[Integrations](https://spiral.ai/integrations) › [opencode](https://spiral.ai/integrations/opencode) › [Qwen2.5-VL 72B Instruct](https://spiral.ai/integrations/opencode/qwen2-5-vl-72b-instruct)

# How to Use Qwen2.5-VL 72B Instruct in opencode

Use Qwen2.5-VL 72B Instruct to extract data from scanned documents and explain charts. It can also locate objects with bounding boxes or points, making it useful when an answer needs a position in the image.

|  |  |
| --- | --- |
| Model | Qwen2.5-VL 72B Instruct |
| Available through | OpenRouter |
| Category | LLM |
| Price | Up to $0.005362 per run at the default inputs. $1.04 per 1M input tokens, $1.30 per 1M output tokens. |
| Returns | text, json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Qwen2.5-VL 72B Instruct in opencode

- Use Qwen2.5-VL 72B Instruct to inspect the screenshots in this project's visual tests. Label the reference Image A and the current render Image B, list visible layout differences, then find the components responsible.
- Use Qwen2.5-VL 72B Instruct to extract the invoice images in the test fixtures into JSON records. Follow the project's existing invoice schema and use null for unreadable values.
- Use Qwen2.5-VL 72B Instruct to read the chart screenshot in the issue. List its title, axis labels, legend, and visible values, then compare them with the chart configuration in the project.
- Use Qwen2.5-VL 72B Instruct to locate the Save button in the failing test screenshot. Return a labeled bounding box, then inspect the related test and component before proposing a fix.
- Use Qwen2.5-VL 72B Instruct to inspect the object-counting fixture. Locate every visible bottle first, report the total, and compare the result with the expected annotation.

## How to set up Qwen2.5-VL 72B Instruct in opencode

Pick the way that suits you. Each takes about two minutes.

### Use Spiral's MCP server

1. **Add the server**: Leave out `--global` to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

```bash
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
```

2. **Sign in**: Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, `/mcps` starts the same sign-in.

```bash
opencode mcp auth spiral
```

3. **Check it**: Spiral shows as connected.

```bash
opencode mcp list
```

### Use the Spiral skill

1. **Send opencode this message**: Your agent reads Spiral's skill and sets itself up.

```
set up https://spiral.ai/SKILL.md
```

2. **Sign in or paste a key**: Approve Spiral in the browser, or give the agent a key from the console.

### Use the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run Qwen2.5-VL 72B Instruct**: One request; the result comes back by polling or a webhook.

