Kimi K2 Thinking API
About
Build advanced reasoning agents with Kimi K2 Thinking, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.75/1M input and $3.20/1M output tokens, native tool calling support, open weights architecture. Access Kimi K2 Thinking via the Venice AI API with up to 66K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
66K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.75
Output
$3.20
Caching (per 1M tokens)
Read
$0.38
Frequently Asked Questions
Kimi K2 Thinking by Venice AI costs $0.75 per 1M input tokens and $3.20 per 1M output tokens. Cached reads cost $0.38 per 1M tokens.
Model Details
ID
kimi-k2-thinking
Provider
Venice AIFamily
kimi-thinking
Release Date
Dec 10, 2025
Knowledge Cutoff
Apr 1, 2024
API Integration