by Alibaba (Qwen Team)

Qwen: Qwen3 VL 30B A3B Thinking.

multimodal open weights laptop+ 30B params 131K ctx
Cheapest input
$0.13/M
on Alibaba DashScope
Cheapest output
$1.56/M
on Alibaba DashScope
Smallest GPU
1× Nvidia RTX 4000 Ada

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM, math, and complex tasks. It excels...

Smallest GPU to run it See all quantisations →

1× Nvidia RTX 4000 Ada.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Alibaba DashScope api direct $0.13 $1.56 Launch ↗
OpenRouter api aggregator $0.13 $1.56 Launch ↗
FAQ

Frequently asked.

How do I run Qwen: Qwen3 VL 30B A3B Thinking?
Qwen: Qwen3 VL 30B A3B Thinking is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Qwen: Qwen3 VL 30B A3B Thinking?
Qwen: Qwen3 VL 30B A3B Thinking is available via Alibaba DashScope, OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Qwen: Qwen3 VL 30B A3B Thinking?
API pricing starts at $0.13/M input tokens and $1.56/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Qwen: Qwen3 VL 30B A3B Thinking open-source or proprietary?
Qwen: Qwen3 VL 30B A3B Thinking is open-weight under the license. You can download and self-host it.