Updated

Qwen4-Max

Alibaba Cloud released Qwen4-Max, the production version of the Qwen4-Max-Preview model, for international deployment. It combines text generation, image and video understanding, reasoning, web search, tool calling, and structured outputs.

By No Code MBA · Facts checked

Provider
Alibaba
Announcement date
Status at last check
Generally available

What changed

Following the November 11 Qwen4-Max-Preview, Alibaba lists Qwen4-Max as available for international deployment on November 16. The model supports text, image, and video input; deep reasoning, web search, tool and function calling, structured outputs, and OpenAI and Anthropic API-compatible interfaces. Alibaba documents a 1,000,000-token context length.

Access and availability

Use Alibaba Cloud Model Studio with model ID qwen4-max. Alibaba lists Singapore, Frankfurt, and Virginia deployments with international or global scope; follow the regional Model Studio setup and API guide to create an API key and make requests.

Official access documentation

What you can build

Compare its multimodal inputs and tool-calling behavior with your existing model on representative tasks before choosing it for an agent workflow.

Limitations

Alibaba documents that batch inference, fine-tuning, and model deployment are not supported. Regional capability and deployment scope vary; check the Model Studio region documentation before use.

Sources and release history