# Qwen 3 VL 235B A22B Instruct

Qwen 3 VL 235B A22B Instruct is the version-pinned instruct release of the Qwen3-VL 235B-A22B vision-language model, built to handle interleaved text, images, and video for visual coding, spatial perception, and detailed multimodal understanding.

- **Model ID:** `alibaba/qwen3-vl-235b-a22b-instruct`
- **Type:** chat
- **Providers:** deepinfra
- **Context window:** 262,144
- **Maximum output tokens:** 262,144
- **Pricing:** $0.2/1M input tokens, $0.88/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/qwen3-vl-235b-a22b-instruct

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'alibaba/qwen3-vl-235b-a22b-instruct',
  prompt: 'Why is the sky blue?'
})
```

## About

Qwen 3 VL 235B A22B Instruct is the September 23, 2025 version of Alibaba Cloud's 235B-A22B vision-language model in instruct configuration. Built on a mixture-of-experts (MoE) architecture, it carries 235 billion total parameters with approximately 22 billion active per token, and serves a context window of 262.1K tokens for interleaved sequences of text, images, and video frames.

Compared with prior Qwen vision-language generations, the Qwen3 VL series brings improvements across visual coding, spatial perception, and fine-grained visual understanding. Qwen 3 VL 235B A22B Instruct parses charts, diagrams, GUI screenshots, and document images with stronger grounding, and can identify and reason about object positions and relationships within complex scenes.

The instruct configuration is tuned for direct instruction following rather than extended chain-of-thought, which makes Qwen 3 VL 235B A22B Instruct a practical default for production multimodal workloads: document intelligence, screen-reading agents, multi-image analysis, and visual coding pipelines that need fast, structured responses. You can integrate Qwen 3 VL 235B A22B Instruct through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python, with a maximum output of 262.1K tokens per request.

## What to consider

Multimodal payloads that combine large images or video frames consume meaningful context tokens. Profile your typical request shape against the context window of 262.1K tokens and confirm your provider's serving infrastructure handles your throughput target before routing production traffic.

## When to use

### Best For

- Visual coding pipelines that turn screenshots, mockups, or diagrams into code or component output
- Document intelligence over scanned pages, tables, and figures where fine-grained visual perception matters
- Screen-reading and GUI automation agents that interpret application screenshots to plan and execute actions
- Multi-image analysis workflows that compare charts, product photos, or document figures side by side
- Multimodal applications that benefit from a single context window of 262.1K tokens for combined text, image, and video inputs

### Consider Alternatives When

- Tasks require visible step-by-step reasoning traces over visual input, in which case Qwen3-VL-Thinking is a closer match
- Workloads are text-only and never use vision, where a dedicated text model offers lower cost per token
- Latency-sensitive basic instruction following can be served by a smaller multimodal model
- Video or image generation is needed instead of understanding, which requires a generation-class model

## Best for

- **Visual Coding Pipelines:** Turning screenshots, mockups, or diagrams into accurate component or function output
- **Document Intelligence Tasks:** Scanned pages, tables, and figures that need fine-grained visual perception
- **Screen-Reading Agents:** Interpreting GUI screenshots to plan and execute UI actions
- **Multi-Image Comparative Analysis:** Charts, product photos, or document figures reviewed side by side in a single request
- **Unified Multimodal Context:** Combined text, image, and video inputs handled within the window of 262.1K tokens

## Consider alternatives

- **Visible Reasoning Required:** Qwen3-VL-Thinking is a closer match when tasks need step-by-step visual reasoning traces
- **Text-Only Workloads:** A dedicated text model offers lower cost per token when vision is never used
- **Latency-Critical Basic Tasks:** A smaller multimodal model can serve simple instruction following at lower cost
- **Image Or Video Generation:** A generation-class model fits tasks that produce pixels rather than read them

## Frequently asked questions

### What modalities does Qwen 3 VL 235B A22B Instruct accept?

The model accepts interleaved text, images, and video frames within a single context window of up to 262.1K tokens, with output up to 262.1K tokens tokens per request.

### How is Qwen 3 VL 235B A22B Instruct different from Qwen3-VL-Thinking?

The instruct variant produces direct, structured answers and is generally faster and cheaper to run. Qwen 3 VL 235B A22B Instruct is tuned for instruction following without extended reasoning traces, while Qwen3-VL-Thinking emits a visible chain-of-thought before its final response and is better suited to complex visual STEM and compositional reasoning.

### What does the 235B-A22B notation mean?

Qwen 3 VL 235B A22B Instruct is a mixture-of-experts model with 235 billion total parameters, of which approximately 22 billion activate per token. This design keeps the active compute close to a 22B dense model while preserving the capability profile of a much larger network.

### Which API surfaces work with Qwen 3 VL 235B A22B Instruct on AI Gateway?

You can call Qwen 3 VL 235B A22B Instruct through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python. Reference ``alibaba/qwen3-vl-235b-a22b-instruct`` as the model identifier in your request.

### What is the context window for Qwen 3 VL 235B A22B Instruct?

The context window is 262.1K tokens, which applies to the combined sequence of text tokens and visual tokens (image patches and video frames encoded as tokens) in an interleaved request.

### Does Qwen 3 VL 235B A22B Instruct support zero data retention?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

### Where can I see live latency and cost data for Qwen 3 VL 235B A22B Instruct?

This page shows live throughput, time-to-first-token, and pricing metrics for Qwen 3 VL 235B A22B Instruct measured across real AI Gateway traffic.

## Links

- [Model page](https://vercel.com/ai-gateway/models/qwen3-vl-235b-a22b-instruct)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://deepinfra.com/Qwen/Qwen3-VL-235B-A22B-Instruct)