Thanks to visit codestin.com
Credit goes to docs.firecrawl.dev

Skip to main content
POST
/
parse
Upload and parse a file
curl --request POST \
  --url https://api.firecrawl.dev/v2/parse \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'options={
  "formats": [
    "markdown"
  ],
  "onlyMainContent": true,
  "includeTags": [
    "<string>"
  ],
  "excludeTags": [
    "<string>"
  ],
  "headers": {},
  "timeout": 30000,
  "parsers": [
    "pdf"
  ],
  "skipTlsVerification": true,
  "removeBase64Images": true,
  "blockAds": true,
  "redactPII": false,
  "origin": "api",
  "integration": "<string>",
  "zeroDataRetention": false
}'
import requests

url = "https://api.firecrawl.dev/v2/parse"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = { "options": "{
\"formats\": [
\"markdown\"
],
\"onlyMainContent\": true,
\"includeTags\": [
\"<string>\"
],
\"excludeTags\": [
\"<string>\"
],
\"headers\": {},
\"timeout\": 30000,
\"parsers\": [
\"pdf\"
],
\"skipTlsVerification\": true,
\"removeBase64Images\": true,
\"blockAds\": true,
\"redactPII\": false,
\"origin\": \"api\",
\"integration\": \"<string>\",
\"zeroDataRetention\": false
}" }
headers = {"Authorization": "Bearer <token>"}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)
const form = new FormData();
form.append('file', '<string>');
form.append('options', '{
"formats": [
"markdown"
],
"onlyMainContent": true,
"includeTags": [
"<string>"
],
"excludeTags": [
"<string>"
],
"headers": {},
"timeout": 30000,
"parsers": [
"pdf"
],
"skipTlsVerification": true,
"removeBase64Images": true,
"blockAds": true,
"redactPII": false,
"origin": "api",
"integration": "<string>",
"zeroDataRetention": false
}');

const options = {method: 'POST', headers: {Authorization: 'Bearer <token>'}};

options.body = form;

fetch('https://api.firecrawl.dev/v2/parse', options)
.then(res => res.json())
.then(res => console.log(res))
.catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
CURLOPT_URL => "https://api.firecrawl.dev/v2/parse",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n \"formats\": [\r\n \"markdown\"\r\n ],\r\n \"onlyMainContent\": true,\r\n \"includeTags\": [\r\n \"<string>\"\r\n ],\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"headers\": {},\r\n \"timeout\": 30000,\r\n \"parsers\": [\r\n \"pdf\"\r\n ],\r\n \"skipTlsVerification\": true,\r\n \"removeBase64Images\": true,\r\n \"blockAds\": true,\r\n \"redactPII\": false,\r\n \"origin\": \"api\",\r\n \"integration\": \"<string>\",\r\n \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>",
"Content-Type: multipart/form-data"
],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
echo "cURL Error #:" . $err;
} else {
echo $response;
}
package main

import (
"fmt"
"strings"
"net/http"
"io"
)

func main() {

url := "https://api.firecrawl.dev/v2/parse"

payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n \"formats\": [\r\n \"markdown\"\r\n ],\r\n \"onlyMainContent\": true,\r\n \"includeTags\": [\r\n \"<string>\"\r\n ],\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"headers\": {},\r\n \"timeout\": 30000,\r\n \"parsers\": [\r\n \"pdf\"\r\n ],\r\n \"skipTlsVerification\": true,\r\n \"removeBase64Images\": true,\r\n \"blockAds\": true,\r\n \"redactPII\": false,\r\n \"origin\": \"api\",\r\n \"integration\": \"<string>\",\r\n \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")

req, _ := http.NewRequest("POST", url, payload)

req.Header.Add("Authorization", "Bearer <token>")

res, _ := http.DefaultClient.Do(req)

defer res.Body.Close()
body, _ := io.ReadAll(res.Body)

