31762,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/mistral-large2": { + "snowflake/mistral-large2": { "litellm_provider": "snowflake", "max_input_tokens": 128000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000006, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true }, "snowflake/mixtral-8x7b": { "litellm_provider": "snowflake", @@ -31727,13 +31809,17 @@ "max_tokens": 8192, "mode": "chat" }, - "snowflake/snowflake-llama-3.3-70b": { + "snowflake/snowflake-llama-3.3-70b": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000072, + "output_cost_per_token": 0.00000072, "litellm_provider": "snowflake", - "max_input_tokens": 8000, - "max_output_tokens": 8192, - "max_tokens": 8192, - "mode": "chat" - }, + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, "stability/sd3": { "litellm_provider": "stability", "mode": "image_generation", @@ -32076,6 +32162,11 @@ "litellm_provider": "tavily", "mode": "search" }, + "you_com/search": { + "input_cost_per_query": 0.0, + "litellm_provider": "you_com", + "mode": "search" + }, "text-completion-codestral/codestral-2405": { "input_cost_per_token": 0.0, "litellm_provider": "text-completion-codestral", @@ -36595,17 +36686,7 @@ "max_input_tokens": 32000, "max_tokens": 32000, "mode": "embedding", - "output_cost_per_token": 0.0, - "supports_vision": true - }, - "voyage/voyage-multimodal-3.5": { - "input_cost_per_token": 1.2e-07, - "litellm_provider": "voyage", - "max_input_tokens": 32000, - "max_tokens": 32000, - "mode": "embedding", - "output_cost_per_token": 0.0, - "supports_vision": true + "output_cost_per_token": 0.0 }, "wandb/openai/gpt-oss-120b": { "max_tokens": 131072, @@ -40270,6 +40351,178 @@ "supports_tool_choice": true, "supports_vision": true }, + "scaleway/qwen/qwen3.5-397b-a17b": { + "input_cost_per_token": 6e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scaleway/qwen/qwen3.6-35b-a3b": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "supports_function_calling": true, + "supports_vision": true, + "supports_reasoning": true + }, + "scaleway/qwen/qwen3-235b-a22b-instruct-2507": { + "input_cost_per_token": 7.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2.25e-06, + "supports_function_calling": true + }, + "scaleway/qwen/qwen3-embedding-8b": { + "input_cost_per_token": 1e-07, + "litellm_provider": "scaleway", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "scaleway/qwen/qwen3-coder-30b-a3b-instruct": { + "input_cost_per_token": 2e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 8e-07, + "supports_function_calling": true + }, + "scaleway/openai/gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6e-07, + "supports_function_calling": true + }, + "scaleway/openai/whisper-large-v3": { + "input_cost_per_audio_token": 0.0, + "litellm_provider": "scaleway", + "mode": "audio_transcription", + "output_cost_per_token": 0.0 + }, + "scaleway/google/gemma-4-26b-a4b-it": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_vision": true + }, + "scaleway/google/gemma-3-27b-it": { + "input_cost_per_token": 2.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 40000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 5e-07, + "supports_function_calling": true, + "supports_vision": true + }, + "scaleway/hcompany/holo2-30b-a3b": { + "input_cost_per_token": 3e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 22000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7e-07, + "supports_reasoning": true, + "supports_vision": true + }, + "scaleway/mistralai/mistral-medium-3.5-128b": { + "input_cost_per_token": 1.5e-06, + "litellm_provider": "scaleway", + "max_input_tokens": 256000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 7.5e-06, + "supports_reasoning": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_tool_choice": true + }, + "scaleway/mistralai/devstral-2-123b-instruct-2512": { + "input_cost_per_token": 4e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true + }, + "scaleway/mistralai/voxtral-small-24b-2507": { + "input_cost_per_audio_token": 1.5e-07, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 32000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_audio_input": true + }, + "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 128000, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 3.5e-07, + "supports_function_calling": true, + "supports_vision": true + }, + "scaleway/mistralai/pixtral-12b-2409": { + "input_cost_per_token": 2e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 2e-07, + "supports_vision": true, + "supports_function_calling": true + }, + "scaleway/BAAI/bge-multilingual-gemma2": { + "input_cost_per_token": 1e-07, + "litellm_provider": "scaleway", + "mode": "embedding", + "output_cost_per_token": 0.0 + }, + "scaleway/meta/llama-3.3-70b-instruct": { + "input_cost_per_token": 