MiniMax
MiniMax M3
minimax/minimax-m3
Multimodal model with a 1M context for long agent work.
MultimodalText, Images, Video → TextReady on endue
- Audio & video
- Agentic work
- Low cost
Overview
Good for
Written by endue
- Audio & video
- Agentic work
- Low cost
Not ideal for
From the model’s specs
Nothing in the specs rules out common agent work.
Capabilities
| Tool use | Supported |
|---|---|
| Structured output | Supported |
| JSON mode | Supported |
| Reasoning | Supported |
| Vision | Supported |
| Audio input | Not supported |
| Video input | Supported |
| File input | Not supported |
| Long context | Supported |
Specifications
- Model ID
minimax/minimax-m3- Family
- MiniMax
- Context window
- 1M tokens
- Input
- Text, Images, Video
- Output
- Text
- Released
- 2026-05-31