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.firecrawl.dev/v2/parse")
.header("Authorization", "Bearer <token>")
.body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n \"formats\": [\r\n \"markdown\"\r\n ],\r\n \"onlyMainContent\": true,\r\n \"includeTags\": [\r\n \"<string>\"\r\n ],\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"headers\": {},\r\n \"timeout\": 30000,\r\n \"parsers\": [\r\n \"pdf\"\r\n ],\r\n \"skipTlsVerification\": true,\r\n \"removeBase64Images\": true,\r\n \"blockAds\": true,\r\n \"redactPII\": false,\r\n \"origin\": \"api\",\r\n \"integration\": \"<string>\",\r\n \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--")
.asString();
require 'uri'
require 'net/http'

url = URI("https://api.firecrawl.dev/v2/parse")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"options\"\r\n\r\n{\r\n \"formats\": [\r\n \"markdown\"\r\n ],\r\n \"onlyMainContent\": true,\r\n \"includeTags\": [\r\n \"<string>\"\r\n ],\r\n \"excludeTags\": [\r\n \"<string>\"\r\n ],\r\n \"headers\": {},\r\n \"timeout\": 30000,\r\n \"parsers\": [\r\n \"pdf\"\r\n ],\r\n \"skipTlsVerification\": true,\r\n \"removeBase64Images\": true,\r\n \"blockAds\": true,\r\n \"redactPII\": false,\r\n \"origin\": \"api\",\r\n \"integration\": \"<string>\",\r\n \"zeroDataRetention\": false\r\n}\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body
{
  "success": true,
  "data": {
    "markdown": "<string>",
    "summary": "<string>",
    "html": "<string>",
    "rawHtml": "<string>",
    "screenshot": "<string>",
    "audio": "<string>",
    "video": "<string>",
    "answer": "<string>",
    "highlights": "<string>",
    "links": [
      "<string>"
    ],
    "actions": {
      "screenshots": [
        "<string>"
      ],
      "scrapes": [
        {
          "url": "<string>",
          "html": "<string>"
        }
      ],
      "javascriptReturns": [
        {
          "type": "<string>",
          "value": "<unknown>"
        }
      ],
      "pdfs": [
        "<string>"
      ]
    },
    "metadata": {
      "title": "<string>",
      "description": "<string>",
      "language": "<string>",
      "sourceURL": "<string>",
      "url": "<string>",
      "keywords": "<string>",
      "ogLocaleAlternate": [
        "<string>"
      ],
      "<any other metadata> ": "<string>",
      "statusCode": 123,
      "numPages": 123,
      "totalPages": 123,
      "contentType": "<string>",
      "error": "<string>",
      "concurrencyLimited": true,
      "concurrencyQueueDurationMs": 123
    },
    "warning": "<string>",
    "changeTracking": {
      "previousScrapeAt": "2023-11-07T05:31:56Z",
      "diff": "<string>",
      "json": {}
    },
    "branding": {
      "logo": "<string>",
      "colors": {
        "primary": "<string>",
        "secondary": "<string>",
        "accent": "<string>",
        "background": "<string>",
        "textPrimary": "<string>",
        "textSecondary": "<string>",
        "link": "<string>",
        "success": "<string>",
        "warning": "<string>",
        "error": "<string>"
      },
      "fonts": [
        {
          "family": "<string>"
        }
      ],
      "typography": {
        "fontFamilies": {
          "primary": "<string>",
          "heading": "<string>",
          "code": "<string>"
        },
        "fontSizes": {
          "h1": "<string>",
          "h2": "<string>",
          "h3": "<string>",
          "body": "<string>"
        },
        "fontWeights": {
          "light": 123,
          "regular": 123,
          "medium": 123,
          "bold": 123
        },
        "lineHeights": {
          "heading": "<string>",
          "body": "<string>"
        }
      },
      "spacing": {
        "baseUnit": 123,
        "borderRadius": "<string>",
        "padding": {},
        "margins": {}
      },
      "components": {
        "buttonPrimary": {
          "background": "<string>",
          "textColor": "<string>",
          "borderRadius": "<string>"
        },
        "buttonSecondary": {
          "background": "<string>",
          "textColor": "<string>",
          "borderColor": "<string>",
          "borderRadius": "<string>"
        },
        "input": {}
