200K
text
text
Supported
About this model
MiniMax M2.5 is an open-source MoE model with 230B total parameters (10B active) and a 200K token context window, released February 2026 under a Modified MIT license. SOTA in coding, agentic tool use, search, and office work — scoring 80.2% on SWE-Bench Verified, 51.3% on Multi-SWE-Bench, and 76.3% on BrowseComp. Trained across 200K+ real-world RL environments in 10+ programming languages.Matches Claude Opus 4.6 speed while completing SWE-Bench 37% faster than M2.1.
Input modalities
text
Accepted as model input
Providers
Available routing options for this model through OneInfer.
Pricing
Current OneInfer pricing for this model.
| Usage | Price |
|---|---|
| Input tokens | $0.300 / 1M tokens |
| Output tokens | $1.200 / 1M tokens |
| Cached input tokens | $0.030 / 1M tokens |
Performance & Benchmarks
Independent evaluations and live cluster operational metrics
We haven’t measured this model yet. Published academic results are under Academic Evaluations.
API Guide
- 1
Generate your access token
Use your API key to generate the JWT access token required by the Models API.
- 2
Add the JWT token
Copy the generated JWT token and replace
JWT_TOKENin the example below. - 3
Check your credits
If your balance is too low, before calling the model.
- 4
Run the API example
Choose your preferred language, copy the example, and send your first model request.
curl https://staging-api.oneinfer.ai/v1/ula/chat/completions \ -H "Authorization: Bearer $JWT_TOKEN" \ -H "Content-Type: application/json" \ -d '{ "model": "Minimax/minimax-m2.5", "messages": [ { "role": "user", "content": "Hello!" } ] }'
Community Model Reviews & Ratings
Verified visitor & developer evaluations on MiniMax: MiniMax M2.5's real-world intelligence, code accuracy, and speed
No community reviews yet
Be the first to share developer feedback on MiniMax: MiniMax M2.5's latency, code accuracy, and reliability in production.