From 834f187f4c9ea34be582b2e7315b93665124d9c0 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 14 Sep 2026 19:20:36 +0000 Subject: [PATCH] feat(models): add Together, Fireworks, Nebius, Cohere, Bedrock models and Inception cache pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 88 +++++++++++++++++++ model_prices_and_context_window.json | 88 +++++++++++++++++++ 2 files changed, 176 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 89d582db151..0954f9360fa 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", @@ -14650,6 +14661,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -34159,6 +34185,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34168,6 +34195,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -37333,6 +37361,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -37599,6 +37636,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -44017,6 +44065,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -61060,6 +61122,32 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 89d582db151..0954f9360fa 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", @@ -14650,6 +14661,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -34159,6 +34185,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34168,6 +34195,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -37333,6 +37361,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -37599,6 +37636,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -44017,6 +44065,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -61060,6 +61122,32 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07,