⌘K

Qwen3 Max 2026-01-23

qwen3-max-2026-01-23

Compared to the snapshot on September 23, 2025, the Qwen-3-Max model achieves an effective integration of thinking mode and non-thinking mode in this version, resulting in a significant, comprehensive improvement in overall model performance. In thinking mode, capabilities for Web Search, Web Information Extraction, and Code Interpreter tools are released simultaneously, enabling the model to solve more difficult problems with higher accuracy by incorporating external tools while engaging in slow thinking. This version is the snapshot from January 23, 2026.

Authentication

authorization string required

All APIs require authentication via Bearer Token.

Get API Key:

Visit API Key Management Page to get your API Key.

Usage:

Add to request header:

Authorization: Bearer YOUR_API_KEY

Parameters

model string required

Model ID to use for the request

Value: qwen3-max-2026-01-23

messages array required

Array of message objects representing the conversation history

role string required

Message role

Options: user, assistant, system, developer

content string | array required

Text string or multimodal array

max_tokens integer

Maximum tokens to generate in the completion.

Range: 1 - 16384

temperature number

Sampling temperature to use.

Default: 1.0

Range: 0.0 - 2.0

top_p number

Nucleus sampling parameter.

Default: 1.0

Range: 0.0 - 1.0

stream boolean

Whether to stream response incrementally.

Default: false