OCR [BETA]

OCR extracts text and structured content from documents and images, enabling applications such as document digitization, data extraction, searchable archives, and automated document processing.

To explore available models, visit cortecs.ai and filter by the OCR tag.

Example usage

Python

import base64
import requests

api_key = "<CORTECS_API_KEY>"
pdf_path = "document.pdf"

with open(pdf_path, "rb") as file:
    encoded_pdf = base64.b64encode(file.read()).decode("utf-8")

response = requests.post(
    "https://api.cortecs.ai/v1/ocr",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": "mistral-ocr-4.1",
        "document": {
            "type": "document_url",
            "document_url": f"data:application/pdf;base64,{encoded_pdf}",
        },
    },
)

response.raise_for_status()
result = response.json()

for page in result["pages"]:
    print(page["markdown"])

Node.js

import fs from "node:fs";

const apiKey = "<CORTECS_API_KEY>";
const pdf = fs.readFileSync("document.pdf").toString("base64");

const response = await fetch("https://api.cortecs.ai/v1/ocr", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "mistral-ocr-4.1",
    document: {
      type: "document_url",
      document_url: `data:application/pdf;base64,${pdf}`,
    },
  }),
});

if (!response.ok) {
  throw new Error(`OCR request failed: ${response.status} ${await response.text()}`);
}

const result = await response.json();

for (const page of result.pages) {
  console.log(page.markdown);
}

Curl

PDF_BASE64="$(base64 < document.pdf | tr -d '\n')"

curl 'https://api.cortecs.ai/v1/ocr' \
  -H 'Authorization: Bearer <CORTECS_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d "{
    \"model\": \"mistral-ocr-4.1\",
    \"document\": {
      \"type\": \"document_url\",
      \"document_url\": \"data:application/pdf;base64,${PDF_BASE64}\"
    }
  }"

OCR with document annotation

Python

import base64
import requests

api_key = "<CORTECS_API_KEY>"
pdf_path = "document.pdf"

with open(pdf_path, "rb") as file:
    encoded_pdf = base64.b64encode(file.read()).decode("utf-8")

response = requests.post(
    "https://api.cortecs.ai/v1/ocr",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": "mistral-ocr-4.1",
        "document": {
            "type": "document_url",
            "document_url": f"data:application/pdf;base64,{encoded_pdf}",
        },
        "document_annotation_prompt": (
            "Provide a concise title and summary for this document."
        ),
        "document_annotation_format": {
            "type": "json_schema",
            "json_schema": {
                "name": "document_summary",
                "strict": True,
                "schema": {
                    "type": "object",
                    "properties": {
                        "title": {"type": "string"},
                        "summary": {"type": "string"},
                    },
                    "required": ["title", "summary"],
                    "additionalProperties": False,
                },
            },
        },
    },
)

response.raise_for_status()
result = response.json()

annotation = json.loads(result["document_annotation"])
print("Title:", annotation["title"])
print("Summary:", annotation["summary"])

Node.js

import fs from "node:fs";

const apiKey = "<CORTECS_API_KEY>";
const pdf = fs.readFileSync("document.pdf").toString("base64");

const response = await fetch("https://api.cortecs.ai/v1/ocr", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "mistral-ocr-4.1",
    document: {
      type: "document_url",
      document_url: `data:application/pdf;base64,${pdf}`,
    },
    document_annotation_prompt:
      "Provide a concise title and summary for this document.",
    document_annotation_format: {
      type: "json_schema",
      json_schema: {
        name: "document_summary",
        strict: true,
        schema: {
          type: "object",
          properties: {
            title: { type: "string" },
            summary: { type: "string" },
          },
          required: ["title", "summary"],
          additionalProperties: false,
        },
      },
    },
  }),
});

if (!response.ok) {
  throw new Error(`OCR request failed: ${response.status} ${await response.text()}`);
}

const result = await response.json();
const annotation = JSON.parse(result.document_annotation);

console.log("Title:", annotation.title);
console.log("Summary:", annotation.summary);

Curl

PDF_BASE64="$(base64 < document.pdf | tr -d '\n')"

curl 'https://api.cortecs.ai/v1/ocr' \
  -H 'Authorization: Bearer <CORTECS_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d "{
    \"model\": \"mistral-ocr-4.1\",
    \"document\": {
      \"type\": \"document_url\",
      \"document_url\": \"data:application/pdf;base64,${PDF_BASE64}\"
    },
    \"document_annotation_prompt\": \"Provide a concise title and summary for this document.\",
    \"document_annotation_format\": {
      \"type\": \"json_schema\",
      \"json_schema\": {
        \"name\": \"document_summary\",
        \"strict\": true,
        \"schema\": {
          \"type\": \"object\",
          \"properties\": {
            \"title\": {
              \"type\": \"string\"
            },
            \"summary\": {
              \"type\": \"string\"
            }
          },
          \"required\": [\"title\", \"summary\"],
          \"additionalProperties\": false
        }
      }
    }
  }"