---
last_updated: 2026-11-21
source_url: https://opper.ai/alibaba/qwen3-vl-235b-a22b-instruct
title: "Qwen3 VL 235B A22B Instruct by Alibaba"
description: "Qwen3 VL 235B A22B Instruct by Alibaba, an open-weight vision-language model with 235B parameters, 22B active, and 131K context."
---

# Qwen3 VL 235B A22B Instruct

By [Alibaba](https://opper.ai/alibaba).

Released 23 Sep 2025 · [Announcement](https://github.com/QwenLM/Qwen3-VL) · [All Alibaba releases](https://opper.ai/model-releases/alibaba)

Qwen3 VL 235B A22B Instruct is the largest model in Alibaba's Qwen3 VL series, combining 235 billion parameters with mixture-of-experts efficiency (about 22B activated) for text, image, and video understanding. With a 131K context window, it handles long documents, video analysis, and full-page screenshots.

The model targets visual agent tasks, including PC and mobile GUI automation, code generation from design mockups, document parsing with 32-language OCR, and spatial reasoning. Its text understanding aligns closely with the pure Qwen3 235B language model, while architectural features such as Interleaved-MRoPE and DeepStack feature fusion integrate visual information.

It is well suited to computer vision agents, document processing pipelines, video analysis, and multimodal RAG. The open-weight release enables local deployment, fine-tuning, and integration into vision-based automation.

## Available routes

Qwen3 VL 235B A22B Instruct runs on 1 route through the Opper gateway. Prices are per 1M tokens. Its route also sells flex and priority processing: the same model at another price, picked per request with service_tier. [How service tiers work](https://docs.opper.ai/build/gateway/service-tiers). Its routes and prices, live from the catalogue, are public JSON with no API key needed at https://api.opper.ai/v3/models?q=deepinfra%2FQwen%2FQwen3-VL-235B-A22B-Instruct.

| Provider | Model id | Region | Zero data retention | Training | Input | Output | Cache read |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [DeepInfra](https://opper.ai/provider/deepinfra) | `deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct` | US (United States) | Yes | No | $0.20 | $0.88 | $0.11 |
| [DeepInfra](https://opper.ai/provider/deepinfra), Flex | `deepinfra:flex/Qwen/Qwen3-VL-235B-A22B-Instruct` | US (United States) | Yes | No | $0.16 | $0.70 | $0.09 |
| [DeepInfra](https://opper.ai/provider/deepinfra), Priority | `deepinfra:priority/Qwen/Qwen3-VL-235B-A22B-Instruct` | US (United States) | Yes | No | $0.30 | $1.32 | $0.17 |

## Key info

- Model id: `deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct`
- Input: Text, Image
- Output: Text
- Features: Tools, Structured output
- Context window: 262K
- Max output: 262K
- Input price: $0.20 per 1M tokens ($0.11 cache read)
- Output price: $0.88 per 1M tokens
- Released: 23 Sep 2025
- US residency available
- Zero data retention on pay-as-you-go
- No training by default

## Data handling per route

Each route hosting Qwen3 VL 235B A22B Instruct has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

### DeepInfra — United States

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs.

- Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
- Training: No training on customer data.
- Logging: None
- Abuse monitoring: No classifier
- Transfer mechanism: SCCs

Verified by Opper on 2026-10-19.

## Benchmarks

Independent benchmark scores via [Artificial Analysis](https://artificialanalysis.ai) ([view on AA](https://artificialanalysis.ai/models/qwen3-vl-235b-a22b-instruct)). Indices and domain scores are out of 100, Omniscience runs from −100 to 100, Briefcase is an Elo rating, and the other evaluation scores are the share of tasks solved.

- Global rank: #278 of 520 LLMs on the [LLM leaderboard](https://opper.ai/llm-leaderboard)
- Tier: Efficient
- Output speed: 36 tok/s
- Intelligence Index (previous version): 9.9

### Coding

- LiveCodeBench: 59%

### Agentic & knowledge work

- Terminal-Bench Hard: 7%
- τ²-Bench Telecom: 35%

### Science & reasoning

- Humanity's Last Exam: 7%
- GPQA Diamond: 71%
- Long-context reasoning: 33%

### Knowledge

- MMMU-Pro: 68%
- MMLU-Pro: 82%

### Math & instruction following

- AIME 2025: 71%
- IFBench: 43%

## Get started

Call Qwen3 VL 235B A22B Instruct through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Qwen3 VL 235B A22B Instruct is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

