Kimi K2.5 API
About
Build advanced reasoning agents with Kimi K2.5, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.56/1M input and $3.50/1M output tokens, native tool calling support, open weights architecture. Access Kimi K2.5 via the Venice AI API with up to 66K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Supported
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.56
Output
$3.50
Caching (per 1M tokens)
Read
$0.11
Frequently Asked Questions
Kimi K2.5 by Venice AI costs $0.56 per 1M input tokens and $3.50 per 1M output tokens. Cached reads cost $0.11 per 1M tokens.
Model Details
API Integration