Models & pricing / qwen3.7-plus · Alibaba
Alibaba

qwen3.7-plus API

Qwen3.7-Plus is a multimodal Qwen 3.7 model that emphasizes visual understanding and interactive agents alongside text work. Use qwen3.7-plus through XiuAI’s current OpenAI-compatible endpoint, with the correct image, video and tool fields, and distinguish it from the text-only Max entry.[1][3]

qwen3.7-plus

Model overview

Published provider specifications. Available features depend on the current API route.

Input
text / image / video
Output
Text
Context
1M
Maximum output
131072
API routes
OpenAI-compatible API

Visual material and interactive tasks

Vendor examples include reading scenes and screens, writing code from visual references and interactive tool tasks. Evaluate it for screenshots, charts or page references followed by analysis and code. Proposed actions do not mean XiuAI hosts a browser, phone or desktop environment.[1]

Modality differences from 3.7 Max

The current generic Plus entry lists image, text and video input with text output, while the generic 3.7 Max entry points to a text-only version. Check exact versions for visual work; the Max name does not imply every Plus modality.[1][2]

The vendor page also includes dated snapshots and regional capability tables. A generic name, dated snapshot and regional service are different concepts. Check the ID actually used instead of combining the largest capabilities from different tables.[1]

Compare the same material and output requirements

Visual inputs, long material, tool results and output affect the total charge. Compare current conditions and request records here rather than treating one Alibaba Cloud region’s prices, search or batch options as XiuAI configuration.[1][3]

API access

Using Plus through XiuAI

Use qwen3.7-plus with your existing key and balance through the current OpenAI-compatible protocol. Check text and media formatting in messages before adding tools. Vendor cross-application demonstrations require a runtime supplied by your application.[3][1]

Send a request using your existing API key.

POST /v1/chat/completions
curl 'https://router-api.xiu.ai/v1/chat/completions' \
  -H "Authorization: Bearer $XIUAI_API_KEY" \
  -H 'Content-Type: application/json' \
  --data-raw '{
  "model": "qwen3.7-plus",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'
Read the API documentation

Frequently asked questions

Does Plus multimodality also apply to qwen3.7-max?

No. The official input ranges differ for these generic IDs: Plus lists images, text and video, while generic Max is text-only. Check the exact ID and snapshot.[1][2]

Does GUI understanding mean the platform executes actions?

No. The model can analyze a screen and propose actions, while the application handles tool connections, permissions, execution and feedback. XiuAI provides a model API, not hosted devices or workflows.[1]

Can I reuse another region’s search or batch configuration?

Do not copy it automatically. Vendor tables distinguish regional capabilities, and XiuAI has its own integration scope. Use the current catalog and protocol rather than inferring availability from another region’s table.[1][3]

Related models

qwen3.7-maxqwen3.8-flash

Sources 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-Plus documentation[2] Qwen3.7-Max versions and modalities[3] Current XiuAI model and pricing dataStructured output