PDF-to-markup API for HTML and Markdown conversion workflows

Use Nutrient DWS when the workflow is broadly about converting PDFs into markup outputs like HTML and Markdown. Start with this markup hub. Then move to the exact output page when the workflow is specifically PDF-to-HTML or PDF-to-Markdown.

START FREE PROCESSOR PRICING

Try it out

This example will convert your uploaded PDF file to an HTML.

Try it out in three steps

Add a PDF file named document.pdf to your project folder.
Run the code from the same folder.
Open result.html in your project folder to view the results.

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.html \
  --fail \
  -F file=@document.pdf \
  -F instructions='{
      "parts": [
        {
          "file": "file"
        }
      ],
      "output": {
        "type": "html"
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.html ^
  --fail ^
  -F file=@document.pdf ^
  -F instructions="{\"parts\": [{\"file\": \"file\"}], \"output\": {\"type\": \"html\"}}"

package com.example.pspdfkit;

import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;

import org.json.JSONArray;
import org.json.JSONObject;

import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;

public final class PspdfkitApiExample {
  public static void main(final String[] args) throws IOException {
    final RequestBody body = new MultipartBody.Builder()
      .setType(MultipartBody.FORM)
      .addFormDataPart(
        "file",
        "document.pdf",
        RequestBody.create(
          MediaType.parse("application/pdf"),
          new File("document.pdf")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "file")
            )
          )
          .put("output", new JSONObject()
            .put("type", "html")
          ).toString()
      )
      .build();

    final Request request = new Request.Builder()
      .url("https://api.nutrient.io/build")
      .method("POST", body)
      .addHeader("Authorization", "Bearer your_api_key_here")
      .build();

    final OkHttpClient client = new OkHttpClient()
      .newBuilder()
      .build();

    final Response response = client.newCall(request).execute();

    if (response.isSuccessful()) {
      Files.copy(
        response.body().byteStream(),
        FileSystems.getDefault().getPath("result.html"),
        StandardCopyOption.REPLACE_EXISTING
      );
    } else {
      // Handle the error
      throw new IOException(response.body().string());
    }
  }
}

using System;
using System.IO;
using System.Net;
using RestSharp;

namespace PspdfkitApiDemo
{
  class Program
  {
    static void Main(string[] args)
    {
      var client = new RestClient("https://api.nutrient.io/build");

      var request = new RestRequest(Method.POST)
        .AddHeader("Authorization", "Bearer your_api_key_here")
        .AddFile("file", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "file"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "html"
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.html");
            responseStream.CopyTo(outputFileWriter);
          }
        }
        else
        {
          var responseStreamReader = new StreamReader(responseStream);
          Console.Write(responseStreamReader.ReadToEnd());
        }
      };

      client.Execute(request);
    }
  }
}

// This code requires Node.js. Do not run this code directly in a web browser.

const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')

const formData = new FormData()
formData.append('instructions', JSON.stringify({
  parts: [
    {
      file: "file"
    }
  ],
  output: {
    type: "html"
  }
}))
formData.append('file', fs.createReadStream('document.pdf'))

;(async () => {
  try {
    const response = await axios.post('https://api.nutrient.io/build', formData, {
      headers: formData.getHeaders({
        'Authorization': 'Bearer your_api_key_here'
      }),
      responseType: "stream"
    })

    response.data.pipe(fs.createWriteStream("result.html"))
  } catch (e) {
    const errorString = await streamToString(e.response.data)
    console.log(errorString)
  }
})()

function streamToString(stream) {
  const chunks = []
  return new Promise((resolve, reject) => {
    stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
    stream.on("error", (err) => reject(err))
    stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
  })
}

import requests
import json

response = requests.request(
  'POST',
  'https://api.nutrient.io/build',
  headers = {
    'Authorization': 'Bearer your_api_key_here'
  },
  files = {
    'file': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'file'
        }
      ],
      'output': {
        'type': 'html'
      }
    })
  },
  stream = True
)

if response.ok:
  with open('result.html', 'wb') as fd:
    for chunk in response.iter_content(chunk_size=8096):
      fd.write(chunk)
else:
  print(response.text)
  exit()

