ZMIME
Alibaba (Qwen) · Released Oct 4, 2025

Qwen3 VL 30B A3B Instruct

Open vision-language MoE model for image and video understanding, documents, and visual agents.

  • Open weights
  • Tool calling
  • Vision
  • Video input
Capability
—No ECI score yet
Input
$0.15per 1M tokens
Output
$0.60per 1M tokens
Context
262K33K max output
Pricing

What it costs

Input
$0.15per million tokens
Output
$0.60per million tokens
Blended (3:1)
$0.263cheaper than 72% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.60
Team assistant25M input + 5M output tokens$6.75
Production app250M input + 50M output tokens$67.50

Median of 13 paid API providers on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for Qwen3 VL 30B A3B Instruct yet.

Specifications

The details

Lab
Alibaba (Qwen)
Released
Oct 4, 2025
Context window
262,144 tokens
Max output
32,768 tokens
Inputs
Text, Images, Video
Output
Text
Reasoning
No
Tool calling
Yes
Structured output
No
Availability
13 API providerslisted on models.dev
Same lab

More from Alibaba (Qwen)

Questions

About Qwen3 VL 30B A3B Instruct

How much does Qwen3 VL 30B A3B Instruct cost?

Qwen3 VL 30B A3B Instruct costs $0.15 input / $0.60 output per million tokens (median across 13 API providers). At a 3:1 input-to-output mix that is $0.263 per million tokens, cheaper than 72% of the 445 priced models we track.

What is the context window of Qwen3 VL 30B A3B Instruct?

Qwen3 VL 30B A3B Instruct accepts up to 262,144 tokens per request and can write up to 32,768 tokens in one response.

How good is Qwen3 VL 30B A3B Instruct?

Epoch AI has not published a Capabilities Index score for Qwen3 VL 30B A3B Instruct yet.

Is Qwen3 VL 30B A3B Instruct open source?

Yes. Alibaba (Qwen) publishes the weights under the Apache-2.0 licence, so it can be downloaded and self-hosted.

What inputs does Qwen3 VL 30B A3B Instruct support?

Qwen3 VL 30B A3B Instruct accepts text, images and video and replies in text. It is not a dedicated reasoning model, supports tool calling.

When was Qwen3 VL 30B A3B Instruct released?

Alibaba (Qwen) released Qwen3 VL 30B A3B Instruct on Oct 4, 2025.

What are the best alternatives to Qwen3 VL 30B A3B Instruct?

The closest current models from other labs on capability, price and release date are Grok 4.1 Fast (xAI, $0.20 / $0.50), Nemotron Nano 12B v2 VL (NVIDIA, $0.20 / $0.60), GLM-4.6V-Flash (Z.ai (Zhipu), $0.161 / $0.559) and Jamba Mini (AI21 Labs, $0.20 / $0.40).