Qwen3-VL-30B-A3B-Thinking is the reasoning-enhanced Thinking edition of the Qwen team's mid-size Qwen3-VL vision-language model, a Mixture-of-Experts model with about 30 billion total parameters and 3 billion active. It accepts text, image and video input and produces text output. It is built for STEM and math reasoning, visual question answering, OCR in 32 languages, video understanding and visual agent tasks.
Modalities
In / out price
$0.175 / $0.63per 1M
Cached price
$0.0263per 1M
Context
128K
Max output
4K
Providers
1 routeCompare providers by price, privacy, and speed.
Surplus Intelligence | Anonymous | $0.175 | $0.63 | $0.0263 | 128K | 4K | — | — |
Privacy
1 / 4Anonymous routing
Anonymous tier
- Anonymous
- Private
- TEE
- E2EE
Your identity is hidden from the inference provider. The inference provider can see prompt content; zero retention is not guaranteed. Learn more
Features
3Uptime
FAQ
Common questions about Qwen3 VL 30B A3B Thinking.