OCR.chat API

En HTTP-anmodning forvandler et billede eller PDF til ren tekst, Markdown, tabeller og JSON ~ i 100 + sprog. Målt pr side, ingen overraskelser.

Oversigt

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)

Godkendelse

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.

Indsend et dokument

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 } ] } ]
}

Få et resultat

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"

Hent et 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 med et dokument

Stil spørgsmål om et færdigt job. Svarene er kun baseret på den udtrukne tekst og citerer kildesiden. Kræver en konto token • chatfunktionen er konto- 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?"}'

Returnerer assistentbeskeden med sit svar og en liste over citerede sider:

{"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/, Hent hele samtaleudskriften til et job.

Kodeeksempler

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

Parametre

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.

Fejl og begrænsninger

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.

Ofte stillede spørgsmål

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.

Brugen måles pr. side mod din kontosaldo: anonyme opkald får en per-IP daglig godtgørelse, gratis konti en månedlig spand, og betalte planer bruger købte kreditter med højere per-fil side caps og prioritet. Når du løber ud får du en 402 med brugt og hætte i kroppen.

Du kan sende PNG, JPG, WEBP, GIF, BMP, TIFF og multi-side PDF. Resultater downloade som txt, md, docx, pdf (søgbar), csv, eller json via download endpoint format parameter.

400 er en manglende fil, ikke- understøttet type eller fil for stor; 401 en manglende eller ugyldig token; 402 ud af siderne; 404 et ukendt job UUID; og 409 en download anmodet før jobbet færdig. Fejlorganer omfatter en kort besked.

Et jobobjekt med status, niveau, sprog, side_count og Mean_confidence plus den fulde tekst og markdown. Siderne array bryder hver side i blokke med deres tekst, grænsende boks (bbox), og per-blok tillid.

Brug cpu (standard) til hurtig, billig anerkendelse af rene trykte dokumenter. Brug vlm, premium AI motor, til håndskrift, komplekse eller multi-kolonne layouts, matematik og oversættelse, hvor det er langt mere præcis.

Pass værktøj med en slug (for eksempel udtrække-borde eller håndskrift-til-tekst) til at anvende dette værktøjs tunet forudindstillede. For oversætte værktøj, også passere oversætte_til med målsprog kode for at få den anerkendte tekst tilbage oversat.

Filer på 5 sider eller færre returinline i POST svar. Større filer kommer tilbage straks som verserende eller behandling, og du meningsmåling GET /api/v1/ocr /<uuid>/ indtil status er gjort eller mislykkedes. Betalte planer hæver per-fil side cap.

API er almindelig REST over HTTPS, så det virker fra ethvert sprog med en HTTP-klient! se Python, Node.js, og cURL eksempler ovenfor. Der er ingen SDK at installere; et par linjer af standard HTTP-kode er alt hvad du behøver.