MiniMax-M3
#25 of 31 text models on overall (provisional). $0.93 per 1,000 support replies at list price.
List price, not verified yet- Released
- 1 Jun 2026
- Context window
- 1M tokens
- Longest reply
- 524K tokens
- Open weights
- Yes
- Reasoning mode
- Yes
- Tool use
- Yes
- Reads
- text, image, video
- Writes
- text
- Knowledge cutoff
- –
Overall31
Writing46
Support49
Coding45
Value32
Provisional, 0 to 100 among the text models we track, from Arena and Epoch AI. How we score.Prices and where to run it
| Provider | Region | Input per 1M | Output per 1M | Cached input | Data retention | Checked |
|---|---|---|---|---|---|---|
| minimax | global | $0.30 | $1.20 | $0.06 | Not checked | List price, unverified |
Price history and a CSV download arrive with the open price dataset.
Benchmarks behind the scores
| Measure | Figure | Run date | Source |
|---|---|---|---|
| Epoch Capabilities Index | 146.9 | 25 Oct 2026 | Epoch AI |
| Arena text, coding | 1470 | 22 Oct 2026 | Arena |
| Arena text, creative writing | 1402.7 | 22 Oct 2026 | Arena |
| Arena text, instruction following | 1432.2 | 22 Oct 2026 | Arena |
| Arena text, multi-turn | 1442.7 | 22 Oct 2026 | Arena |
| Arena text, overall | 1431.7 | 22 Oct 2026 | Arena |
| Arena WebDev | 1482.3 | 23 Oct 2026 | Arena |
Call it through OpenRouter
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "minimax/minimax-m3", "messages": [{"role": "user", "content": "Hello"}]}'Not listed on OpenRouter; use the vendor’s own API.