# Alibaba Qwen3 VL 235B A22B Instruct API

> Qwen3-VL 235B A22B Instruct is the largest Mixture-of-Experts model in Alibaba's open-weight Qwen3-VL vision-language family, in its non-thinking Instruct edition, released in September 2025. Qwen positions it for visual agents that operate PC and mobile GUIs, generating HTML, CSS or diagrams from images and video, 2D and 3D grounding, long-video understanding and OCR in 32 languages. Choose it for direct answers; a separate Thinking edition targets multimodal STEM reasoning.

Source: https://www.sandbase.ai/model/alibaba/qwen3-vl-235b-a22b-instruct
API reference: https://www.sandbase.ai/model/alibaba/qwen3-vl-235b-a22b-instruct/docs

## Facts

- Provider: Alibaba
- Type: Language model
- Model ID: `alibaba/qwen3-vl-235b-a22b-instruct`
- Price: $0.40 per 1M input tokens, $1.60 per 1M output tokens
- Context window: 131.1K tokens, up to 16.4K output tokens
- Capabilities: chat, vision, structured output, function calling
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

- Chat Completions API: `POST https://api.sandbase.ai/v1/chat/completions`

```bash
curl -X POST https://api.sandbase.ai/v1/chat/completions \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/qwen3-vl-235b-a22b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}'
```

## FAQ

### How do I call Alibaba Qwen3 VL 235B A22B Instruct through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/qwen3-vl-235b-a22b-instruct" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.

### How much does Alibaba Qwen3 VL 235B A22B Instruct cost?

$0.40 per 1M input tokens and $1.60 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.

### What is the context window of Alibaba Qwen3 VL 235B A22B Instruct?

131.1K tokens of context, with up to 16.4K output tokens per response.

### How does Alibaba Qwen3 VL 235B A22B Instruct score on benchmarks?

Alibaba Qwen3 VL 235B A22B Instruct scores 9.9 on the Artificial Analysis Intelligence Index (v4.3), ranking #74 of 83 models on SandBase. Source: Artificial Analysis, measured as Qwen3 VL 235B A22B Instruct.

### Which features does Alibaba Qwen3 VL 235B A22B Instruct support?

Alibaba Qwen3 VL 235B A22B Instruct supports vision (image input), function calling, structured output. See Specifications above for the full list.

### Do I need a separate Alibaba account?

No. One SandBase API key and balance gives you access to Alibaba Qwen3 VL 235B A22B Instruct and the other models in the catalog; you do not need to sign up with Alibaba separately.