MiniMax
MiniMax M3
minimax/minimax-m3
Input
$0.30
per 1M tokens
Output
$1.20
per 1M tokens
Cached input
$0.06
per 1M tokens
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,...
- Released
- Context window
- 1M tokens
- Max output
- 512K tokens
- Input
- text, image, video
- Output
- text
- Reasoning
- Yes
Price history
No price changes since we started tracking on .
Providers on OpenRouter
13 endpoints serve this model. Uptime is OpenRouter's share of successful requests; prices per 1M tokens.
| Provider | Input | Output | Context window | Uptime 30 min | Uptime 24 h |
|---|---|---|---|---|---|
| DeepInfrafp8 · flexdiscount/priority tier | $0.224 | $0.88 | 524K | — | 85.7% |
| CoreWeavefp4 | $0.23 | $0.96 | 262K | 100% | 99.93% |
| GMICloudfp8 | $0.24 | $0.96 | 1M | 100% | 89.9% |
| DeepInfrafp8 | $0.28 | $1.10 | 524K | 100% | 99.51% |
| AtlasCloudfp8 | $0.30 | $1.20 | 524K | 100% | 100% |
| Novitafp8 | $0.30 | $1.20 | 1M | 100% | 100% |
| Together | $0.30 | $1.20 | 524K | 100% | 100% |
| Minimaxvendor's own | $0.30 | $1.20 | 524K | 100% | 99.93% |
| Parasailfp8 | $0.30 | $1.20 | 1M | 100% | 99.23% |
| StreamLakefp8 | $0.30 | $1.20 | 1M | 100% | 99.22% |
| Venicefp8 | $0.30 | $1.20 | 524K | 100% | 97.9% |
| ModelRunfp8 | $0.30 | $1.30 | 1M | 100% | 96.6% |
| Mara | $0.60 | $2.40 | 1M | — | 100% |