9e-07, + "litellm_provider": "scaleway", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 9e-07, + "supports_function_calling": true + }, "novita/deepseek/deepseek-v3.2": { "litellm_provider": "novita", "mode": "chat", @@ -43051,192 +43304,362 @@ "supports_native_structured_output": true, "supports_pdf_input": true }, - "soniox/stt-async-v4": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "supports_audio_input": true - }, - "soniox/stt-async-v5": { - "litellm_provider": "soniox", - "max_output_tokens": 8000, - "max_tokens": 8000, - "input_cost_per_second": 0.0, - "output_cost_per_second": 0.0000277778, - "mode": "audio_transcription", - "source": "https://soniox.com/pricing", - "supported_endpoints": [ - "/v1/audio/transcriptions" - ], - "supports_audio_input": true - }, - "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 6e-07, - "output_cost_per_token": 3.6e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 4.5e-07, - "output_cost_per_token": 1.8e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/Qwen/Qwen3.6-27B-FP8": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3.2e-07, - "output_cost_per_token": 3.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 262144, - "max_output_tokens": 262144, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 202752, - "max_output_tokens": 202752, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/moonshotai/Kimi-K2.6": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 9.6e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/MiniMaxAI/MiniMax-M2.5": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 3e-07, - "output_cost_per_token": 1.2e-06, - "cache_read_input_token_cost": 0, - "max_input_tokens": 196608, - "max_output_tokens": 196608, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/google/gemma-4-31B-it": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.4e-07, - "output_cost_per_token": 5.6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 32768, - "max_output_tokens": 32768, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-120b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - }, - "tensormesh/openai/gpt-oss-20b": { - "litellm_provider": "tensormesh", - "mode": "chat", - "input_cost_per_token": 7e-08, - "output_cost_per_token": 2.8e-07, - "cache_read_input_token_cost": 0, - "max_input_tokens": 131072, - "max_output_tokens": 131072, - "supports_function_calling": true, - "supports_tool_choice": true, - "supports_response_schema": true, - "supports_prompt_caching": true, - "supports_system_messages": true, - "supports_reasoning": true, - "source": "https://serverless.tensormesh.ai/v1/models/openrouter" - } -, + "snowflake/claude-sonnet-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-sonnet-4-6": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-4-opus": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000005, + "output_cost_per_token": 0.000025, + "cache_read_input_token_cost": 0.0000005, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/claude-haiku-4-5": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000001, + "output_cost_per_token": 0.000005, + "cache_read_input_token_cost": 0.0000001, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/claude-3-7-sonnet": { + "max_tokens": 16384, + "max_input_tokens": 200000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000015, + "cache_read_input_token_cost": 0.0000003, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-4.1": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.000002, + "output_cost_per_token": 0.000008, + "cache_read_input_token_cost": 0.0000005, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5": { + "max_tokens": 16384, + "max_input_tokens": 300000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000125, + "output_cost_per_token": 0.00001, + "cache_read_input_token_cost": 0.000000125, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-mini": { + "max_tokens": 16384, + "max_input_tokens": 1000000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.0000012, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/openai-gpt-5-nano": { + "max_tokens": 16384, + "max_input_tokens": 5000000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000015, + "output_cost_per_token": 0.0000006, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true, + "supports_response_schema": true + }, + "snowflake/llama4-maverick": { + "max_tokens": 16384, + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "input_cost_per_token": 0.00000024, + "output_cost_per_token": 0.00000097, + "litellm_provider": "snowflake", + "mode": "chat", + "supports_function_calling": true, + "supports_system_messages": true + }, + "snowflake/snowflake-arctic-embed-l-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 0.00000007, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "snowflake/snowflake-arctic-embed-m-v2.0": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 