Skip to main content
Text Generation

kimi-k3

Kimi K3 is Kimi's most powerful flagship model with 2.8 trillion parameters. Built on KDA hybrid linear attention (Kimi Delta Attention) and Attention Residuals technologies, it natively supports vision understanding and features a 1 million token context window. It is the world's first open-source 3-trillion-parameter model designed for long-context programming, knowledge work, and advanced reasoning.

Inference Service Provider

The inference service provider for kimi-k3 is Alibaba Cloud Model Studio.

Model Capabilities

  • China (Beijing)
  • Singapore
  • Germany (Frankfurt)
  • Japan (Tokyo)
  • Hong Kong (China)
CapabilitySupportCapabilitySupport

Input Modality

Image Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Unsupported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

1048576

Max Output Length

1048576

Context Window

1048576

Max Input Length (Thinking Mode)

1048576

Max Output Length (Thinking Mode)

1048576

Max Chain-of-Thought Length

1048576

Pricing

This page only shows the original pricing for model API calls, excluding any limited-time promotions. Visit Model Studio Console for promotional offers.
  • China (Beijing)
  • Singapore
  • Germany (Frankfurt)
  • Japan (Tokyo)
  • Hong Kong (China)
Billing ItemPrice (USD)Unit

Input

2.827

Per 1M tokens

Output

14.133

Per 1M tokens

Input(Implicit Cache)

0.283

Per 1M tokens

Rate Limits

  • China (Beijing)
  • Singapore
ParameterValue

RPM (Requests Per Minute)

500

TPM (Tokens Per Minute)

1,000,000

Token Plan
Model Playground
  • Music generation
Statistics and Monitoring