### Set it up with your agent

Paste this into a coding agent like Claude Code, Cursor or Codex and it will wire up Opper for you:

```text
Use curl to download, read and follow: https://skills.opper.ai Call Qwen3 VL 235B A22B Instruct
```

### Or call it directly

OpenAI:

```javascript
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-235B-A22B-Instruct",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);
```

Anthropic:

```javascript
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.OPPER_API_KEY,
  baseURL: "https://api.opper.ai/v3/compat",
});

const message = await client.messages.create({
  model: "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Hello" }],
});
console.log(message.content);
```

Gemini:

```javascript
import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
  apiKey: process.env.OPPER_API_KEY,
  httpOptions: { baseUrl: "https://api.opper.ai/v3/compat" },
});

const response = await ai.models.generateContent({
  model: "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct",
  contents: "Hello",
});
console.log(response.text);
```

cURL:

```bash
curl https://api.opper.ai/v3/compat/chat/completions \
  -H "Authorization: Bearer $OPPER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepinfra/Qwen/Qwen3-VL-235B-A22B-Instruct",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'
```

## Use Qwen3 VL 235B A22B Instruct in your apps

Pick your tool to see how to run it on Qwen3 VL 235B A22B Instruct through Opper.

- [Claude Code](https://opper.ai/apps/claude-code/qwen3-vl-235b-a22b-instruct)
- [Claude Cowork](https://opper.ai/apps/claude-cowork/qwen3-vl-235b-a22b-instruct)
- [Codex](https://opper.ai/apps/codex/qwen3-vl-235b-a22b-instruct)
- [DeepSeek Harness](https://opper.ai/apps/deepseek-harness/qwen3-vl-235b-a22b-instruct)
- [GitHub Copilot CLI](https://opper.ai/apps/github-copilot-cli/qwen3-vl-235b-a22b-instruct)
- [Aider](https://opper.ai/apps/aider/qwen3-vl-235b-a22b-instruct)
- [Goose](https://opper.ai/apps/goose/qwen3-vl-235b-a22b-instruct)
- [Droid](https://opper.ai/apps/droid/qwen3-vl-235b-a22b-instruct)
- [OpenCode](https://opper.ai/apps/opencode/qwen3-vl-235b-a22b-instruct)
- [Pi](https://opper.ai/apps/pi/qwen3-vl-235b-a22b-instruct)
- [OpenClaw](https://opper.ai/apps/openclaw/qwen3-vl-235b-a22b-instruct)
- [Hermes](https://opper.ai/apps/hermes/qwen3-vl-235b-a22b-instruct)
- [Copilot for Obsidian](https://opper.ai/apps/obsidian-copilot/qwen3-vl-235b-a22b-instruct)
- [OmniRoute](https://opper.ai/apps/omniroute/qwen3-vl-235b-a22b-instruct)
- [Cursor](https://opper.ai/apps/cursor/qwen3-vl-235b-a22b-instruct)
- [Cline](https://opper.ai/apps/cline/qwen3-vl-235b-a22b-instruct)
- [Continue](https://opper.ai/apps/continue/qwen3-vl-235b-a22b-instruct)
- [Kilo Code](https://opper.ai/apps/kilo-code/qwen3-vl-235b-a22b-instruct)
- [GitHub Copilot](https://opper.ai/apps/github-copilot/qwen3-vl-235b-a22b-instruct)
- [Zed](https://opper.ai/apps/zed/qwen3-vl-235b-a22b-instruct)
- [JetBrains AI Assistant](https://opper.ai/apps/jetbrains-ai-assistant/qwen3-vl-235b-a22b-instruct)
- [Voidleap Code](https://opper.ai/apps/voidleap-code/qwen3-vl-235b-a22b-instruct)
- [n8n](https://opper.ai/apps/n8n/qwen3-vl-235b-a22b-instruct)
- [LibreChat](https://opper.ai/apps/librechat/qwen3-vl-235b-a22b-instruct)
- [Open WebUI](https://opper.ai/apps/open-webui/qwen3-vl-235b-a22b-instruct)
- [See all apps](https://opper.ai/apps)

## Other models from Alibaba

- [Qwen4-Max](https://opper.ai/alibaba/qwen4-max)
- [Qwen3.8 Max](https://opper.ai/alibaba/qwen3-8-max)
- [Qwen3.8 27B](https://opper.ai/alibaba/qwen3-8-27b)
- [Qwen3.8-2.4T-A95B](https://opper.ai/alibaba/qwen3-8-2-4t-a95b)
- [Qwen3.8 Flash-Next](https://opper.ai/alibaba/qwen3-8-flash-next)
- [Qwen3.7-Max](https://opper.ai/alibaba/qwen3-7-max)
