qwen3.7-flash

Description

Alibaba Qwen3.7-Flash — the fast tier of the Qwen3.7 native vision-language line, which the vendor highlights for multimodal agent work (search and CI agents) and for steadier end-to-end task execution than 3.6-Flash. 1,000,000-token context window, up to 65,536 output tokens, and up to 256 images or 64 videos per request. Accepts text, image, and video input and returns text; supports thinking mode, function calling, built-in tools, and structured outputs. Priced in three context bands, so a long-context request costs more per token than a short one.