Should you use MiniMax: MiniMax M2.5?
MiniMax: MiniMax M2.5 is listed for chat workloads and supports a 205K context window.
Use the comparison and availability sections before choosing this listing, because it is not currently marked as free.
https://openrouter.ai/api/v1 minimax/minimax-m2.5 MiniMax: MiniMax M2.5 is listed for chat workloads and supports a 205K context window.
Use the comparison and availability sections before choosing this listing, because it is not currently marked as free.
We found 3 provider listings for minimax. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | MiniMax: MiniMax M2.5 | Paid | 205K | OpenAI-style | 200 req/day (free tier) |
| Gonka Broker | MiniMaxAI/MiniMax-M2.7 | Free tier | 200K | Native | ~1M tokens/month (shared, varies by model) |
| | minimaxai/minimax-m3.1-flash | Free tier | 1.0M | OpenAI-style | Up to 40 RPM |
| Model | Provider | Context | Access |
|---|---|---|---|
| MiniMaxAI/MiniMax-M2.7 | Gonka Broker | 200K | Free tier |
| minimaxai/minimax-m3.1-flash | NVIDIA NIM | 1.0M | Free tier |
| Recursive: Flint (free) | OpenRouter | 262K | Free tier |
| XingChen: Xing4.0 29B A4B (free) | OpenRouter | 262K | Free tier |
| NVIDIA: Nemotron 3.5 Super VL (free) | OpenRouter | 1.0M | Free tier |
MiniMax: MiniMax M2.5 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
MiniMax: MiniMax M2.5 is not currently marked as free on OpenRouter.
The model ID shown in this catalog is minimax/minimax-m2.5.
The listed free tier limit is 200 req/day (free tier). Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 205K tokens with up to 131K output tokens.
MiniMax M2.5 is a SOTA large language model designed for real-world productivity, available free on OpenRouter. It builds on M2.1's coding strengths and extends into general office tasks — handling Word, Excel, and PowerPoint files, switching between software environments, and working across teams. Achieved 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp. 197K context window. Text-only. OpenAI-compatible via OpenRouter. Free tier: 200 RPD.
For API keys, setup steps, and provider-level limits, see the OpenRouter provider page.