kimi-k3

Updated at:

Kimi-K3 is Moonshot AI's most capable flagship model to date, featuring 2.8 trillion parameters. Built on the KDA hybrid linear attention mechanism (Kimi Delta Attention) and Attention Residuals, it natively supports visual understanding and offers a 1-million-token context window. As the world's first open-source model at the 3-trillion-parameter scale, it is designed for frontier intelligence scenarios such as long-horizon programming, knowledge work, and reasoning.

Inference Service Provider

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

Model Capabilities

China (Beijing)

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Singapore

Scope: International

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Germany (Frankfurt)

Scope: Global

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

US (Virginia)

Scope: Global

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Scope: International

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Japan (Tokyo)

Scope: Global

Capability

Support

Capability

Support

Input Modality

Text Image

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Unsupported

Fine-tuning

Unsupported

Context Limits

Parameter

Value

Parameter

Value

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)

Billing Item

Price (CNY)

Unit

Input

20

Per 1M tokens

Output

100

Per 1M tokens

Input(Implicit Cache)

2

Per 1M tokens

Singapore

Scope: International

Billing Item

Price (CNY)

Unit

Input

21.875

Per 1M tokens

Output

109.376

Per 1M tokens

Input(Implicit Cache)

2.188

Per 1M tokens

Germany (Frankfurt)

Scope: Global

Billing Item

Price (CNY)

Unit

Input

20

Per 1M tokens

Output

100

Per 1M tokens

Input(Implicit Cache)

2

Per 1M tokens

US (Virginia)

Scope: Global

Billing Item

Price (CNY)

Unit

Input

20

Per 1M tokens

Output

100

Per 1M tokens

Input(Implicit Cache)

2

Per 1M tokens

Scope: International

Billing Item

Price (CNY)

Unit

Input

21.875

Per 1M tokens

Output

109.376

Per 1M tokens

Input(Implicit Cache)

2.188

Per 1M tokens

Japan (Tokyo)

Scope: Global

Billing Item

Price (CNY)

Unit

Input

20

Per 1M tokens

Output

100

Per 1M tokens

Input(Implicit Cache)

2

Per 1M tokens

Rate Limits

China (Beijing)

Parameter

Value

RPM (Requests Per Minute)

15,000

TPM (Tokens Per Minute)

1,200,000

Singapore

Scope: International

Parameter

Value

RPM (Requests Per Minute)

10,000

TPM (Tokens Per Minute)

1,200,000

Germany (Frankfurt)

Scope: Global

Parameter

Value

RPM (Requests Per Minute)

15,000

TPM (Tokens Per Minute)

1,200,000

US (Virginia)

Scope: Global

Parameter

Value

RPM (Requests Per Minute)

15,000

TPM (Tokens Per Minute)

1,200,000

Scope: International

Parameter

Value

RPM (Requests Per Minute)

10,000

TPM (Tokens Per Minute)

1,200,000

Japan (Tokyo)

Scope: Global

Parameter

Value

RPM (Requests Per Minute)

15,000

TPM (Tokens Per Minute)

1,200,000