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,...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Minimaxfp8 | $0.300 | $1.20 | 524K | 99.8% |
| Novita | $0.300 | $1.20 | 1M | 97.9% |
| Parasailfp8 | $0.300 | $1.20 | 1.0M | 94.1% |
| AtlasCloudfp8 | $0.420 | $1.68 | 524K | 99.8% |
| Morph | $0.600 | $2.40 | 131K | 99% |
MiniMax M3 costs $0.300 per million input tokens and $1.20 per million output tokens via OpenRouter, making it 128th cheapest of 298 paid models.
MiniMax M3 scores 54.7 on the Artificial Analysis Intelligence Index, ranking 7th of 178 benchmarked models, with a GPQA Diamond score of 93%.
MiniMax M3 generates around 50 tokens per second with 630ms time-to-first-token (p50), the 164th fastest tracked model.
MiniMax M3 supports a 1.0M-token context window and can output up to 512K tokens. It accepts text, image, video input.