MiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.
Prices for the AI credit you buy. $BINF holders pay up to 8% less.
| Charge | Price | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.12 | $0.11 | per 1M tokens |
| Outputper 1M tokens | $0.48 | $0.44 | per 1M tokens |
| Cached inputper 1M tokens | $0.012 | $0.011 | per 1M tokens |
The price per million tokens, by day.
Unchanged since Oct 22, 2026: $0.12 in and $0.48 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| InferenceNetFp4fp4, answering | 99.4% | 1M |
| InferenceNetFp4fp4, answering | 100% | 1M |
| GMICloudFp8fp8, answering | 100% | 1M |
| DigitalOcean, answering | 100% | 1M |
| NovitaFp16fp16, answering | 99.9% | 1M |
| NebiusFp4fp4, answering | 94.4% | 1M |
| Wafer, answering | 99.7% | 1M |
| ModelRunFp4fp4, answering | 91.3% | 1M |
| ParasailFp8fp8, answering | 98.4% | 1M |
| Together, answering | 100% | 1M |
| Minimax, answering | 100% | 1M |
| SambaNova, answering | 100% | 1M |