Qwen3.7 Flash

qwenqwen/qwen3.7-flash

How TheRouter serves this differently from the vendor

As the vendor operates it

Alibaba Cloud Model Studio lists qwen3.7-flash with 1M context, thinking mode (toggled with enable_thinking), function calling, built-in tools such as web search and code execution, and structured output, plus image and video input.

On TheRouter

TheRouter serves qwen/qwen3.7-flash on the OpenAI-compatible chat route with text+image+video input, text output, 1,000,000 context, 131,072 max output, and supported parameters temperature, max_tokens, top_p, tools, tool_choice, response_format, and stop. No reasoning parameter and no built-in-tool switch are listed; tools carries your own function definitions.

alibabacloud.com ↗

API guide

Vision input

Send images with the OpenAI-compatible content-array message format. This is the direct replacement call shape for former qwen/qwen3-vl-flash requests.

cURL

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.7-flash",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Extract every visible error message from this screenshot."},
        {"type": "image_url", "image_url": {"url": "https://therouter.ai/assets/vision-sample.png"}}
      ]
    }],
    "max_tokens": 1024
  }'

Chat completion

Use Qwen3.7-Flash for low-cost long-context text work through the same Chat Completions endpoint.

cURL

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.7-flash",
    "messages": [
      {"role": "system", "content": "Return concise JSON."},
      {"role": "user", "content": "Classify these support tickets by urgency and product area."}
    ],
    "temperature": 0.1,
    "max_tokens": 1200,
    "response_format": {"type": "json_object"}
  }'

Function calling

Alibaba lists function calling as supported for qwen3.7-flash. Keep tool schemas small for Flash-tier agent lanes.

cURL

curl https://api.therouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $THEROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.7-flash","messages":[{"role":"user","content":"Check whether ticket TR-204 needs escalation."}],"tools":[{"type":"function","function":{"name":"get_ticket","description":"Fetch a ticket by id","parameters":{"type":"object","properties":{"id":{"type":"string"}},"required":["id"]}}}],"tool_choice":"auto"}'

Part of

multimodal openai-compatible routing

Guides

Guide2026-08-28Qwen3.8-Flash API Guide: Multimodal, 1M Context, and OpenAI SDK Setup

Fact ledger — every claim on this page traces here

source	URL	retrieved
Stable alias	alibabacloud.com ↗	2026-10-17	verified
Context window	alibabacloud.com ↗	2026-10-17	verified
Maximum completion	—	—	verified
Modalities	alibabacloud.com ↗	2026-10-17	verified
Image limits (vendor)	alibabacloud.com ↗	2026-10-17	verified
Video limits (vendor)	alibabacloud.com ↗	2026-10-17	verified
Thinking mode	alibabacloud.com ↗	2026-10-17	verified
Tooling	alibabacloud.com ↗	2026-10-17	verified
Release date	—	—	unknown
Training cutoff	—	—	unknown
License / weights	—	—	unknown
Official benchmark table	alibabacloud.com ↗	2026-10-17	unknown
Multimodal benchmark table	alibabacloud.com ↗	2026-10-17	unknown
Alibaba names qwen3.7-flash as the cost-reduced step after qwen3.7-plus for image and video understanding	alibabacloud.com ↗	2026-10-17	verified
What should I use now that qwen/qwen3-vl-flash is retired?	alibabacloud.com ↗	2026-10-17	to verify
When should I choose qwen3.7-flash instead of qwen3.7-plus?	alibabacloud.com ↗	2026-10-17	to verify
Can I turn on thinking mode for qwen/qwen3.7-flash?	alibabacloud.com ↗	2026-10-17	to verify
Is Qwen3.7-Flash open source?	alibabacloud.com ↗	2026-10-17	to verify