Free MiniMax-M2.5-highspeed API.
https://api-inference.modelscope.cn/v1 MiniMax/MiniMax-M2.5 MiniMax-M2.5-highspeed is listed for chat workloads and supports a 205K context window.
Check ModelScope's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We found 2 provider listings for minimax. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | MiniMax-M2.5-highspeed | Check provider | 205K | OpenAI-style | See provider page |
| | minimaxai/minimax-m3 | Free tier | 1.0M | OpenAI-style | Up to 40 RPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| minimaxai/minimax-m3 | NVIDIA NIM | 1.0M | Free tier |
| Qwen/Qwen3.5-35B-A3B | ModelScope | 131K | Check provider |
| Qwen/Qwen3.5-27B | ModelScope | 131K | Check provider |
| Kimi K2.5 | ModelScope | 262K | Check provider |
| Qwen/Qwen-Image | ModelScope | 131K | Check provider |
MiniMax-M2.5-highspeed is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
MiniMax-M2.5-highspeed appears in the free model catalog for ModelScope, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is MiniMax/MiniMax-M2.5.
The listed context window is 205K tokens with up to 131K output tokens.
Free MiniMax-M2.5-highspeed API.
For API keys, setup steps, and provider-level limits, see the ModelScope provider page.