Qwen3.7 Flash

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception.

ChatQwen1M tokens$0.0327 / $0.1417 · 1M

qwen/qwen3.7-flash

Context
1M tokens
Completion cap
65,536
Tools
Yes
JSON
Yes
Released
2026-07-27

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.7-flash",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Qwen3.7 Flash?
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world visual perception. Qwen3.7 Flash runs on the Geek Hub API (OpenAI-compatible). Model id: qwen/qwen3.7-flash.
Is Qwen3.7 Flash free?
No. Input is $0.0327 per 1M tokens and output is $0.1417 per 1M tokens on Geek Hub (markup included).
What is the context length of Qwen3.7 Flash?
Qwen3.7 Flash has a 1M tokens context window. It supports up to 65,536 completion tokens.
Does Qwen3.7 Flash support tool calling and structured outputs?
Qwen3.7 Flash accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Qwen3.7 Flash released?
Qwen3.7 Flash was released on 2026-07-27.

More models from Qwen