Kimi
Kimi k2.5
kimi/kimi-k2.5- Context
- 256K tokens
- Token rate
- 4.0×
- Speed
- Fast
- Hosting
- Direct API
Maximum prompt length
Relative to baseline
Estimated output rate
Optimised routing
Description
Kimi's versatile multimodal model, thinking & non-thinking modes — 256k context
Modalities
- Text in / out
- Supported
- Image / vision input
- Supported
- Audio in / out
- Not supported
- Video synthesis
- Not supported
Pricing
- Baseline per token
- ~$0.0000033
- Adjusted rate
- 4.0× baseline
- Included in
- All paid plans