Developer API / docs

OCR PDF (33 languages) API

Extract text from scanned or image-based PDFs with OCR in 33 languages: English, Hindi and other Devanagari scripts, Arabic, Chinese, Japanese, Korean, Tamil, Telugu, Bengali, Urdu and more. format=text gives reading-order plain text, format=json gives every token with its position - the raw material for building spreadsheets from scanned tables.

POSThttps://api.gigai.tools/v1/jobsAsync

Runs as the ocr-pdf operation inside a job. Needs a key with the jobs:write scope.

Options

langs - string
format - string, one of text, json

Limits

Input: pdf (one file, checked by content, never by extension).
Max input size: 30 MB.
Output: txt, json.
Time budget: 600 seconds, then the task fails with the timeout code.
Engine: tesseract.

Inside a bigger job

Chain it: any task can consume this one's output by naming it in input. The recipes show working pipelines.

as one task in a graph

"step": { "operation": "ocr-pdf", "input": ["previous-task"] }

Errors this tool returns

invalid_input, invalid_option, file_too_large, timeout. The full list with fixes is on the errors page.

Merge PDF · Split PDF · Rotate PDF · PDF to Text

Was this page helpful?

curl -X POST https://api.gigai.tools/v1/jobs \
  -H "Authorization: Bearer $GIGAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "tasks": {
    "in": { "operation": "import/url", "url": "https://example.com/input.pdf" },
    "work": { "operation": "ocr-pdf", "input": ["in"] },
    "out": { "operation": "export/url", "input": ["work"] }
  } }'

# then poll until finished and follow the export URL:
curl https://api.gigai.tools/v1/jobs/JOB_ID/wait -H "Authorization: Bearer $GIGAI_API_KEY"

Finished job

{
  "id": "job_27b562f72d84a9a52324ced8",
  "status": "finished",
  "retention_s": 3600,
  "tasks": [
    { "name": "work", "operation": "ocr-pdf",
      "status": "finished", "duration_ms": 47 },
    { "name": "out", "operation": "export/url", "status": "finished",
      "result": { "files": [
        { "id": "file_63930500160eadd44dee99f1",
          "filename": "result.txt", "size": 10420,
          "url": "https://api.gigai.tools/v1/files/file_639.../download?e=...&s=..." }
      ]}}
  ]
}

OCR PDF (33 languages) API

Options

Limits

Inside a bigger job

Errors this tool returns

Related tools