Open MiniMax flagship for coding agents, office automation, and complex environments
https://api.sambanova.ai/v1 minimax-m2-7 | Benchmark | Score | Metric | Date |
|---|---|---|---|
| SWE-Bench Verified | 79.9 | resolved | 2026-06-01 |
| SWE-Bench Pro | 56.2 | resolve rate | 2026-06-01 |
| Terminal-Bench | 51.1 | success rate | 2026-06-01 |
MiniMax-M2.7 is listed for chat workloads and supports a 128K context window.
Check SambaNova's current endpoint status before integrating this listing. Use the alternatives table if the provider listing is unavailable.
We found 3 provider listings for minimax-m2-7. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | MiniMax-M2.7 | Check provider | 128K | Native | 20 RPM, 20 RPD, 200K TPD |
| | minimax-m2.7 | Free tier | 180K | OpenAI-style | 10 RPM, 60 req/hr (anonymous) |
| | MiniMax-M2.7 | Free tier | 205K | Native | Varies |
| Model | Provider | Context | Access |
|---|---|---|---|
| minimax-m2.7 | LLM7.io | 180K | Free tier |
| MiniMax-M2.7 | OpenCode Zen | 205K | Free tier |
| DeepSeek-V3.1 | SambaNova | 128K | Check provider |
| DeepSeek-V3.2 (Preview) | SambaNova | 128K | Check provider |
| gemma-4-31B-it (Preview) | SambaNova | 128K | Check provider |
MiniMax-M2.7 is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
MiniMax-M2.7 appears in the free model catalog for SambaNova, but its current endpoint availability should be confirmed with the provider before use.
The model ID shown in this catalog is minimax-m2-7.
The listed free tier limit is 20 RPM, 20 RPD, 200K TPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 192K output tokens.
MiniMax-M2.7 — free model from SambaNova.
For API keys, setup steps, and provider-level limits, see the SambaNova provider page.