# OCR.space text from an image or PDF

Extract text from a public image or PDF URL (JPG, PNG, GIF, BMP, TIFF, PDF) with OCR.space. Needs url.

Extract text from a public image or PDF URL (JPG, PNG, GIF, BMP, TIFF, PDF) with OCR.space. Returns the parsed text of each page; table mode keeps line by line layout for receipts and tables. Free plan limits: file up to 1 MB, PDF up to 3 pages, 500 requests per day per IP. Engine 2 (default) is the fast all-round choice; engine 3 is the most accurate, including for handwriting and tables, but slower. Both detect the language by themselves. Set filetype when the URL has no file extension.

- Tool ID: `ocrspace/ocr-image`
- Provider: [OCR.space](/providers/ocrspace.md)
- Capability: [Document & PDF parsing](/tools/web-scraping/documents.md)
- Price: no charge per call
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

No charge per call. A workspace is still needed so your agent can call it.


```json
{
  "model": "per_call",
  "amountUsd": 0
}
```

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "pattern": "^https?://[^\\s]{4,2000}$",
      "description": "Public URL of the image or PDF, e.g. 'https://dl.a9t9.com/ocr/solarcell.jpg'"
    },
    "language": {
      "type": "string",
      "enum": [
        "auto",
        "ara",
        "bul",
        "chs",
        "cht",
        "hrv",
        "cze",
        "dan",
        "dut",
        "eng",
        "fin",
        "fre",
        "ger",
        "gre",
        "hun",
        "kor",
        "ita",
        "jpn",
        "pol",
        "por",
        "rus",
        "slv",
        "spa",
        "swe",
        "tha",
        "tur",
        "ukr",
        "vnm"
      ],
      "default": "auto",
      "description": "Leave 'auto'; three-letter codes are deprecated fallbacks, e.g. 'fre'"
    },
    "engine": {
      "type": "integer",
      "enum": [
        2,
        3
      ],
      "default": 2,
      "description": "OCR engine: 2 fast all-round, 3 most accurate but slower, e.g. 3"
    },
    "table": {
      "type": "boolean",
      "default": false,
      "description": "Table mode: return text line by line, for receipts and tables, e.g. true"
    },
    "scale": {
      "type": "boolean",
      "description": "Upscale low-resolution images before OCR, e.g. true"
    },
    "detect_orientation": {
      "type": "boolean",
      "description": "Auto-rotate the image when needed, e.g. true"
    },
    "filetype": {
      "type": "string",
      "enum": [
        "PDF",
        "GIF",
        "PNG",
        "JPG",
        "TIF",
        "BMP"
      ],
      "description": "File type when the URL has no extension, e.g. 'PDF'"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "ocrspace/ocr-image",
  "input": {
    "url": "https://dl.a9t9.com/ocr/solarcell.jpg"
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

Licence: OCR.space free OCR API (free plan may be used in commercial projects, no uptime guarantee).

[Provider documentation](https://ocr.space/ocrapi)

[REST inspection](https://api.agentik.cc/v1/tools/ocrspace/ocr-image) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/ocrspace/ocr-image) · [Agent index](/llms.txt)