Skip to main content
Post

Qwen4-Max now available on AI Gateway

Vercel made Alibaba's Qwen4-Max available on AI Gateway. It's the first model in the Qwen4 series: a reasoning model with native vision and a 1M-token context window, aimed at coding, professional work, and long-running agent tasks.

Alibaba says it's better at working with professional tools. It can build 3D scenes in Blender and playable games in Unity, Unreal Engine, and Godot, then run what it built and use visual feedback to fix camera, animation, and lighting problems. For finance, legal, and healthcare work, it can call many MCP tools, go through large sets of documents and images, and produce spreadsheets, slide decks, and reports that cite their sources.

On long tasks, it delivers a usable first version early and improves it in later releases, so you can review progress and change direction before the work is done. Alibaba is open-sourcing a Live Delivery plugin for this workflow. Compared with earlier Qwen Max models, Alibaba also says Qwen4-Max uses fewer tokens for the same tasks and writes more secure code by default, with fewer injection, memory safety, and access control vulnerabilities.

Call it with the model name alibaba/qwen4-max in the AI SDK, Chat Completions, or fx. For coding agents like Claude Code, Codex, and Cursor, install the latest Vercel CLI and run npx vercel ai-gateway setup, then pick alibaba/qwen4-max in the agent. The coding agents guide says setup detects the agents on your machine and shows a diff of each planned change before it writes anything. Vercel says AI Gateway passes through provider pricing with no markup, including on bring-your-own-key requests.

Loading replies