Minimax
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,...
| Specifications | |
|---|---|
| Provider | Minimax |
| Input pricing | $0.30/M tokens |
| Output pricing | $1.20/M tokens |
| Context length | 1.0M tokens |
| Max output | 512K tokens |
| Input modalities | textimagevideo |
| Output modalities | text |
| Tokenizer | Other |
| Content moderated | No |
| HuggingFace | MiniMaxAI/Minimax-M3 |
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p