MiniMax M2.5: 229B MoE model trained on hundreds of thousands of real environments, scoring 80.2% on SWE-Bench Verified and 76.3% on BrowseComp
Available on
Privacy
- ZDR
- Training
- No
- Region
- EU + US
Voidleap Code is a desktop agentic IDE from Voidleap that runs on your own machine, with every agent, skill, hook, and security rule left editable. You can change model in the middle of a thread, planning on one, implementing on another, and reviewing on a third without starting over, then read back the tokens, cost, latency, and cache hit rate for each. Opper ships inside the app as a provider rather than a base URL override, so you add your key once in settings and pick Opper models per turn.
In Voidleap Code, go to Settings → Providers → Add Provider, choose Opper, and paste your API key. Then pick MiniMax M2.5.
MiniMax M2.5 runs on the routes below. Route only to EU providers when your data has to stay in Europe.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| GreenPT | EU | No | $0.38 | $1.50 | |
| TensorX | EU | No | $0.30 | $1.20 | |
| DigitalOcean | US | No | $0.30 | $1.20 | |
| Novita | US | No | $0.30 | $1.20 |
MiniMax M2.5: 229B MoE model trained on hundreds of thousands of real environments, scoring 80.2% on SWE-Bench Verified and 76.3% on BrowseComp
Anthropic's terminal coding agent. Run it on any model on Opper, not just Claude.
opper launch claudeOpenAI's open-source coding CLI. Run it on any model on Opper.
opper launch codexDeepSeek's open-source coding agent. Add Opper as a custom provider to run it on any model, not just DeepSeek's.
OpenAI-compatible