0.00000007, + "output_cost_per_token": 0.0, + "litellm_provider": "snowflake", + "mode": "embedding" + }, + "soniox/stt-async-v4": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 0.0000277778, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "supports_audio_input": true + }, + "soniox/stt-async-v5": { + "litellm_provider": "soniox", + "max_output_tokens": 8000, + "max_tokens": 8000, + "input_cost_per_second": 0.0, + "output_cost_per_second": 0.0000277778, + "mode": "audio_transcription", + "source": "https://soniox.com/pricing", + "supported_endpoints": ["/v1/audio/transcriptions"], + "supports_audio_input": true + }, + "tensormesh/Qwen/Qwen3.5-397B-A17B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 6e-07, + "output_cost_per_token": 3.6e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 4.5e-07, + "output_cost_per_token": 1.8e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/Qwen/Qwen3.6-27B-FP8": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 3.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/lukealonso/GLM-5.1-NVFP4-MTP": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 202752, + "max_output_tokens": 202752, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/deepseek-ai/DeepSeek-V4-Flash": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/moonshotai/Kimi-K2.6": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 9.6e-07, + "output_cost_per_token": 4e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/MiniMaxAI/MiniMax-M2.5": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 0, + "max_input_tokens": 196608, + "max_output_tokens": 196608, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/google/gemma-4-31B-it": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.4e-07, + "output_cost_per_token": 5.6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-120b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + }, + "tensormesh/openai/gpt-oss-20b": { + "litellm_provider": "tensormesh", + "mode": "chat", + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2.8e-07, + "cache_read_input_token_cost": 0, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_response_schema": true, + "supports_prompt_caching": true, + "supports_system_messages": true, + "supports_reasoning": true, + "source": "https://serverless.tensormesh.ai/v1/models/openrouter" + } + , "deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, "cache_read_input_token_cost": 2.8e-09, @@ -43370,5 +43793,83 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": false + }, + "pinstripes/ps/glm-4.5-air": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.000000125, + "output_cost_per_token": 0.00000045, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": true, + "source": "https://pinstripes.io/pricing" + }, + "pinstripes/ps/qwen3.6-35b-a3b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.00000014, + "output_cost_per_token": 0.00000045, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": true, + "source": "https://pinstripes.io/pricing" + }, + "pinstripes/ps/qwen3-30b-a3b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.00000009, + "output_cost_per_token": 0.0000002, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": true, + "source": "https://pinstripes.io/pricing" + }, + "pinstripes/ps/qwen3-coder-30b-a3b": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.0000006, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": false, + "source": "https://pinstripes.io/pricing" + }, + "pinstripes/ps/deepseek-v4-flash": { + "max_tokens": 163840, + "max_input_tokens": 163840, + "max_output_tokens": 163840, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.0000002, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": true, + "source": "https://pinstripes.io/pricing" + }, + "pinstripes/ps/minimax-m2.7": { + "max_tokens": 1000192, + "max_input_tokens": 1000192, + "max_output_tokens": 1000192, + "input_cost_per_token": 0.000000255, + "output_cost_per_token": 0.00000055, + "litellm_provider": "pinstripes", + "mode": "chat", + "supports_function_calling": true, + "supports_assistant_prefill": true, + "supports_reasoning": false, + "source": "https://pinstripes.io/pricing" } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d7017a40993..cffb00c6b22 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -570,6 +570,15 @@ "output_cost_per_token": 0.0, "output_vector_size": 1536 }, + "amazon.titan-embed-g1-text-02": { + "input_cost_per_token": 1e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1536 + }, "amazon.titan-embed-text-v2:0": { "input_cost_per_token": 2e-08, "litellm_provider": "bedrock", @@ -31381,13 +31390,13 @@ "output_cost_per_token": 0.0 }, "sambanova/MiniMax-M2.7": { - "input_cost_per_token": 3e-07, + "input_cost_per_token": 6e-07, "litellm_provider": "sambanova", - "max_input_tokens": 