Qwen3 VL 30B A3B Instruct

by Alibaba

Qwen3 VL 30B A3B Instruct is an open-weight mixture-of-experts vision-language model that balances capability with efficiency through roughly 3B active parameters from a 30B base. With a 131K context window, it handles long documents, video understanding, and visual agent tasks. The model targets visual agent functions for PC and mobile GUI automation, code generation from images and video, OCR in 32 languages, and spatial perception for object positioning and viewpoint understanding. It fuses text and vision for multimodal comprehension alongside STEM reasoning. It is designed for cost-efficient deployment of visual agents, document processing pipelines, and multimodal RAG where lower latency and a smaller memory footprint matter relative to the 235B variant. The open-weight release supports local deployment, fine-tuning for specialized visual domains, and integration into automation loops.

Key info

Input
Output
Features
Context window
262K
Max output
262K
Input price
$0.15 /1M
Output price
$0.60 /1M
  • US residency available
  • Zero data retention via Enterprise
  • No training by default
  • GDPR DPA available

Available routes

Qwen3 VL 30B A3B Instruct runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
DeepInfraUSEnterpriseNo$0.15$0.60
NovitaUSEnterpriseNo$0.20$0.70

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Qwen3 VL 30B A3B Instruct has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Limited debug logs
Third-party access
None disclosed
GDPR DPA
No DPA
Transfer mechanism
unknown

Novita β€” United StatesπŸ‡ΊπŸ‡Έ

Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
SCCs

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#319 of 531 LLMs
TierEfficient
Output speed125 tok/s
First token1.07s
Intelligence Index10.0
Coding Index14.3
Math Index72.3
Reasoning & knowledge
MMLU-Pro
76%
GPQA Diamond
70%
Humanity's Last Exam
6%
Long-context reasoning
24%
Coding
LiveCodeBench
48%
SciCode
31%
Agentic & tool use
Terminal-Bench Hard
6%
τ²-Bench Telecom
19%
Math & instruction following
AIME 2025
72%
IFBench
33%

Get started

Call Qwen3 VL 30B A3B Instruct through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "deepinfra/Qwen/Qwen3-VL-30B-A3B-Instruct",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Qwen3 VL 30B A3B Instruct with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Alibaba

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Qwen3 VL 30B A3B Instruct by Alibaba β€” pricing, benchmarks | Opper AI