feat: add MiniMax as new LLM provider

Add support for MiniMax M2.5 series models via OpenAI-compatible API:
- Add minimax_fn() to Provider class with configurable base URL
- Support both international and China mainland endpoints
- Update documentation in README.md and README_CHS.md
- Add MINIMAX_API_KEY and MINIMAX_BASE_URL to .env.example
- Add unit tests for MiniMax provider

Made-with: Cursor
This commit is contained in:
ximi
2026-03-06 17:10:52 +08:00
parent 781275c881
commit fc268ed087
6 changed files with 2065 additions and 1589 deletions
+1
View File
@@ -230,6 +230,7 @@ provider_server_address = # 当 is_local = False 时,对于大多数 API 通
| Hugging Face | `huggingface` | 否 | 使用 Hugging Face Inference API 中的模型。 | [huggingface.co/settings/tokens](https://huggingface.co/settings/tokens) |
| TogetherAI | `togetherAI` | 否 | 通过 TogetherAI API 使用各种开源模型。| [api.together.ai/settings/api-keys](https://api.together.ai/settings/api-keys) |
| OpenRouter | `openrouter` | No | 通过 OpenRouter 使用各种开源模型| [https://openrouter.ai/](https://openrouter.ai/) |
| MiniMax | `minimax` | 否 | 使用 MiniMax 的 M2.5 系列模型(如 MiniMax-M2.5)。 | [platform.minimax.io](https://platform.minimax.io/user-center/basic-information) |
*注意:*
* 我们不建议将 `gpt-4o` 或其他 OpenAI 模型用于复杂的网页浏览和任务规划,因为当前的提示优化针对 Deepseek 等模型。