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "openrouter",
    "model": "qwen/qwen2.5-vl-72b-instruct",
    "input": {
      "messages": [
        {
          "role": "system"
        }
      ]
    }
  }'
```

Then paste one of the prompts above: opencode finds Qwen2.5-VL 72B Instruct on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/opencode

## Qwen2.5-VL 72B Instruct tools and prices

- [Qwen: Qwen2.5 VL 72B Instruct](https://spiral.ai/tools/openrouter/qwen/qwen2.5-vl-72b-instruct) (OpenRouter): Up to $0.005362 per run at the default inputs. $1.04 per 1M input tokens, $1.30 per 1M output tokens.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — |  |
| stop |  | — |  |
| top_k | 0 to … | — |  |
| top_p | 0 to 1 | — |  |
| logprobs |  | — |  |
| max_tokens | 1 to 115200 | — | The most output tokens to generate. |

## What can you do with Qwen2.5-VL 72B Instruct in opencode?

Turn screenshots and document images into evidence for code changes with Qwen2.5-VL. Ask your coding agent to connect visible labels, layouts, or extracted records to the relevant project files.

### Invoice extraction

Turn invoice images into records containing the supplier, invoice number, date, line items, and total. Mark unreadable values for review.

### Form transcription

Extract printed labels and completed entries from form images into a consistent table.

### Chart explanations

Read chart titles, axes, legends, and visible values, then explain the comparison in plain English.

### Screenshot review

Inspect interface screenshots for visible labels, layout differences, and the locations of named controls.

### Multilingual text collection

Transcribe signs or document images in languages covered by Qwen's OCR training, preserving the original script.

### Object annotation

Locate specified objects in images and return labeled bounding boxes or points for review.

### Visual counting

Identify each visible instance of a requested object before returning a count and locations that a reviewer can inspect.

## Overview

- [OpenRouter](https://spiral.ai/providers/openrouter)
- [All opencode guides](https://spiral.ai/integrations/opencode)

## Qwen2.5-VL 72B Instruct in other agents

- [Amp](https://spiral.ai/integrations/amp/qwen2-5-vl-72b-instruct)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/qwen2-5-vl-72b-instruct)
- [Claude](https://spiral.ai/integrations/claude-desktop/qwen2-5-vl-72b-instruct)
- [Claude Code](https://spiral.ai/integrations/claude-code/qwen2-5-vl-72b-instruct)
- [Cline](https://spiral.ai/integrations/cline/qwen2-5-vl-72b-instruct)
- [Codex](https://spiral.ai/integrations/codex/qwen2-5-vl-72b-instruct)
- [Cursor](https://spiral.ai/integrations/cursor/qwen2-5-vl-72b-instruct)
- [Devin](https://spiral.ai/integrations/devin/qwen2-5-vl-72b-instruct)
- [dots](https://spiral.ai/integrations/dots/qwen2-5-vl-72b-instruct)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/qwen2-5-vl-72b-instruct)
- [Gemini](https://spiral.ai/integrations/gemini/qwen2-5-vl-72b-instruct)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/qwen2-5-vl-72b-instruct)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/qwen2-5-vl-72b-instruct)
- [goose](https://spiral.ai/integrations/goose/qwen2-5-vl-72b-instruct)
- [Grok](https://spiral.ai/integrations/grok/qwen2-5-vl-72b-instruct)
- [Grok Build](https://spiral.ai/integrations/grok-build/qwen2-5-vl-72b-instruct)
- [Hermes](https://spiral.ai/integrations/hermes/qwen2-5-vl-72b-instruct)
- [Instinct](https://spiral.ai/integrations/instinct/qwen2-5-vl-72b-instruct)
- [Manus](https://spiral.ai/integrations/manus/qwen2-5-vl-72b-instruct)
- [Muse](https://spiral.ai/integrations/muse/qwen2-5-vl-72b-instruct)
- [Muse Code](https://spiral.ai/integrations/muse-code/qwen2-5-vl-72b-instruct)
- [n8n](https://spiral.ai/integrations/n8n/qwen2-5-vl-72b-instruct)
- [Notion](https://spiral.ai/integrations/notion/qwen2-5-vl-72b-instruct)
- [OpenClaw](https://spiral.ai/integrations/openclaw/qwen2-5-vl-72b-instruct)
- [Perplexity](https://spiral.ai/integrations/perplexity/qwen2-5-vl-72b-instruct)
- [Raycast](https://spiral.ai/integrations/raycast/qwen2-5-vl-72b-instruct)
- [VS Code](https://spiral.ai/integrations/vscode/qwen2-5-vl-72b-instruct)
- [Windsurf](https://spiral.ai/integrations/windsurf/qwen2-5-vl-72b-instruct)
- [Zapier](https://spiral.ai/integrations/zapier/qwen2-5-vl-72b-instruct)

## More opencode guides

- [Qwen2.5 Coder 32B Instruct](https://spiral.ai/integrations/opencode/qwen2-5-coder-32b-instruct)
- [Qwen3 14B](https://spiral.ai/integrations/opencode/qwen3-14b)
- [Qwen2.5 72B Instruct](https://spiral.ai/integrations/opencode/qwen2-5-72b-instruct)
- [Qwen3 235B A22B Instruct 2507](https://spiral.ai/integrations/opencode/qwen3-235b-a22b-instruct-2507)
- [Qwen Plus](https://spiral.ai/integrations/opencode/qwen-plus)
- [Qwen3 235B A22B Thinking 2507](https://spiral.ai/integrations/opencode/qwen3-235b-a22b-thinking-2507)

## Questions about Qwen2.5-VL 72B Instruct in opencode

**Can opencode use Qwen2.5-VL 72B Instruct?**

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Qwen2.5-VL 72B Instruct like any built-in tool.

**How much does Qwen2.5-VL 72B Instruct cost in opencode?**

Up to $0.005362 per run at the default inputs. $1.04 per 1M input tokens, $1.30 per 1M output tokens. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.

**Do I need an OpenRouter account to use Qwen2.5-VL 72B Instruct in opencode?**

No. Spiral runs Qwen2.5-VL 72B Instruct on its own OpenRouter account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Qwen2.5-VL 72B Instruct in opencode?**

About two minutes: add the server, then sign in, then check it.

**Does opencode wait while Qwen2.5-VL 72B Instruct runs?**

Qwen2.5-VL 72B Instruct runs in the background. opencode starts the run, checks on it and gives you the text, json when it's ready.

**What is Qwen2.5-VL useful for?**

Use it to extract information from document images, interpret charts, and locate objects. Good starting tasks include turning an invoice scan into structured data or explaining a chart's labels and values.

**Can Qwen2.5-VL extract tables and forms?**

Yes. It supports structured extraction from scanned tables, forms, and invoices. Specify the columns you want and ask it to mark unreadable entries instead of guessing.

**Which languages does Qwen2.5-VL's OCR training cover?**

Qwen names French, German, Italian, Spanish, Portuguese, Arabic, Russian, Japanese, Korean, and Vietnamese in its multilingual OCR training data. Treat that list as training coverage, not a promise of equal accuracy across languages.

**What context limit does Qwen publish?**

The model card describes a default configuration of 32,768 tokens. It also warns that YaRN context extension affects spatial and temporal localization, so a longer configuration should not be assumed to preserve location accuracy.

**How should I prompt Qwen2.5-VL to count objects?**

Ask it to locate each object first, then report the total. Qwen uses this detect-then-count approach in its reported evaluation; check the returned locations against the image.

