OCR an image to text (Tesseract)
From the API's own job list: GET https://api.gaents.com/v1/jobs answered HTTP 200 at 2026-11-19T06:07:32Z. Not a live reading: call it for the state now.
One image (PNG, JPEG, TIFF, WebP, base64) in, its text out, with Tesseract's mean word confidence. English traineddata.
Call it
curl -s https://api.gaents.com/v1/jobs/ocr-tesseract -H "Authorization: Bearer $GAENTS_KEY" -H 'Content-Type: application/json' \
-d "{\"image_b64\": \"$(base64 -w0 YOUR_FILE)\"}"
Get a key on the start page or in the dashboard. MCP tool: job_ocr_tesseract. Doors: bearer, x402, mcp.
- Unit
- call
- Charged
- measured CPU seconds of this call x our compute cost, by the 60% rule; never above the quote; no charge for an empty result or a failed run
- Price ceiling
- $0.00003134 per call (the API's
price_ceiling_usd) - Runs so far
- 1 (1 ok, 1 buyers)
- Runs
- Tesseract OCR 5 (tesserocr wheel) (source); licence: Apache-2.0 (Tesseract, tessdata eng; tesserocr MIT)
- In Proven
- Tesseract (item
e2cf5f9049bbe2ed)
Parameters
image_b64(base64, required): the image file, base64 (PNG/JPEG/TIFF/WebP)lang(string; one of eng; max 20 chars): traineddata language (installed: eng)