QwenReleased on Sep 22, 2025

Qwen3 VL 4B Instruct: Benchmarks, Pricing & Size

Qwen3 VL 4B Instruct is a language model from Qwen, released in September 2025, with multimodal input.

Qwen3-VL is a large multimodal model that unifies vision, language, and reasoning to achieve human-level perception and cognition across text, images, and video. Built on a 235B-parameter architecture, it integrates early joint training of

Input
TextImage
Output
Text
Speed
Latency p956.92s
Throughput P9548.7char/s
Cost
$0.16/ 1M · 8:1 in:out
$0.10 in · $0.60 out

Qwen3 VL 4B Instruct pricing

Providers

Qwen3 VL 4B Instruct starts at $0.100 per million input tokens and $0.600 per million output tokens via DeepInfra.

ProviderInput $/MOutput $/MMax InputMax OutputLatency p95 sThroughput P95QuantInputOutput
DeepInfra logoDeepInfra
$0.100$0.600262.1K262.1K
6.92
49 c/s
fp8

Qwen3 VL 4B Instruct model size

Qwen3 VL 4B Instruct has 4 billion parameters. See how it compares to other models in the same parameter range.

Parameters
4B
Small (3–10B)
4B
1B7B70B405B

Qwen3 VL 4B Instruct API

API access coming soon

Qwen3 VL 4B Instruct will be available through our gateway shortly.

Qwen3 VL 4B Instruct examples

Recent arena outputs from Qwen3 VL 4B Instruct, picked from the highest-ranked matchups.

Qwen3 VL 4B Instruct license

Qwen3 VL 4B Instruct is released under the Apache 2.0 license, which permits commercial use, has 4.0B parameters.

License
Apache 2.0
Commercial use allowed
Parameters
4.0B

Apache License 2.0 - allows commercial use

FAQ

Common questions about Qwen3 VL 4B Instruct.

When was Qwen3 VL 4B Instruct released?

Qwen3 VL 4B Instruct was released on September 22, 2025 by Qwen. This is the official Qwen3 VL 4B Instruct release date tracked on LLM Stats.

Is Qwen3 VL 4B Instruct available via API?

Yes, Qwen3 VL 4B Instruct is available via API. See the official documentation for authentication and endpoint details. It is served by 1 provider tracked on LLM Stats.

How big is Qwen3 VL 4B Instruct?

Qwen3 VL 4B Instruct has 4 billion parameters. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Qwen3 VL 4B Instruct?

Qwen3 VL 4B Instruct was created by Qwen.

What is the license for Qwen3 VL 4B Instruct?

Qwen3 VL 4B Instruct is released under the Apache 2.0 license. This is an open-source / open-weight license that permits self-hosting.

Is Qwen3 VL 4B Instruct multimodal?

Yes, Qwen3 VL 4B Instruct is multimodal and can accept both text and images as input.

Where can I use Qwen3 VL 4B Instruct?

Qwen3 VL 4B Instruct is available through 1 provider including DeepInfra.

Where is the Qwen3 VL 4B Instruct paper or technical report?

Qwen3 VL 4B Instruct has a paper or technical report available at https://qwen.ai/blog?id=99f0335c4ad9ff6153e517418d48535ab6d8afef&from=research.latest-advancements-list. Use that source for architecture, training, release and evaluation details.