Kimi K2 Thinking API
About
Process massive datasets with Kimi K2 Thinking, featuring an expansive 256K context window for long-document analysis. This model delivers available completely free of charge, native tool calling support. Access Kimi K2 Thinking via the Qiniu API with up to 100K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
Yes
WeightsClosed
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
256K
Tokens
Input Limit
256K
Tokens
Max Output
100K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Kimi K2 Thinking by Qiniu costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
QINIU_API_KEY
API Base URL
https://api.qnaigc.com/v1