qwen3.7-max API
Qwen3.7-Max targets coding, knowledge work and long-running tasks in the Qwen 3.7 family. The current generic qwen3.7-max vendor entry points to a text-only version. Do not transfer visual capabilities from other dated snapshots on that page to this XiuAI ID.[1][3]
qwen3.7-maxModel overview
Published provider specifications. Available features depend on the current API route.
- Input
- text
- Output
- Text
- Context
- 1M
- Maximum output
- 131072
- API routes
- OpenAI-compatible API
Start with text-based engineering and knowledge tasks
Evaluate code reasoning, long-document analysis, instruction execution and tool-assisted knowledge work. Provide sufficient evidence and checkable output requirements. If raw screenshots or video are required, choose a model with that modality rather than selecting solely by Max positioning.[1]
Do not combine snapshots from the same document
The current vendor page says generic qwen3.7-max is functionally equivalent to the 2026-05-20 text-only snapshot, and separately lists a visual 2026-06-08 snapshot. Their names and scope differ; the later snapshot is not evidence for the generic ID’s capabilities.[1]
When comparing with 3.7 Plus, resolve modality requirements first, then compare like-for-like text quality and cost. Plus image and video input does not automatically carry over because another entry is called Max.[1][2]
Pricing generic names and dated snapshots
The vendor page contains several snapshots and regional prices; XiuAI displays the exact catalog ID and its current billing conditions. Match version, input/output units and cache conditions before comparing. Do not combine one snapshot’s pricing with another’s capabilities.[1][3]
API access
Using the current Max entry through XiuAI
Use qwen3.7-max through the current OpenAI-compatible endpoint with your existing key. Validate text responses and tool workflows. If you need a dated snapshot, confirm that its ID is actually published in the XiuAI catalog instead of constructing a name.[3][1]
Send a request using your existing API key.
POST /v1/chat/completionscurl 'https://router-api.xiu.ai/v1/chat/completions' \
-H "Authorization: Bearer $XIUAI_API_KEY" \
-H 'Content-Type: application/json' \
--data-raw '{
"model": "qwen3.7-max",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'Read the API documentationFrequently asked questions
Why does this page describe text when the vendor page also mentions vision?
The vendor page groups a generic ID with several dated snapshots. The current generic entry points to the May 20 text-only snapshot; the June 8 visual snapshot is separate. Content must follow the exact callable ID.[1]
Which field should I change to send a screenshot?
First select an available model supporting visual input rather than adding an image field to a text-only entry. Review 3.7 Plus or another available visual model, then use its protocol format.[1][2][3]
Does a generic model name permanently pin a snapshot?
It is not a permanent promise. This describes the current documented mapping and should be reviewed when release notes change. Keep regression samples and confirm the service’s supported version-selection mechanism if behavior must remain fixed.[1]
Related models
qwen3.7-plusqwen3.8-maxSources and updates
Specifications reference provider documentation; prices and availability come from the current XiuAI catalog. Specifications checked: 2026-11-11
Content reviewed: 2026-11-16
[1] Alibaba Cloud Qwen3.7-Max documentation[2] Qwen3.7-Plus modalities[3] Current XiuAI model and pricing dataStructured output