OCR.chat API

Satu permintaan HTTP mengubah imej atau PDF ke teks bersih, Markdown, jadual, dan JSON — dalam 100+ bahasa. Diukur per halaman, tiada kejutan.

Lihat

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)

Pengesahan

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.

Hantar dokumen

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 } ] } ]
}

Dapatkan hasil

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"

Muat turun format

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

Chat dengan dokumen

Tanya soalan mengenai kerja yang selesai. Jawapan hanya didasarkan pada teks yang diekstrak dan menyebut halaman sumber. Memerlukan token akaun - ciri sembang adalah akaun-gated.

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?"}'

Kembalikan mesej pembantu dengan jawapan dan senarai halaman yang dikutip:

{"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/, Dapatkan transkripsi perbualan penuh untuk kerja.

Contoh kod

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

Parameter

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.

Ralat & had

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.

Pertanyaan yang kerap ditanya

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.

Penggunaan diukur per halaman terhadap baki akaun anda: panggilan anonim mendapat peruntukan harian per IP, akaun percuma satu tong bulanan, dan rancangan berbayar menggunakan kredit yang dibeli dengan had halaman per fail dan keutamaan yang lebih tinggi. Apabila anda kehabisan anda akan mendapat 402 dengan digunakan dan had dalam badan.

Anda boleh menghantar PNG, JPG, WEBP, GIF, BMP, TIFF, dan PDF berbilang halaman. Hasil muat turun sebagai txt, md, docx, pdf (boleh dicari), csv, atau json melalui parameter format titik akhir muat turun.

400 ialah fail hilang, jenis tidak disokong, atau fail terlalu besar; 401 ialah token hilang atau tidak sah; 402 adalah keluar dari halaman; 404 ialah UUID kerja tidak diketahui; dan 409 ialah muat turun diminta sebelum kerja selesai. Badan ralat termasuk mesej pendek.

Objek kerja dengan status, aras, bahasa, page_count, dan mean_confidence, ditambah teks penuh dan markdown. Aras halaman memecah setiap halaman ke blok dengan teks mereka, kotak sempadan (bbox), dan kepercayaan per-blok.

Guna cpu (piawai) untuk pengecaman pantas, kos rendah dokumen cetak bersih. Guna vlm, enjin AI premium, untuk tulisan tangan, susunatur kompleks atau berbilang-kolum, matematik, dan terjemahan, di mana ia lebih tepat.

Serahkan alat dengan slug (contohnya, ekstrak-tabel atau tulisan-tangan-ke-teks) untuk melaksanakan preset alat yang diset. Untuk alat menterjemah, juga serahkan translate_to dengan kod bahasa sasaran untuk mendapatkan teks yang dikenali kembali diterjemahkan.

Fail 5 halaman atau kurang kembali dalam baris dalam maklum balas POST. Fail yang lebih besar kembali segera sebagai menunggu atau pemprosesan, dan anda poll GET /api/v1/ocr/<uuid>/ sehingga status selesai atau gagal. Rancangan berbayar menaikkan had halaman per fail.

API adalah REST biasa di atas HTTPS, jadi ia berfungsi dari mana-mana bahasa dengan klien HTTP — lihat contoh Python, Node.js, dan cURL di atas. Tiada SDK untuk dipasang; beberapa baris kod HTTP piawai adalah semua yang anda perlukan.