- Context (input / output)
- 1.05M / -
- Release date
- 2026-10
- Input modalities
- Text · Image · Video
- Output modalities
- Text
- Note
- Highspeed offers the same capabilities at approximately 2–3 times the output speed
- Total parameters
- 3T-class (exact count not disclosed)
- Weight status
- Not yet available; full weights planned by November 4, 2026
- API model ID
- kimi-k3.1-pro / kimi-k3.1-pro-highspeed
- Default reasoning effort
- max (low / high / max)