Context131.1K tokens
Price (In / Out)$0.20/M / $0.60/M
CategoryMultimodal LLM
Max Output8.2K tokens
About Qwen3-VL
Qwen3-VL is Alibaba's multimodal vision-language model from the Qwen3 family. It processes images, videos, and text together, excelling at document understanding, chart reading, OCR, and visual reasoning tasks across multiple languages.
Capabilities
textvisioncodetool use
Input Modalities
textimagevideo
Output Modalities
text
Technical Details
- API Identifier
- qwen-vl-max
- Category
- Multimodal LLM
- Context Window
- 131,072 tokens
- Max Output Tokens
- 8,192 tokens
Tags
vision-language-modelmultimodalocrdocument-understandingvideo-understandingchinese-aialibabaqwenopen-sourcevisual-reasoning
Run this model yourself
Local and cloud setup for Qwen3-VL, with exact configurations, sources and clear evidence limits.
No reviewed setup guide is available for this model yet. Explore configurations with documented support in the hardware finder.
Benchmarks
Performance scores for Qwen3-VL across standard benchmarks.
MMMUOpenRouter · Apr 2025
70.3
DocVQAOpenRouter · Apr 2025
94.1
ChartQAOpenRouter · Apr 2025
86.5
OCRBenchOpenRouter · Apr 2025
88.7
MathVistaOpenRouter · Apr 2025
74.8
RealWorldQAOpenRouter · Apr 2025
75.2
Video-MMEOpenRouter · Apr 2025
69.8
Pricing
Token pricing for Qwen3-VL API usage.
Input Tokens
$0.20/M
per million tokens
Output Tokens
$0.60/M
per million tokens
Alibabaenterprise
AI, cloud, and commerce powered by Qwen
2 Tools5 ModelsFounded 1999Hangzhou, China
View full profileTools by Alibaba
Other AI tools from the same organization.
AI Models by Alibaba
AI models from the same organization.
| Model | Context Window | Price (In / Out per M) |
|---|---|---|
| Qwen3.6 PlusCurrent | 1.0M | $0.33 / $1.95 |
| Qwen3.5-9BCurrent | 262K | $0.10 / $0.15 |
| Qwen3.5-35B-A3BCurrent | 262K | $0.16 / $1.30 |
| Qwen3.5-27BCurrent | 262K | $0.20 / $1.56 |
Related News
Latest coverage and updates.