Kimi K2.5

moonshotai

Kimi's most versatile model featuring a native multimodal architecture that supports both visual and text input. Combines thinking and non-thinking modes with dialogue and agent capabilities. With a 262K context window and massive 252K output capacity, it handles complex multimodal workflows at an exceptional price point.

Try Now

Capabilities

Tool Use

Extended Thinking

Image Input

Example Use Cases

Need vision and reasoning combined

Multimodal agent tasks

Versatile model for mixed dialogue and agent work

Technical Specifications

Context Window

262,144 tokens

Max Output

252,144 tokens

Cache Miss Cost

$0.45 per 1M tokens

Non-Reasoning Cost

$2.80 per 1M tokens

Web Search Cost

$15 per 1K calls

Code Execution Cost

$0.19 per 1K calls