The Qwen 3.6 native vision-language Plus model demonstrates outstanding performance comparable to current state-of-the-art models, with significant improvements over the 3.5 series. The model has notably enhanced capabilities in areas such as agentic coding, front-end programming, vibe coding, as well as multimodal recognition, OCR, and object localization.
Different token groups have different prices. Unit: Million tokens (M)
/v1/chat/completionsPOST/v1/messagesPOST