kimi-k2.5

Chat Qwen
API Docs

Description

kimi-k2.5 is the most versatile model released by Moonshot AI to date, with native multimodal architecture design, supporting both visual and text input, thinking and non-thinking modes, dialogue and Agent tasks.

Specifications

Type
Chat
Vendor
Qwen
Model ID
kimi-k2.5
Context Window
256K
Max Input
224K
Max Output
16K
Requests / Minute
500
Tokens / Minute
1000000

Pricing

Default

Input + Output
Input Base Price
$0.004018 / 1000 tokens
Output Base Price
$0.021077 / 1000 tokens

Cache Hitin

Input Only
Input Base Price
$0.000805 / 1000 tokens

Explicit Cache Creation

Input Only
Input Base Price
$0.005026 / 1000 tokens

Explicit Cache Hitin

Input Only
Input Base Price
$0.000399 / 1000 tokens