Kimi K2.5

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.

Model overview

Model ID: moonshotai/kimi-k2.5
Provider: moonshotai
Type: language
Context window: 262,114 tokens
Max output tokens: 262,114

Tags: reasoning, vision, tool-use, implicit-caching

Model pricing

Metric	Value
`Input tokens (/1M)`	`$0.60`
`Output tokens (/1M)`	`$3.00`
`Image generation`	`n/a`
`Cached input read (/1M)`	`$0.10`
`Cached input write (/1M)`	`n/a`
`Pricing source`	`gateway`

Related docs

Model catalog

Browse every generated model page.

Open catalog

Pricing matrix

Compare model pricing across the full catalog.

Open pricing matrix