OCR.chat API

ຄໍາຮ້ອງຂໍ HTTP ຫນຶ່ງປ່ຽນຮູບຫຼື PDF ເປັນຂໍ້ຄວາມທີ່ສະອາດ, Markdown, ຕາຕະລາງ, ແລະ JSON - ໃນພາສາ 100 +. ວັດແທກຕໍ່ ໜ້າ, ບໍ່ມີຄວາມແປກໃຈ.

ເບິ່ງ​ລວມ

The OCR.chat API is a small REST interface. You POST a file and get back a job with the recognized text and a per-page breakdown (text, bounding boxes, confidence). Jobs of 5 pages or fewer return inline; larger jobs return immediately with a pending status that you poll until done.

  • Base URL: https://ocr.chat
  • Formats in: PNG, JPG, WEBP, GIF, BMP, TIFF, and multi-page PDF
  • Formats out: txt, md, docx, pdf, csv, json
  • Engines: cpu (fast, printed docs) and vlm (premium AI, handwriting, complex layout, math)

ການ​ផ្ទៀង​ផ្ទាត់​ຄວາມ​ຖືກຕ້ອງ

Authenticate with your API token (find it on your account page) as a Bearer header:

Authorization: Bearer YOUR_API_TOKEN

You can also pass ?api_token=… as a query parameter. Usage is metered against your account's page balance.

ສົ່ງ​ເອກະສານ

POST /api/v1/ocr/, multipart form upload.

curl -X POST https://ocr.chat/api/v1/ocr/ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -F "file=@invoice.pdf" \
  -F "tier=vlm" \
  -F "language=auto"

Returns the job. For ≤5-page files it is already done with the text; larger files come back pending/processing, poll the status endpoint.

{
  "uuid": "9f2c1b7e4a...",
  "status": "done",
  "tier": "vlm",
  "language": "auto",
  "page_count": 1,
  "mean_confidence": 0.98,
  "text": "INVOICE\nAcme Corp\nTotal: 215.00 USD",
  "markdown": "# INVOICE\n\n**Acme Corp** ...",
  "pages": [ { "index": 0, "text": "...", "blocks": [ { "text": "...", "bbox": [x0,y0,x1,y1], "confidence": 0.98 } ] } ]
}

ຮັບ​ຜົນ​ໄດ້

GET /api/v1/ocr/<uuid>/, poll until status is done or failed.

curl https://ocr.chat/api/v1/ocr/9f2c1b7e4a.../ \
  -H "Authorization: Bearer YOUR_API_TOKEN"

ດາວໂຫລດ​ຮູບແບບ

GET /api/v1/ocr/<uuid>/download/?format=md, export the result. format is one of txt, md, docx, pdf, csv, json.

curl -L "https://ocr.chat/api/v1/ocr/9f2c1b7e4a.../download/?format=docx" \
  -H "Authorization: Bearer YOUR_API_TOKEN" -o result.docx

ສົນທະນາ​ກັບ​ເອກະສານ

ຖາມ​ຄໍາຖາມ​ກ່ຽວກັບ​ວຽກ​ທີ່​ໄດ້​ເຮັດ​ແລ້ວ. ຄໍາຕອບ​ແມ່ນ​ອີງ​ໃສ່​ຂໍ້ຄວາມ​ທີ່​ໄດ້​ຖອດ​ອອກ​ມາ ແລະ ຖອດ​ບົດ​ຄວາມ​ທີ່​ມາ​ຈາກ​ຫນ້າ​ແຫຼ່ງ. ຕ້ອງການ​ບັນຊີ​ໂຕກັ່ນ - ຄຸນສົມບັດ​ການ​ສົນທະນາ​ແມ່ນ​ບັນຊີ​ທີ່​ໄດ້​ຮັບ​ການ​ເຂົ້າ​ເຖິງ.

POST /api/v1/chat/<uuid>/, JSON body {"message": "your question"}.

curl -X POST https://ocr.chat/api/v1/chat/9f2c1b7e4a.../ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"message": "What is the invoice total and due date?"}'

ສົ່ງຄືນ​ຂໍ້ຄວາມ​ຂອງ​ຜູ້ຊ່ວຍ​ພ້ອມ​ດ້ວຍ​ຄຳ​ຕອບ ແລະ ລາຍ​ຊື່​ຂອງ​ໜ້າ​ທີ່​ອ້າງອີງ:

{"conversation": "a1b2…", "message": {
   "role": "assistant",
   "content": "The total is $42, due on March 3 (p. 1).",
   "citations": [{"page": 1, "snippet": "The invoice total is $42…"}]
}}

GET /api/v1/chat/<uuid>/history/, ເອົາ​ການ​ສົນທະນາ​ເຕັມ​ມາ​ໃຊ້​ໃນ​ວຽກ​ໜຶ່ງ

ຕົວຢ່າງ​ຂອງ​កូដ

import requests, time

API = "https://ocr.chat/api/v1/ocr/"
H = {"Authorization": "Bearer YOUR_API_TOKEN"}

