PDF to Text & Markdown OCR API

const form = new FormData();
form.append('pdf', fileInput.files[0]);

const res = await fetch('https://api.corenexis.com/pdf-to-text/v1', {
  method: 'POST',
  headers: { 'x-api-key': 'your_api_key' },
  body: form
});
const data = await res.json();
console.log('Job ID:', data.data.job_id);

import requests

with open("document.pdf", "rb") as f:
    res = requests.post(
        "https://api.corenexis.com/pdf-to-text/v1",
        headers={"x-api-key": "your_api_key"},
        files={"pdf": f}
    )
print(res.json()["data"]["job_id"])

$ch = curl_init("https://api.corenexis.com/pdf-to-text/v1");
curl_setopt_array($ch, [
    CURLOPT_POST => true,
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_HTTPHEADER => ["x-api-key: your_api_key"],
    CURLOPT_POSTFIELDS => ["pdf" => new CURLFile("document.pdf")],
]);
$resp = json_decode(curl_exec($ch), true);
echo "Job ID: " . $resp["data"]["job_id"];

import requests
with open("bilingual.pdf", "rb") as f:
    res = requests.post(
        "https://api.corenexis.com/pdf-to-text/v1",
        headers={"x-api-key": "your_api_key"},
        files={"pdf": f},
        data={"lang": "eng+hin", "output_format": "both"}
    )
print(res.json())

# Pages 2, 7, and 9 only — billed as 3 pages
curl -X POST "https://api.corenexis.com/pdf-to-text/v1" \
  -H "x-api-key: your_api_key" \
  -F "[email protected]" \
  -F "extract_pages=2,7,9"

# Just page 5
curl -X POST "https://api.corenexis.com/pdf-to-text/v1" \
  -H "x-api-key: your_api_key" \
  -F "[email protected]" \
  -F "extract_pages=5"

curl -X POST "https://api.corenexis.com/pdf-to-text/v1" \
  -H "x-api-key: your_api_key" \
  -d '{"pdf_url":"https://drive.google.com/uc?export=download&id=1--EMd70IQHnLuVJXqXHNoiO...L","lang":"eng+hin"}'

curl -X POST "https://api.corenexis.com/pdf-to-text/v1" \
  -H "x-api-key: your_api_key" \
  -F "pdf_url=https://cdn.example.com/contract.pdf" \
  -F "extract_pages=1to5"

import requests, time

API_KEY = "your_api_key"

# 1. Submit
with open("document.pdf", "rb") as f:
    sub = requests.post(
        "https://api.corenexis.com/pdf-to-text/v1",
        headers={"x-api-key": API_KEY},
        files={"pdf": f},
        data={"output_format": "both"}
    ).json()

job_id = sub["data"]["job_id"]
print("Job ID:", job_id)

# 2. Poll
while True:
    r = requests.get(f"https://api.corenexis.com/pdf-to-text/status/{job_id}",
                     headers={"x-api-key": API_KEY}).json()
    status = r["data"]["status"]
    print("Status:", status)
    if status != "processing":
        break
    time.sleep(3)

# 3. Download
txt_url = r["data"]["output"]["txt"]
text = requests.get(txt_url).text
print(text[:500])

const API_KEY = 'your_api_key';

// 1. Submit
const form = new FormData();
form.append('pdf', fileInput.files[0]);
form.append('output_format', 'both');

const sub = await fetch('https://api.corenexis.com/pdf-to-text/v1', {
  method: 'POST',
  headers: { 'x-api-key': API_KEY },
  body: form
}).then(r => r.json());

const jobId = sub.data.job_id;
console.log('Job ID:', jobId);

// 2. Poll
let result;
while (true) {
  result = await fetch(`https://api.corenexis.com/pdf-to-text/status/${jobId}`, {
    headers: { 'x-api-key': API_KEY }
  }).then(r => r.json());
  if (result.data.status !== 'processing') break;
  await new Promise(r => setTimeout(r, 3000));
}

// 3. Download
const text = await fetch(result.data.output.txt).then(r => r.text());
console.log(text);

{
  "success": true,
  "plan": "starter",
  "data": {
    "job_id": "a3f9c1d2e4b567890123456789abcdef",
    "status": "completed",
    "lang": "eng+hin",
    "submitted_at": 1748000000000,
    "completed_at": 1748000060000,
    "file_size": "500 KB",
    "total_pages": 10,
    "extraction_pages": "all",
    "pages_processed": 10,
    "output_format": "both",
    "webhook_url": null,
    "output": {
      "txt": "https://cdn.corenexis.com/user_content/documents/a3f9c1d2.txt",
      "md":  "https://cdn.corenexis.com/user_content/documents/a3f9c1d2.md"
    }
  },
  "usage": { "remaining": 98, "rate_limit": 10, "monthly_limit": 100 }
}

{
  "success": true,
  "plan": "starter",
  "data": {
    "job_id": "a3f9c1d2e4b567890123456789abcdef",
    "status": "partial",
    "warning": "Processing timed out after 5 minutes. Only 8 of 50 pages processed.",
    "lang": "eng",
    "submitted_at": 1748000000000,
    "completed_at": 1748000300000,
    "file_size": "5 MB",
    "total_pages": 50,
    "extraction_pages": "all",
    "pages_processed": 8,
    "output_format": "text",
    "output": {
      "txt": "https://cdn.corenexis.com/user_content/documents/a3f9c1d2.txt"
    }
  },
  "usage": { "remaining": 98, "rate_limit": 10, "monthly_limit": 100 }
}

{
  "success": true,
  "plan": "starter",
  "data": {
    "job_id": "a3f9c1d2e4b567890123456789abcdef",
    "status": "error",
    "error": "PDF to image conversion failed.",
    "submitted_at": 1748000000000,
    "completed_at": 1748000005000
  },
  "usage": { "remaining": 98, "rate_limit": 10, "monthly_limit": 100 }
}

{
  "success": false,
  "code": "PARAM_LIMIT_EXCEEDED",
  "message": "Invalid value for 'max_file_size_bytes'. Allowed for your plan: 2097152 or less. Your request contains: 5242880. Please change 'max_file_size_bytes' or upgrade your plan.",
  "param": "max_file_size_bytes",
  "provided": 5242880,
  "op": "lte",
  "max_allowed": 2097152
}

{
  "success": false,
  "code": "PARAM_LIMIT_EXCEEDED",
  "message": "Feature 'markdown' is not allowed on your current plan. Allowed for your plan: false. Your request contains: true. Please disable 'markdown' or upgrade your plan.",
  "param": "markdown",
  "provided": true,
  "allowed": false
}

{
  "success": false,
  "code": "INVALID_INPUT",
  "message": "Unsupported language code 'klingon'. See /pdf-ocr/languages for the supported list."
}

{
  "success": false,
  "code": "QUOTA_EXCEEDED",
  "message": "Monthly quota reached. Upgrade your plan or wait for the next billing cycle."
}

{
  "success": false,
  "code": "RATE_LIMIT_EXCEEDED",
  "message": "Too many requests. Please wait before making another request."
}