MiniMax: MiniMax M3
MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agentic work, coding,...
Everything else
| Max output | 512K |
|---|---|
| Input / 1M | $0.3 |
| Output / 1M | $1.20 |
| Cache read / 1M | $0.06 |
| Cache write / 1M | — |
| 1M in + 1M out | $1.50 |
| Takes | text, image, video |
| Returns | text |
| Tools | yes |
| Reasoning | optional |
| Open weights | yes |
| Released | 2026-05-31 |
| Knowledge cutoff | — |
| Retires | — |
| Catalog id | minimax/minimax-m3 |
Benchmarks
| source | epoch |
|---|---|
| eci | 147.01 |
| confidence | Confident |
| accessibility | API access |
Benchmark scores by Epoch AI, CC BY 4.0.
Using it
In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.