Qwen: Qwen3.6 35B A3B

Qwen3.6 35B A3B is a model from Qwen that accepts text, image, and video input and returns text. It offers a 262,144-token context window and allows completions of up to 235,929 tokens, which suits long documents, extended transcripts, or lengthy generated output. It supports tool calling and a reasoning mode. The listing does not confirm structured output support or open-weights availability, so verify both before depending on them. Pricing is $0.10 per million input tokens and $0.95 per million output tokens. Because input costs far less than output, the model fits workloads that read large amounts of material, including images and video, but write comparatively little. Its blended benchmark score of 24.2 comes from a single independent benchmark, where it scored 30.1 on the AI index. That is thin evidence, so treat its standing as unproven. Shortlist it for budget-conscious multimodal or long-context work, and run your own tests before committing.