204800, + "max_input_tokens": 196608, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 2.4e-06, "source": "https://cloud.sambanova.ai/plans/pricing", "supports_function_calling": true, "supports_reasoning": true, @@ -31404,6 +31413,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2026-03-20", "input_cost_per_token": 7e-07, "litellm_provider": "sambanova", "max_input_tokens": 131072, @@ -31414,6 +31424,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/DeepSeek-V3-0324": { + "deprecation_date": "2026-04-14", "input_cost_per_token": 3e-06, "litellm_provider": "sambanova", "max_input_tokens": 32768, @@ -31444,6 +31455,7 @@ "supports_vision": true }, "sambanova/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2025-06-19", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -31460,6 +31472,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-405B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 5e-06, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31473,6 +31486,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.1-8B-Instruct": { + "deprecation_date": "2026-04-14", "input_cost_per_token": 1e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31486,6 +31500,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-3.2-1B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 4e-08, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31496,6 +31511,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Meta-Llama-3.2-3B-Instruct": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 8e-08, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -31519,6 +31535,7 @@ "supports_tool_choice": true }, "sambanova/Meta-Llama-Guard-3-8B": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 3e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31529,6 +31546,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/QwQ-32B": { + "deprecation_date": "2025-06-25", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 16384, @@ -31539,6 +31557,7 @@ "source": "https://cloud.sambanova.ai/plans/pricing" }, "sambanova/Qwen2-Audio-7B-Instruct": { + "deprecation_date": "2025-06-19", "input_cost_per_token": 5e-07, "litellm_provider": "sambanova", "max_input_tokens": 4096, @@ -31550,6 +31569,7 @@ "supports_audio_input": true }, "sambanova/Qwen3-32B": { + "deprecation_date": "2026-04-06", "input_cost_per_token": 4e-07, "litellm_provider": "sambanova", "max_input_tokens": 8192, @@ -31563,9 +31583,9 @@ "supports_tool_choice": true }, "sambanova/DeepSeek-V3.1": { - "max_tokens": 32768, - "max_input_tokens": 32768, - "max_output_tokens": 32768, + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, "input_cost_per_token": 3e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "sambanova", @@ -31579,13 +31599,36 @@ "max_tokens": 131072, "max_input_tokens": 131072, "max_output_tokens": 131072, + "input_cost_per_token": 2.2e-07, + "output_cost_per_token": 5.9e-07, + "litellm_provider": "sambanova", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/DeepSeek-V3.2": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, "input_cost_per_token": 3e-06, "output_cost_per_token": 4.5e-06, "litellm_provider": "sambanova", "mode": "chat", "supports_function_calling": true, "supports_tool_choice": true, - "supports_reasoning": true, + "source": "https://cloud.sambanova.ai/plans/pricing" + }, + "sambanova/gemma-4-31B-it": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 3.8e-07, + "output_cost_per_token": 1.15e-06, + "litellm_provider": "sambanova", + "mode": "chat", + "supports_vision": true, "source": "https://cloud.sambanova.ai/plans/pricing" }, "snowflake/claude-3-5-sonnet": { diff --git a/tests/llm_translation/test_bedrock_embedding.py b/tests/llm_translation/test_bedrock_embedding.py index 92c22f582d9..2bc4192833b 100644 --- a/tests/llm_translation/test_bedrock_embedding.py +++ b/tests/llm_translation/test_bedrock_embedding.py @@ -34,6 +34,11 @@ img_base_64 = "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAGQAAABkBAMAAACCzIh "text", titan_embedding_response, ), # V2 text model + ( + "bedrock/amazon.titan-embed-g1-text-02", + "text", + titan_embedding_response, + ), # G1 text model ( "bedrock/amazon.titan-embed-image-v1", "image", @@ -459,3 +464,13 @@ def test_bedrock_embedding_region_bug_reproduction(): os.environ["AWS_REGION_NAME"] = original_region_name else: os.environ.pop("AWS_REGION_NAME", None) + + +def test_bedrock_titan_g1_text_02_model_info(): + """Test that amazon.titan-embed-g1-text-02 has correct pricing metadata""" + model_info = litellm.get_model_info("amazon.titan-embed-g1-text-02") + assert model_info is not None, "Model info should not be None" + assert model_info["litellm_provider"] == "bedrock" + assert model_info["mode"] == "embedding" + assert model_info["input_cost_per_token"] == 1e-07 + assert model_info["max_input_tokens"] == 8192