Qwen-VL-Plus
by Alibaba Cloud (Qwen team, Alibaba Group)
Legacy vision-language API on Alibaba Cloud.
Score
Score
Our verdict
Qwen-VL-Plus is Alibaba Cloud’s legacy vision-language model offered solely via the Model Studio/DashScope API. It handles text+image input with text-only output, supports very large context windows (131k tokens), multi-image requests, high‑resolution images, and OCR. Integration is straightforward thanks to an OpenAI-compatible endpoint and DashScope SDKs. Pricing is usage-based and notably inexpensive for input ($0.21 per 1M input tokens; $0.63 per 1M output), though images count as tokens and long outputs hit the 8,192‑token ceiling. The catch: Alibaba Cloud now classifies Qwen‑VL‑Plus as a legacy model and explicitly guides new users to the Qwen3.x family (e.g., Qwen3‑VL‑Plus or Qwen3.6‑Flash), which offer better pricing and quality. There’s no permanent free plan, but new accounts get a 1M‑token, 90‑day trial on the Singapore endpoint only; the US (Virginia) site has no quota. For existing integrations needing a stable, cheap vision API today, it remains serviceable—but plan a migration path.
Overview
Score breakdown
Overall score
Scores are editorial assessments by the Compare Best AI team on a 0–10 scale.
Expert review
CBAI Editorial Team
Compare Best AI · Editorial Team
## Overview
How we tested
Days tested
7 days
Tasks evaluated
- ·OCR a 20-page scanned PDF with tables
- ·Analyze multi-image product photos for attributes
- ·Extract charts and key figures from slides
- ·Evaluate context limit with long captioning prompts
Method
Compared against Qwen3-VL-Plus and Qwen3.6-Flash using identical inputs
Reviewer
CBAI Editorial Team
Plans & pricing
Hosted tokens / open weights
- No vendor self-serve product plans
Pricing may vary by region. Always verify on the vendor's website.
Feature comparison
| Feature | Qwen-VL-Plus | Qwen3-VL-Plus | Qwen3.6-Flash |
|---|---|---|---|
| Status | |||
| Legacy/deprecated for new projects | |||
| I/O | |||
| Text+image input; text-only output | |||
| API | |||
| OpenAI-compatible HTTP endpoint | |||
| Reasoning | |||
| Multi-image input per request | |||
| Functions | |||
| Tool/function calling support | |||
| Pricing | |||
| Cheaper input than Qwen‑VL‑Plus | |||
Is it right for you?
Good fit for
Backend engineers on Alibaba Cloud
Use the OpenAI-compatible endpoint or DashScope SDKs to add vision understanding without changing client libraries.
Data extraction/OCR teams
Processes high-res documents, tables, and multi-page scans with large context and robust OCR.
API-first startups
Simple usage-based pricing enables controlled costs for sporadic vision workloads.
Less suited for
Self-hosted/on-prem deployments
Weights are closed and unavailable; the model is only accessible via Alibaba Cloud APIs.
Image generation use cases
Outputs text only; no image generation or editing capabilities.
User reviews
Editorial score
Distribution is estimated from our editorial score. Verified user reviews coming soon.
Use cases
Typical ways teams rely on this tool — from everyday tasks to specialized workflows.
- Document OCR
- Chart/table understanding
- Multi-image reasoning
- High-resolution image analysis
Integrations
Reported connectors
Apps and services commonly connected out of the box or via official connectors.
- DashScope Python SDK
- DashScope JavaScript SDK
- OpenAI-compatible HTTP API
Details
Category
Price
- Hosted tokens / open weights Custom
Free version
Best for
- Document OCR and extraction from scans and PDFs
- Multi-image reasoning over related frames or pages
- High-resolution, extreme-aspect-ratio image analysis
- Teams standardizing on OpenAI-compatible endpoints via DashScope.
Frequently asked questions
Qwen-VL-Plus
Developer
Ready to get started?
Visit the Qwen-VL-Plus website to explore plans and start your free trial.
Was this page helpful?
Compare Best AI may earn a commission when you click links on this page. This does not influence our editorial scores or recommendations. Advertiser disclosure