# Alibaba Qwen2.5 VL 72B Instruct API

> Qwen2.5-VL 72B Instruct is the largest instruction-tuned model in Alibaba's open-weight Qwen2.5-VL vision-language family, released in early 2025. Qwen highlights recognition of common objects and analysis of text, charts, icons and layouts in images, visual localization with bounding boxes or points, structured extraction from invoices, forms and tables, visual agent use and understanding of videos over an hour long. It predates the Qwen3-VL line and suits workloads validated on it.

Source: https://www.sandbase.ai/model/alibaba/qwen2.5-vl-72b-instruct
API reference: https://www.sandbase.ai/model/alibaba/qwen2.5-vl-72b-instruct/docs

## Facts

- Provider: Alibaba
- Type: Language model
- Model ID: `alibaba/qwen2.5-vl-72b-instruct`
- Price: $0.25 per 1M input tokens, $0.75 per 1M output tokens
- Context window: 128K tokens, up to 131.1K output tokens
- Capabilities: chat, vision, structured output
- 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/qwen2.5-vl-72b-instruct",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ],
  "max_tokens": 2048
}'
```

## FAQ

### How do I call Alibaba Qwen2.5 VL 72B Instruct through SandBase?

Create a SandBase API key, then send requests with the model ID "alibaba/qwen2.5-vl-72b-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 Qwen2.5 VL 72B Instruct cost?

$0.25 per 1M input tokens and $0.75 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 Qwen2.5 VL 72B Instruct?

128K tokens of context, with up to 131.1K output tokens per response.

### Which features does Alibaba Qwen2.5 VL 72B Instruct support?

Alibaba Qwen2.5 VL 72B Instruct supports vision (image input), 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 Qwen2.5 VL 72B Instruct and the other models in the catalog; you do not need to sign up with Alibaba separately.