# Submit
with open("invoice.pdf", "rb") as f:
    job = requests.post(API, headers=H,
        files={"file": f}, data={"tier": "vlm"}).json()

# Poll until done
while job["status"] in ("pending", "processing"):
    time.sleep(2)
    job = requests.get(API + job["uuid"] + "/", headers=H).json()

print(job["markdown"])

# Download as DOCX
r = requests.get(API + job["uuid"] + "/download/",
                 headers=H, params={"format": "docx"})
open("result.docx", "wb").write(r.content)
import fs from "fs";

const API = "https://ocr.chat/api/v1/ocr/";
const H = { Authorization: "Bearer YOUR_API_TOKEN" };

const form = new FormData();
form.append("file", new Blob([fs.readFileSync("invoice.pdf")]), "invoice.pdf");
form.append("tier", "vlm");

let job = await (await fetch(API, { method: "POST", headers: H, body: form })).json();

while (["pending", "processing"].includes(job.status)) {
  await new Promise(r => setTimeout(r, 2000));
  job = await (await fetch(API + job.uuid + "/", { headers: H })).json();
}
console.log(job.markdown);
# 1. Submit
curl -X POST https://ocr.chat/api/v1/ocr/ \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -F "file=@invoice.pdf" -F "tier=vlm"

# 2. Poll  (use the uuid from step 1)
curl https://ocr.chat/api/v1/ocr/UUID/ \
  -H "Authorization: Bearer YOUR_API_TOKEN"

# 3. Download
curl -L "https://ocr.chat/api/v1/ocr/UUID/download/?format=md" \
  -H "Authorization: Bearer YOUR_API_TOKEN" -o result.md

​ប៉ារ៉ាម៉ែត្រ

FieldTypeDescription
filefileRequired. The image or PDF to process.
tierstringcpu (default, fast/printed) or vlm (premium AI: handwriting, layout, math).
languagestringauto (default) or a language code (en, ch, ja, ar, …).
toolstringOptional tool slug (e.g. extract-tables, handwriting-to-text) to apply that tool's preset.
translate_tostringFor the translate tool, target language code.

ຂໍ້ຜິດພາດ & ຈໍາກັດ

CodeMeaning
400No file, unsupported type, or file too large.
401Missing or invalid API token.
402Out of pages, daily/monthly free limit reached, or no credits. The body includes used/cap.
404Job UUID not found.
409Download requested before the job finished.

Each page processed costs credits (1/page on the fast tier, more on premium). Paid plans raise per-file page caps and add priority. See pricing.

ຄໍາຖາມທີ່ຖາມເລື້ອຍໆ

Create a free account and open your account page, your token is shown there with a copy button.

Yes, files of 5 pages or fewer return the full result inline in the POST response, so no polling is needed for most images and short PDFs.

Over 100, including Latin, CJK, Arabic, Cyrillic and Indic scripts. Use language=auto to detect, or pass a specific code.

Uploads are processed for OCR and deleted automatically. We never sell, share, or train on your documents.

ການໃຊ້ງານແມ່ນຖືກວັດແທກຕໍ່ ໜ້າ ຕໍ່ກັບສະຖິຕິບັນຊີຂອງທ່ານ: ການໂທທີ່ບໍ່ຮູ້ຊື່ໄດ້ຮັບເງິນອຸດ ໜູນ ຕໍ່ IP ຕໍ່ມື້, ບັນຊີຟຣີແມ່ນບັອກເດືອນແລະແຜນທີ່ຈ່າຍໃຊ້ເງິນກູ້ທີ່ຊື້ມາພ້ອມກັບ ໜ້າ ຈໍແລະຄວາມສໍາຄັນຂອງ ໜ້າ ຈໍທີ່ສູງກວ່າ. ເມື່ອທ່ານແລ່ນອອກໄປທ່ານຈະໄດ້ຮັບ 402 ທີ່ມີໃຊ້ແລະກອບໃນຮ່າງກາຍ.

ທ່ານສາມາດສົ່ງ PNG, JPG, WEBP, GIF, BMP, TIFF, ແລະ PDF ຫຼາຍ ໜ້າ. ຜົນໄດ້ຮັບດາວໂຫລດເປັນ txt, md, docx, pdf (ສາມາດຄົ້ນຫາໄດ້), csv, ຫຼື json ຜ່ານການດາວໂຫລດປາຣາເມັດຮູບແບບຈຸດສຸດທ້າຍ.

