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 $0.60/1M input and $2.50/1M output tokens, native tool calling support, open weights architecture. Access Kimi-K2-Thinking via the Nebius Token Factory API with up to 16K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
Yes
Tool Use
Yes
WeightsOpen
Limits
Context Window
128K
Tokens
Input Limit
120K
Tokens
Max Output
16K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.60
Output
$2.50
Reasoning (per 1M tokens)
Output
$2.50
Caching (per 1M tokens)
Read
$0.06
Write
$0.75
Frequently Asked Questions
Kimi-K2-Thinking by Nebius Token Factory costs $0.60 per 1M input tokens and $2.50 per 1M output tokens. Cached reads cost $0.06 per 1M tokens. Cache writes cost $0.75 per 1M tokens.
Model Details
ID
moonshotai/Kimi-K2-Thinking
Provider
Nebius Token FactoryFamily
Release Date
Jan 5, 2026
Knowledge Cutoff
Oct 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NEBIUS_API_KEY
API Base URL
https://api.tokenfactory.nebius.com/v1