qwen-max

Updated at:

A Qwen2.5-series ultra-large language model at the hundred-billion parameter scale, supporting input in Chinese, English, and other languages. qwen-max is upgraded on a rolling basis as the model evolves. To use a fixed version, use a historical snapshot version. This model version is functionally equivalent to the snapshot model qwen-max-2025-01-25.

Inference Service Provider

The inference service provider for qwen-max is Alibaba Cloud Model Studio.

Model Capabilities

China (Beijing)

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Supported

Structured Outputs

Supported

Web Search

Supported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Supported

Fine-tuning

Unsupported

Singapore

Scope: International

CapabilitySupportCapabilitySupport

Input Modality

Text

Output Modality

Text

Model Experience

Supported

Function Calling

Unsupported

Structured Outputs

Supported

Web Search

Unsupported

Prefix Completion

Supported

Context Caching

Supported

Batch Inference

Supported

Fine-tuning

Unsupported

Context Limits

ParameterValueParameterValue

Max Input Length

30720

Max Output Length

8192

Context Window

32768

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 ItemPrice (CNY)Unit

Input

2.4

Per 1M tokens

Output

9.6

Per 1M tokens

Input(Implicit Cache)

0.48

Per 1M tokens

Input(Batch File)

1.2

Per 1M tokens

Output(Batch File)

4.8

Per 1M tokens

Singapore

Scope: International

Billing ItemPrice (CNY)Unit

Input

11.743

Per 1M tokens

Output

46.971

Per 1M tokens

Input(Implicit Cache)

2.349

Per 1M tokens

Input(Batch File)

5.871

Per 1M tokens

Output(Batch File)

23.486

Per 1M tokens

Rate Limits

China (Beijing)

ParameterValue

RPM (Requests Per Minute)

1200

TPM (Tokens Per Minute)

1,000,000

Singapore

Scope: International

ParameterValue

RPM (Requests Per Minute)

600

TPM (Tokens Per Minute)

1,000,000