Qwen: Qwen3.5-35B-A3B

Qwen3.5-35B-A3B is a model from Qwen that accepts text, image, and video input and returns text. It offers a 262,144-token context window with up to 81,920 completion tokens per response, which leaves room for long documents, extended transcripts, or multi-step outputs. It supports tool calling and a reasoning mode. The listing does not confirm structured output support or open weights, so teams that depend on either should verify them before committing. At $0.14 per million input tokens and $1.00 per million output tokens, it sits at the low end of the price range. That makes it a candidate for high-volume or input-heavy workloads, especially multimodal ones involving images or video. Its blended benchmark score of 47.9 rests on a single independent benchmark, so its standing is thinly measured. Shortlist it for cost-sensitive testing, and run your own evaluations before relying on it.