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 $0.55/1M input and $2.25/1M output tokens, native tool calling support. Access Kimi K2 Thinking via the IO.NET API with up to 4K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
Yes
WeightsClosed
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
33K
Tokens
Input Limit
33K
Tokens
Max Output
4K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.55
Output
$2.25
Caching (per 1M tokens)
Read
$0.28
Write
$1.10
Frequently Asked Questions
Kimi K2 Thinking by IO.NET costs $0.55 per 1M input tokens and $2.25 per 1M output tokens. Cached reads cost $0.28 per 1M tokens. Cache writes cost $1.10 per 1M tokens.
Model Details
ID
moonshotai/Kimi-K2-Thinking
Provider
IO.NETFamily
kimi-thinking
Release Date
Nov 1, 2024
Knowledge Cutoff
Aug 1, 2024
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
IOINTELLIGENCE_API_KEY
API Base URL
https://api.intelligence.io.solutions/api/v1