Kimi K2 Instruct API
About
Kimi K2 Instruct is a high-performance LLM available via the IO.NET API, ideal for scalable text generation and natural language processing. This model delivers cost-effective pricing at $0.39/1M input and $1.90/1M output tokens, native tool calling support. Access Kimi K2 Instruct via the IO.NET API with up to 4K 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
33K
Tokens
Input Limit
33K
Tokens
Max Output
4K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.39
Output
$1.90
Caching (per 1M tokens)
Read
$0.20
Write
$0.78
Frequently Asked Questions
Kimi K2 Instruct by IO.NET costs $0.39 per 1M input tokens and $1.90 per 1M output tokens. Cached reads cost $0.20 per 1M tokens. Cache writes cost $0.78 per 1M tokens.
Model Details
ID
moonshotai/Kimi-K2-Instruct-0905
Provider
IO.NETFamily
kimi-k2
Release Date
Sep 5, 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