Compare Models
Created by
moonshotai
moonshotaiReleasedJan 26, 2026
kimi-k2.5 is Kimi's most versatile model to date, featuring a native multimodal architecture that supports both visual and text input, thinking and non-thinking modes, and dialogue and agent tasks.
Limits
Context Length256K
Max Output Tokens256K
Pricing
Pricing (Input)$0.60/M
Pricing (Output)$3.00/M
Caching
Input Modalities
Text
Image
PDF
Audio
Output Modalities
Text
Image
Audio
Features
Reasoning
Tools
Temperature
No model selected
Use the selector above to choose a model.