Skip to main content

Latest model: Qwen4-Max-Preview

Explore Qwen4-Max-Preview's multimodal understanding, deep reasoning, tool calling, and Token Plan access

Qwen4-Max-Preview is the next-generation flagship multimodal model in the Qwen family, combining text generation, image and video understanding, and deep reasoning. It is designed for coding, office productivity, frontend design, and complex agentic tasks. With support for web search, tool calling, and structured outputs, along with compatibility with the OpenAI and Anthropic APIs, it enables developers to build intelligent applications capable of multimodal understanding and task execution. Model ID: qwen4-max-preview
Qwen4-Max-Preview is currently in preview and is available through Token Plan only. Pay-as-you-go access is not supported. The preview period runs from 10:00 on November 11, 2026 to 24:00 on November 25, 2026 (UTC+8); no changes will be made during this period, and the model will be retired after the preview ends.

Capabilities and specs

CapabilityDescription
Text generation and deep reasoningThinking is enabled by default; use reasoning_effort to adjust reasoning intensity
Image and video understandingAccepts text, images, and video for screenshot analysis, document understanding, and video analysis
Tool callingSupports Function Calling, web search, and built-in tools
Structured outputsSupports JSON Object and JSON Schema
API compatibilityCompatible with OpenAI Chat Completions, Responses, and Anthropic Messages APIs
ParameterValue
Context length1M tokens
Maximum output393,216 tokens, shared by thinking and the final answer

Quick start

Access Qwen4-Max-Preview through Token Plan:
  1. Choose Token Plan Personal or Token Plan Team and follow its guide to obtain a dedicated API key.
  2. Use the dedicated Base URL: https://token-plan.ap-southeast-1.maas.aliyuncs.com. See the Token Plan guide for the complete endpoint for each protocol.
  3. Set the model ID to qwen4-max-preview.
See the Token Plan guides for supported clients, configuration steps, and Credits benefits.

Usage notes

Output budget change (OpenAI Chat Completions): Starting with qwen4-max-preview, max_tokens is equivalent to max_completion_tokens. Both limit the combined tokens for thinking and the final answer. Thinking consumes part of the same budget, so a limit previously sized for the answer alone may truncate output. Allow room for both when choosing the limit. Existing Qwen models retain their previous behavior. See API compatibility upgrade notice.
  • Thinking: Enabled by default. Choose low, medium, or xhigh (default). Do not set reasoning_effort and thinking_budget together. See Thinking.
  • Multi-turn conversations: Chat Completions enables preserve_thinking by default. Return all historical thinking in the assistant messages' reasoning_content field; do not concatenate it into content.
  • Multimodal input and tool calling: See Image and video understanding for visual input, Function calling for tool definitions and workflows, and Structured outputs for output formats.