400 ແມ່ນ​ເອກະສານ​ທີ່​ຂາດ, ປະເພດ​ທີ່​ບໍ່​ໄດ້​ຮັບ​ການ​ສະໜັບສະໜູນ ຫຼື ເອກະສານ​ທີ່​ໃຫຍ່​ເກີນ​ໄປ; 401 ແມ່ນ​ເອກະສານ​ທີ່​ຂາດ ຫຼື ບໍ່ມີ​ຕົວ​ແທນ​ທີ່​ຖືກຕ້ອງ; 402 ອອກ​ຈາກ​ໜ້າ; 404 ແມ່ນ​ວຽກ UUID ທີ່​ບໍ່​ຮູ້; ແລະ 409 ແມ່ນ​ການ​ດາວໂຫລດ​ທີ່​ໄດ້​ຮ້ອງຂໍ​ກ່ອນ​ທີ່​ວຽກ​ຈະ​ສຳເລັດ. ເນື້ອໃນ​ຂອງ​ຂໍ້ຜິດພາດ​ລວມ​ມີ​ຂໍ້ຄວາມ​ສັ້ນໆ.

ສິ່ງ​ຂອງ​ວຽກ​ທີ່ມີ​ສະຖານະ, ລະດັບ, ພາສາ, page_ count, ແລະ mean_ confidence, ລວມ​ທັງ​ຂໍ້ຄວາມ​ເຕັມ ແລະ markdown. ລາຍການ​ໜ້າ​ແບ່ງ​ໜ້າ​ແຕ່ລະ​ໜ້າ​ອອກ​ເປັນ​ບລັອກ​ດ້ວຍ​ຂໍ້ຄວາມ, ຕົວ​ຈຳກັດ​ກ່ອງ (bbox), ແລະ ຕົວ​ຈຳກັດ​ຄວາມ​ເຊື່ອ​ຖື​ຕໍ່​ບລັອກ.

ໃຊ້ cpu (ປັ໊ມ​ເດີມ) ເພື່ອ​ຮັບຮູ້​ເອກະສານ​ທີ່​ພິມ​ອອກ​ຢ່າງ​ໄວ ແລະ ລາຄາ​ຖືກ. ໃຊ້ vlm, ເຄື່ອງຈັກ AI ທີ່ມີ​ລາຄາ​ຖືກ, ສຳ​ລັບ​ການ​ຂຽນ​ດ້ວຍ​ມື, ການຈັດ​ວາງ​ທີ່​ສັບສົນ ຫຼື ຫຼາຍ​ແຖວ, ຄະນິດສາດ ແລະ ການ​ແປ, ບ່ອນ​ທີ່​ມັນ​ຈະ​ຖືກຕ້ອງ​ຫຼາຍ​ກວ່າ​ເກົ່າ.

ສົ່ງ​ເຄື່ອງມື​ໄປ​ພ້ອມ​ກັບ​ສະລກ (ຕົວຢ່າງ: extract-table ຫຼື handwriting-to-text) ເພື່ອ​ນຳ​ໃຊ້​ການ​ຕັ້ງຄ່າ​ລ່ວງໜ້າ​ຂອງ​ເຄື່ອງມື​ນັ້ນ. ສຳ​ລັບ​ເຄື່ອງມື​ແປ, ສົ່ງ translate_to ກັບ​ລະຫັດ​ພາສາ​ເປົ້າ​ໝາຍ​ເພື່ອ​ຮັບ​ຂໍ້ຄວາມ​ທີ່​ໄດ້​ຮັບ​ການ​ຮັບຮູ້​ຄືນ​ມາ​ແປ.

ໄຟລ໌ຂອງ5ຫນ້າຫຼື ໜ້ອຍ ກວ່າກັບຄືນໃນຄໍາຕອບ POST. ໄຟລ໌ໃຫຍ່ກວ່າມາກັບຄືນທັນທີເປັນ pendent ຫຼື ຂະບວນການ, ແລະທ່ານ poll GET /api/v1/ocr /<uuid>/ ຈົນກວ່າ​ສະຖານະ​ຈະ​ສຳເລັດ ຫຼື ລົ້ມເຫລວ. ແຜນທີ່​ຈ່າຍ​ເພີ່ມ​ການ​ກີດ​ກັນ​ຂອງ​ໜ້າ​ຕໍ່​ໄຟລ໌.

API ແມ່ນ REST ປົກກະຕິຜ່ານ HTTPS, ສະນັ້ນມັນເຮັດວຽກຈາກພາສາໃດກໍ່ຕາມທີ່ມີລູກຄ້າ HTTP - ເບິ່ງຕົວຢ່າງ Python, Node.js ແລະ cURL ຂ້າງເທິງ. ບໍ່ມີ SDK ທີ່ຈະຕິດຕັ້ງ; ບາງລໍາດັບຂອງລະຫັດ HTTP ມາດຕະຖານແມ່ນທຸກຢ່າງທີ່ທ່ານຕ້ອງການ.