The Qwen3.6 native vision-language Plus series models demonstrate exceptional performance on par with the current state-of-the-art models, with a significant improvement in overall results compared to the 3.5 series. The models have been markedly enhanced in code-related capabilities such as agentic coding, front-end programming, and Vibe coding, as well as in multi-modal general object recognition, OCR, and object localization

1curl https://smartoken.top/v1/chat/completions \
2  -H "Authorization: Bearer $SMARTOKEN_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "qwen3.6-plus",
6    "messages": [
7      {
8        "role": "user",
9        "content": "你好"
10      }
11    ],
12    "stream": false
13  }'