      },
      "icons": {},
      "images": {
        "logo": "<string>",
        "favicon": "<string>",
        "ogImage": "<string>"
      },
      "animations": {},
      "layout": {},
      "personality": {}
    },
    "product": {
      "title": "<string>",
      "url": "<string>",
      "variants": [
        {
          "availability": {
            "inStock": true,
            "text": "<string>"
          },
          "id": "<string>",
          "sku": "<string>",
          "title": "<string>",
          "values": {},
          "price": {
            "amount": 123,
            "currency": "<string>",
            "formatted": "<string>"
          },
          "sale": {
            "originalPrice": {
              "amount": 123,
              "currency": "<string>",
              "formatted": "<string>"
            }
          },
          "images": [
            {
              "url": "<string>",
              "alt": "<string>"
            }
          ]
        }
      ],
      "brand": "<string>",
      "category": "<string>",
      "description": "<string>"
    },
    "menu": {
      "isMenu": true,
      "sections": [
        {
          "name": "<string>",
          "items": [
            {
              "name": "<string>",
              "id": "<string>",
              "description": "<string>",
              "images": [
                {
                  "url": "<string>",
                  "alt": "<string>"
                }
              ],
              "price": {
                "amount": 123,
                "currency": "<string>",
                "formatted": "<string>"
              },
              "availability": {
                "inStock": true,
                "text": "<string>"
              },
              "dietary": [
                "<string>"
              ],
              "calories": 123,
              "optionGroups": [
                {}
              ],
              "identifiers": {
                "merchantItemId": "<string>"
              },
              "url": "<string>",
              "sourceUrl": "<string>"
            }
          ],
          "id": "<string>",
          "description": "<string>"
        }
      ],
      "confidence": 123,
      "merchant": {
        "name": "<string>",
        "type": "<string>"
      },
      "currency": "<string>",
      "sourceUrl": "<string>"
    }
  }
}
{
"success": false,
"code": "BAD_REQUEST",
"error": "Invalid multipart form-data request."
}
{
"error": "Payment required to access this resource."
}
{
"error": "Request rate limit exceeded. Please wait and try again later."
}
{
"success": false,
"code": "UNKNOWN_ERROR",
"error": "An unexpected error occurred on the server."
}
Upload a local or non-public document and convert it into clean, LLM-ready data. /parse accepts file bytes via multipart/form-data and returns Markdown, JSON, HTML, links, images, or a summary — with reading order and tables preserved.
  • Turn PDF, DOCX, XLSX, HTML, and more into Markdown or structured JSON
  • Up to 5x faster parsing via a Rust-based engine
  • Files up to 50 MB per request
  • Zero Data Retention support

When to use /parse

Use /parse when the source document is a local file or not publicly accessible by URL. If you have a public URL that points to a document, prefer /scrape — it auto-detects the file type from the extension or content type and parses it the same way.
SourceEndpoint
Public URL to a document (e.g. https://example.com/report.pdf)POST /scrape
Local file or non-public bytes (PDF, DOCX, XLSX, HTML, …)POST /parse (this endpoint)
Using Firecrawl through MCP? Use firecrawl_parse for local files. Local MCP can read the file directly when configured with FIRECRAWL_API_URL. Remote hosted MCP returns a short-lived upload command first, then parses the returned uploadRef. Public document URLs should still use /scrape.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
file
file
required

The file bytes to parse. Supported extensions: .html, .htm, .pdf, .docx, .doc, .odt, .rtf, .xlsx, .xls.

options
object

Optional parse options sent as JSON in the multipart options field.

Response

Successful response

success
boolean
data
object