Qwen 3 VL 235B A22B Instruct
Qwen 3 VL 235B A22B Instruct is Alibaba Cloud's 235B mixture-of-experts vision-language model with 22B active parameters per token, supporting interleaved text, images, and video over a context window of 262.1K tokens for visual coding, spatial perception, and fine-grained visual understanding.
View API reference- Input and output price
- Prices from: Input $0.20, Output $0.88, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Qwen 3 VL 235B A22B Instruct by Alibaba Cloud. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Qwen 3 VL 235B A22B Instruct
Qwen 3 VL 235B A22B Instruct
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Qwen 3 VL 235B A22B Instruct through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Qwen 3 VL 235B A22B Instruct request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, temperature: 0.5, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. alibaba/qwen3-vl-235b-a22b-instruct. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Qwen 3 VL 235B A22B Instruct supports up to 262,144 output tokens. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 262K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK alibaba provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['deepinfra', 'alibaba'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Tool calling
Expose tools the model can call. Define each tool’s inputs with a Zod schema.
import { generateText, tool } from 'ai';import { z } from 'zod';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'alibaba/qwen3-vl-235b-a22b-instruct', prompt: 'What is the weather in San Francisco?', tools: { getWeather: tool({ description: 'Get the current weather for a location', inputSchema: z.object({ location: z.string() }), execute: async ({ location }) => ({ location, temperatureC: 18 }), }), }, });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Alibaba Cloud
| Model |
|---|
| 991K | 4.6 s | 51 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +2 | | 09/01/2026 | |||||
| 991K | 1.2 s | 84 tps | $0.16/M | $0.47/M | Read$0.02/M Write$0.20/M | — | +2 | | 08/26/2026 | |||||
| 1M | 0.6 s | 154 tps | $0.10/M | $0.40/M | Read$0.01/M Write$0.63/M | — | +1 |   +3 | 08/14/2026 | |||||
| 1M | 2.6 s | 153 tps | $2/M | $6/M | Read$0.25/M Write$2.50/M | — | +1 |  | 08/02/2026 | |||||
| 991K | 1.8 s | 133 tps | $0.03/M+2 more | $0.13/M+2 more | Read$0.006/M Write$0.04/M | — | +2 | | 07/28/2026 | |||||
| 1M | 1.9 s | 58 tps | $0.40/M+1 more | $1.60/M+1 more | Read$0.08/M Write$0.50/M | — | +2 | | 06/02/2026 |
Copy link to headingAbout Qwen 3 VL 235B A22B Instruct
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.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: 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.
- Zero Data Retention: Zero Data Retention is available for this model. It is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Qwen 3 VL 235B A22B Instruct
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 when
- 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
Copy link to headingConclusion
Qwen 3 VL 235B A22B Instruct is the pinned 235B-A22B instruct release in the Qwen3 vision-language line, suited to production multimodal workloads that need strong visual perception, spatial reasoning, and direct instruction following. Routing through AI Gateway gives you provider failover, unified billing, and a consistent integration surface across the Qwen3-VL family.
Copy link to headingFrequently 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.
Your use is subject to Alibaba Cloud's Terms & Privacy Policies.