Qwen

Qwen3-VL 30B-A3B

CTX131K

Reasoning · Vision · Tools

Input$0.20/M

Output$0.80/M

Qwen vision-language model for visual reasoning, documents, and agent tasks

Open weightsApache 2.0530/1044

Drag to turn

QwenTextCommon

Qwen3-VL 30B-A3B

Qwen vision-language model for visual reasoning, documents, and agent tasks

qwen3-vl-30b-a3b

Type: Text
Quality: Not rated yet
Context window: 131,072 tokens
Max output: 32,768 tokens
Input price: $0.20 / 1M tokens
Output price: $0.80 / 1M tokens
Cache read: —
Cache write: —
Parameters: 31B (31,070,754,032)
Downloads: 250K in the last 30 days
Likes: 620
Access to weights: Open download
Released: Apr 1, 2025
Knowledge cutoff: Apr 2025
Takes in: Text, Image
Puts out: Text
Reasoning: Yes
Tool calling: Yes
Structured output: No
File attachments: No
Access: Open weights
License: Apache 2.0
Rarity: Common
Set number: 530/1044

Open Qwen docs Weights on Hugging Face Where to run it 17 Evolution 3/3 Race it 37 tok/s Meet its creature Battle Trinity Large Thinking

License read from the model’s Hugging Face card. Specs from models.dev, downloads from Hugging Face, last changed Oct 19, 2026. Official source: www.alibabacloud.com.

How good is it?

Public leaderboard scores for Qwen3-VL 30B-A3B, refreshed daily from Epoch AI and LMArena.

No public leaderboard lists Qwen3-VL 30B-A3B yet. Epoch AI and LMArena cover most chat, image, and video models from the big labs; embeddings, speech, and small open models mostly go unrated.

Where to run it

14 providers sell Qwen3-VL 30B-A3B through an API, and 3 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

CheapestAlibaba (China)$0.11 in · $0.43 out
From the labAlibaba$0.20 in · $0.80 out
Fastest on Hugging FaceNovita37 tokens/s

API providers

Provider	Input	Output	Context
Alibaba (China)Cheapest paid`qwen3-vl-30b-a3b`	$0.11	$0.43	131K
NEAR AI Cloud`Qwen/Qwen3-VL-30B-A3B-Instruct`	$0.15	$0.55	16K
Deep Infra`Qwen/Qwen3-VL-30B-A3B-Instruct`	$0.15	$0.60	262K
DevPass (LLM Gateway)`qwen3-vl-30b-a3b-instruct`	$0.15	$0.60	262K
Eden AI`deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct`	$0.15	$0.60	262K
Kilo Gateway`qwen/qwen3-vl-30b-a3b-instruct`	$0.15	$0.60	262K
LLM Gateway`deepinfra/qwen3-vl-30b-a3b-instruct`	$0.15	$0.60	262K
Merge Gateway`qwen/qwen3-vl-30b-a3b-instruct`	$0.15	$0.60	131K
OpenRouter`qwen/qwen3-vl-30b-a3b-instruct`	$0.15	$0.60	262K
Novita AI`qwen/qwen3-vl-30b-a3b-instruct`	$0.20	$0.70	131K

Show 4 more providers

Provider	Input	Output	Context
Prime Inference`qwen/qwen3-vl-30b-a3b-instruct`	$0.20	$0.70	262K
AlibabaOfficial`qwen3-vl-30b-a3b`	$0.20	$0.80	131K
SiliconFlow`Qwen/Qwen3-VL-30B-A3B-Instruct`	$0.29	$1.00	262K
SiliconFlow (China)`Qwen/Qwen3-VL-30B-A3B-Instruct`	$0.29	$1.00	262K

Hugging Face Inference Providers

Host	Input	Output	Context	Speed	First token
DeepInfraTools	$0.15	$0.60	262K	16 tok/s	0.3s
NovitaFastestTools	$0.20	$0.70	131K	37 tok/s	0.9s
Featherless	—	—	—	—	—

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

Face off

Current text models from other labs at a similar output price.

Qwen3-VL 30B-A3B

Qwen3-VL 30B-A3B

How good is it?

Where to run it

API providers

Hugging Face Inference Providers

Face off

More from Qwen

Qwen-Image-2.1-Turbo

Qwen3.8 Omni Flash

Qwen-Image-2.1

Qwen3.8 Flash

Qwen3.8-Flash-Next

Qwen3.8-2.4T-A95B

Qwen3.8-27B

Qwen3.8 Max