Updated

Qwen4-Max-Preview (preview)

Alibaba Cloud introduced Qwen4-Max-Preview, a multimodal model for text generation, image and video understanding, and reasoning. It supports tool calling and structured outputs and is available in preview through Token Plan only.

By No Code MBA · Facts checked

Provider
Alibaba
Announcement date
Status at last check
Limited access or preview

What changed

Qwen4-Max-Preview is a new preview model in Alibaba's Qwen family, combining text generation, image and video understanding, reasoning, web search, tool calling, and structured outputs. Alibaba documents a 1-million-token context length and OpenAI and Anthropic API compatibility.

Access and availability

Choose Token Plan Personal or Token Plan Team, obtain a dedicated API key using Alibaba Cloud's guide, then call model ID qwen4-max-preview through the documented Token Plan endpoint.

Official access documentation

What you can build

Treat this as a time-limited preview, and validate multimodal and tool-calling behavior before relying on it in an application.

Limitations

This is a preview available only through Token Plan, not pay-as-you-go. Alibaba states the preview runs through November 25, 2026 UTC+8 and the model will be retired afterward. The maximum output budget is shared between reasoning and final response.

Sources and release history