From 876c936fa6eaf7d8c7bc19b414e122408112699b Mon Sep 17 00:00:00 2001 From: Octopus Date: Wed, 18 Mar 2026 05:11:23 -0500 Subject: [PATCH] feat: upgrade MiniMax default model to M2.7 - Add MiniMax-M2.7 and MiniMax-M2.7-lightning to model list - Set MiniMax-M2.7 as default model - Keep all previous models as alternatives - Update provider documentation with new model entries --- docs/my-website/docs/providers/minimax.md | 6 +++- litellm/llms/minimax/chat/transformation.py | 4 +++ ...odel_prices_and_context_window_backup.json | 30 +++++++++++++++++++ model_prices_and_context_window.json | 30 +++++++++++++++++++ 4 files changed, 69 insertions(+), 1 deletion(-) diff --git a/docs/my-website/docs/providers/minimax.md b/docs/my-website/docs/providers/minimax.md index 9505c26aade..a85320d80fa 100644 --- a/docs/my-website/docs/providers/minimax.md +++ b/docs/my-website/docs/providers/minimax.md @@ -11,10 +11,14 @@ Litellm provides anthropic specs compatible support for minmax ## Supported Models -MiniMax offers three models through their Anthropic-compatible API: +MiniMax offers the following models through their Anthropic-compatible API: | Model | Description | Input Cost | Output Cost | Prompt Caching Read | Prompt Caching Write | |-------|-------------|------------|-------------|---------------------|----------------------| +| **MiniMax-M2.7** | Latest flagship model with enhanced reasoning and coding | $0.3/M tokens | $1.2/M tokens | $0.03/M tokens | $0.375/M tokens | +| **MiniMax-M2.7-lightning** | High-speed version of M2.7 for low-latency scenarios | $0.3/M tokens | $2.4/M tokens | $0.03/M tokens | $0.375/M tokens | +| **MiniMax-M2.5** | Advanced reasoning, Agentic capabilities | $0.3/M tokens | $1.2/M tokens | $0.03/M tokens | $0.375/M tokens | +| **MiniMax-M2.5-lightning** | High-speed version of M2.5 | $0.3/M tokens | $2.4/M tokens | $0.03/M tokens | $0.375/M tokens | | **MiniMax-M2.1** | Powerful Multi-Language Programming with Enhanced Programming Experience (~60 tps) | $0.3/M tokens | $1.2/M tokens | $0.03/M tokens | $0.375/M tokens | | **MiniMax-M2.1-lightning** | Faster and More Agile (~100 tps) | $0.3/M tokens | $2.4/M tokens | $0.03/M tokens | $0.375/M tokens | | **MiniMax-M2** | Agentic capabilities, Advanced reasoning | $0.3/M tokens | $1.2/M tokens | $0.03/M tokens | $0.375/M tokens | diff --git a/litellm/llms/minimax/chat/transformation.py b/litellm/llms/minimax/chat/transformation.py index 4095e57a8ae..270ab31ff67 100644 --- a/litellm/llms/minimax/chat/transformation.py +++ b/litellm/llms/minimax/chat/transformation.py @@ -17,6 +17,10 @@ class MinimaxChatConfig(OpenAIGPTConfig): - China: https://api.minimaxi.com/v1 Supported models: + - MiniMax-M2.7 + - MiniMax-M2.7-lightning + - MiniMax-M2.5 + - MiniMax-M2.5-lightning - MiniMax-M2.1 - MiniMax-M2.1-lightning - MiniMax-M2 diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 6786fc33595..44c45dc244b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -21142,6 +21142,36 @@ "max_input_tokens": 1000000, "max_output_tokens": 8192 }, + "minimax/MiniMax-M2.7": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2.7-lightning": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, "minimax/MiniMax-M2.5": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6786fc33595..44c45dc244b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -21142,6 +21142,36 @@ "max_input_tokens": 1000000, "max_output_tokens": 8192 }, + "minimax/MiniMax-M2.7": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 1.2e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, + "minimax/MiniMax-M2.7-lightning": { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07, + "litellm_provider": "minimax", + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_system_messages": true, + "max_input_tokens": 1000000, + "max_output_tokens": 8192 + }, "minimax/MiniMax-M2.5": { "input_cost_per_token": 3e-07, "output_cost_per_token": 1.2e-06,