Qwen3.7 Plus API
Qwen3.7-Plus is the multimodal agent model in the Qwen3.7 line. The official page highlights image, text and video input, GUI operation, visual-reference coding and end-to-end mobile navigation, alongside a 1M context and 131K output.
Official source: model page · verified 2026-10-22
Pricing
Prices can change with upstream providers; the rate at settlement is authoritative.
Call the API
Use the OpenAI-compatible endpoint; no model-specific SDK setup is required.
curl https://api.kimiseek.app/v1/chat/completions \
-H "Authorization: Bearer $KIMISEEK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.7-plus",
"messages": [{"role": "user", "content": "Hello from KimiSeek"}]
}'Where it fits
Best for
- GUI and visual-reference coding agents
- Multimodal product and workflow automation
- Long-context applications that need image/video input
Tradeoffs
- Less capable than Qwen3.8-Max for the hardest tasks
- Not a pure-text model; validate multimodal latency and cost
Model details
FAQ
What makes Qwen3.7-Plus different from Max?
Plus is multimodal and visually agentic; Max in the official page is pure text and positioned around agentic coding/productivity.
Can it operate a GUI?
The official page highlights reading screens and operating GUIs as a core capability; test it against your target interfaces.
How do I call this model?
Use KimiSeek's OpenAI-compatible API and set the model field to qwen3.7-plus with your KimiSeek API key.