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 cost-effective pricing at $0.48/1M input and $2.00/1M output tokens, native tool calling support. Access Kimi K2 Thinking via the Helicone API with up to 262K 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
262K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.48
Output
$2.00
Frequently Asked Questions
Kimi K2 Thinking by Helicone costs $0.48 per 1M input tokens and $2.00 per 1M output tokens.
Model Details
ID
kimi-k2-thinking
Provider
HeliconeFamily
kimi-thinking
Release Date
Nov 6, 2025
Knowledge Cutoff
Nov 1, 2025
API Integration
NPM Package
@ai-sdk/openai-compatible
Environment Variables
HELICONE_API_KEY
API Base URL
https://ai-gateway.helicone.ai/v1