Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

Model basics

Reasoning traces

Not supported

Context length

256K tokens

Max output length

32768 tokens

Model type

多模态大模型

Release date

2025-09-23

Model file size

470GB

MoE architecture

Yes

Total params / Active params

2350.0B / 220B

Knowledge cutoff

No data

Inference modes

常规模式（Non-Thinking Mode）

Open source & experience

Code license

Apache 2.0

Weights license

Apache 2.0- 免费商用授权

GitHub repo

https://github.com/QwenLM/Qwen3-VL

Hugging Face

https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct

Live demo

https://chat.qwen.ai/

Official resources

Paper

Qwen3-VL: Sharper Vision, Deeper Thought, Broader Action

DataLearnerAI blog

No blog post yet

API details

API speed

3/5

💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.

Standard pricingStandard

Modality	Input	Output
Text	$0.6	$4.8
Image	$0.6	--

Benchmark Scores

数学推理

1 evaluations

Benchmark / mode

Score

Rank/total

IMO-ProofBenchnormal

5.20

14 / 16

Publisher

阿里巴巴

View publisher details

Model Overview

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送