MiniMax M2.7 High Speed vs MiniMax M3
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | MiniMax M2.7 High Speedminimax/minimax-m2.7-highspeed | MiniMax M3minimax/minimax-m3 |
|---|---|---|
| Maker | minimax | minimax |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.63 | $0.315 Lower |
| Cached input per 1M tokens | $0.063 | $0.063 |
| Cache write per 1M tokens | $0.39375 | Same as input |
| Output per 1M tokens | $2.52 | $1.26 Lower |
| Context window | 204,800 tokens | 512,000 tokens Larger |
| Max output | 131,100 tokens | 512,000 tokens Larger |
| Capabilities | Reasoning, tool use | Reasoning, tool use, vision, file input |
| Takes | Text | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Not on every provider | Not on every provider |
| No training on requests | Not on every provider | Not on every provider |
| Released | 2026-03-18 | 2026-05-31 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | MiniMax M2.7 High Speed | MiniMax M3 |
|---|---|---|
| 1,000 tokens in, 200 out | $0.001134 | $0.000567 |
| 10,000 tokens in, 1,000 out | $0.00882 | $0.00441 |
| 100,000 tokens in, 4,000 out | $0.07308 | $0.03654 |