Kimi K2 Instruct API
About
Build advanced reasoning agents with Kimi K2 Instruct, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers available completely free of charge, native tool calling support. Access Kimi K2 Instruct via the Nvidia API with up to 8K 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
128K
Tokens
Input Limit
128K
Tokens
Max Output
8K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Kimi K2 Instruct by Nvidia costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
ID
moonshotai/kimi-k2-instruct
Provider
NvidiaFamily
kimi
Release Date
Jan 1, 2025
Knowledge Cutoff
Jan 1, 2024
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
NVIDIA_API_KEY
API Base URL
https://integrate.api.nvidia.com/v1