How to Install / Upgrade: Qwen 3.8 Max now available on Vercel AI Gateway

Qwen 3.8 Max is now available on the Vercel AI Gateway. It is a single model for text-only and vision-language work, with 2.4 trillion parameters and a context window of up to 1 million tokens. It fits software engineering and office productivity, and visual tasks such as turning screenshots or design files into working pages, captioning video, and answering questions grounded in an image.

To install or upgrade, send your model traffic through the Vercel AI Gateway and select Qwen 3.8 Max as the model for new or existing requests. Point both text-only and vision-language calls at that same model so one gateway configuration covers chat, coding, and image-grounded work. If you already use another model on the gateway, switch the model choice to Qwen 3.8 Max for the workloads you want on this release; no separate text and vision models are required for those use cases.

Watch for long inputs: the context window reaches up to 1 million tokens, so large documents, long threads, or multi-image prompts can grow cost and latency. Confirm the model is active by running a short text prompt and a vision prompt (for example a screenshot or design file) through the AI Gateway and checking that both complete under Qwen 3.8 Max. If either path fails or routes elsewhere, recheck that the gateway is set to Qwen 3.8 Max and that the request type matches what you expect for text-only versus vision-language use.