# Ai Extract Salary From Job Ads

**Use case:** 

Pull a structured salary range and currency out of free-text job ads, with null when no salary is stated, so you can filter and sort listings by pay. Uses built-in example ads; point it at your job-board scraper output.

## Input

```json
{
  "fileFormat": "auto",
  "data": [
    {
      "title": "Senior React Developer",
      "description": "Remote, UK based. £70,000 to £85,000 per year plus equity. 4 day week trial."
    },
    {
      "title": "Warehouse Operative",
      "description": "Immediate start, £12.50 per hour, 40 hours a week, overtime available."
    },
    {
      "title": "Marketing Manager",
      "description": "Competitive salary, hybrid working in Manchester, private healthcare."
    },
    {
      "title": "Data Analyst",
      "description": "USD 95k-110k depending on experience. Austin, TX, on-site 3 days."
    }
  ],
  "prompt": "Extract the salary from this job ad. Return the minimum and maximum yearly salary as numbers in the currency stated (convert an hourly rate to yearly assuming 40 hours a week and 52 weeks), plus the ISO currency code. If no salary is stated, return null for all three.\n\nTitle: {{title}}\nDescription: {{description}}",
  "outputFields": [
    {
      "name": "salaryMin",
      "type": "number",
      "description": "minimum yearly salary, or null"
    },
    {
      "name": "salaryMax",
      "type": "number",
      "description": "maximum yearly salary, or null"
    },
    {
      "name": "currency",
      "type": "string",
      "description": "ISO code such as GBP, USD or EUR, or null"
    }
  ],
  "model": "anthropic/claude-haiku-4.5",
  "previewRows": 0,
  "maxRows": 1000,
  "rowsPerRequest": 4,
  "concurrency": 4,
  "maxInputCharsPerField": 4000,
  "maxOutputTokensPerRow": 150,
  "temperature": 0,
  "skipIfEmpty": true,
  "includeOriginalFields": true,
  "exportFormats": [
    "csv"
  ]
}
```

## Output

```json
{
  "id": {
    "label": "Id",
    "format": "number"
  },
  "product": {
    "label": "Product",
    "format": "text"
  },
  "review": {
    "label": "Review",
    "format": "text"
  },
  "sentiment": {
    "label": "Sentiment",
    "format": "text"
  },
  "topic": {
    "label": "Topic",
    "format": "text"
  },
  "aspects": {
    "label": "Aspects",
    "format": "array"
  },
  "aiModel": {
    "label": "Model",
    "format": "text"
  },
  "aiError": {
    "label": "Error",
    "format": "text"
  }
}
```

## About this Actor

This example demonstrates how to use [Dataset AI Enrich (LLM Classify, Extract, Summarise Rows)](https://apify.com/nerolabs/dataset-ai-enrich.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/nerolabs/dataset-ai-enrich.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
This Task's input is already configured above — use it as-is rather than inventing a new one.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/nerolabs/dataset-ai-enrich.md

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).