Qwen3.5-27B is a dense (non-MoE) transformer model and the only full-weight model in the Qwen3.5 Medium Series. Released February 24, 2026, it achieves 72.4% on SWE-bench Verified — matching GPT-5 mini — despite having just 27B parameters. It supports native multimodal input (text + images + video) via early fusion, runs on a 22GB Mac M-series device, and natively extends to 1M token contexts.

Provider: Alibaba (Cloud)

Category: Vision

Pricing: $0.30 In / $2.40 Out per 1M

Back to model catalog · Try in playground

Loading model details...

Fetching the latest models and pricing from the API.

    Qwen3.5 27B API | Alibaba (Cloud) | Fast Inference