<?php

$FileHandle = fopen('result.html', 'w+');

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.nutrient.io/build',
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_POSTFIELDS => array(
    'instructions' => '{
      "parts": [
        {
          "file": "file"
        }
      ],
      "output": {
        "type": "html"
      }
    }',
    'file' => new CURLFILE('document.pdf')
  ),
  CURLOPT_HTTPHEADER => array(
    'Authorization: Bearer your_api_key_here'
  ),
  CURLOPT_FILE => $FileHandle,
));

$response = curl_exec($curl);

curl_close($curl);

fclose($FileHandle);

POST https://api.nutrient.io/build HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here

--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json

{
  "parts": [
    {
      "file": "file"
    }
  ],
  "output": {
    "type": "html"
  }
}
--customboundary
Content-Disposition: form-data; name="file"; filename="document.pdf"
Content-Type: application/pdf

(file data)
--customboundary--

Try it out

This example will convert your uploaded PDF file to an MD.

Try it out in three steps

Add a PDF file named document.pdf to your project folder.
Run the code from the same folder.
Open result.md in your project folder to view the results.

curl -X POST https://api.nutrient.io/build \
  -H "Authorization: Bearer your_api_key_here" \
  -o result.md \
  --fail \
  -F file=@document.pdf \
  -F instructions='{
      "parts": [
        {
          "file": "file"
        }
      ],
      "output": {
        "type": "markdown"
      }
    }'

curl -X POST https://api.nutrient.io/build ^
  -H "Authorization: Bearer your_api_key_here" ^
  -o result.md ^
  --fail ^
  -F file=@document.pdf ^
  -F instructions="{\"parts\": [{\"file\": \"file\"}], \"output\": {\"type\": \"markdown\"}}"

package com.example.pspdfkit;

import java.io.File;
import java.io.IOException;
import java.nio.file.FileSystems;
import java.nio.file.Files;
import java.nio.file.StandardCopyOption;

import org.json.JSONArray;
import org.json.JSONObject;

import okhttp3.MediaType;
import okhttp3.MultipartBody;
import okhttp3.OkHttpClient;
import okhttp3.Request;
import okhttp3.RequestBody;
import okhttp3.Response;

public final class PspdfkitApiExample {
  public static void main(final String[] args) throws IOException {
    final RequestBody body = new MultipartBody.Builder()
      .setType(MultipartBody.FORM)
      .addFormDataPart(
        "file",
        "document.pdf",
        RequestBody.create(
          MediaType.parse("application/pdf"),
          new File("document.pdf")
        )
      )
      .addFormDataPart(
        "instructions",
        new JSONObject()
          .put("parts", new JSONArray()
            .put(new JSONObject()
              .put("file", "file")
            )
          )
          .put("output", new JSONObject()
            .put("type", "markdown")
          ).toString()
      )
      .build();

    final Request request = new Request.Builder()
      .url("https://api.nutrient.io/build")
      .method("POST", body)
      .addHeader("Authorization", "Bearer your_api_key_here")
      .build();

    final OkHttpClient client = new OkHttpClient()
      .newBuilder()
      .build();

    final Response response = client.newCall(request).execute();

    if (response.isSuccessful()) {
      Files.copy(
        response.body().byteStream(),
        FileSystems.getDefault().getPath("result.md"),
        StandardCopyOption.REPLACE_EXISTING
      );
    } else {
      // Handle the error
      throw new IOException(response.body().string());
    }
  }
}

using System;
using System.IO;
using System.Net;
using RestSharp;

namespace PspdfkitApiDemo
{
  class Program
  {
    static void Main(string[] args)
    {
      var client = new RestClient("https://api.nutrient.io/build");

      var request = new RestRequest(Method.POST)
        .AddHeader("Authorization", "Bearer your_api_key_here")
        .AddFile("file", "document.pdf")
        .AddParameter("instructions", new JsonObject
        {
          ["parts"] = new JsonArray
          {
            new JsonObject
            {
              ["file"] = "file"
            }
          },
          ["output"] = new JsonObject
          {
            ["type"] = "markdown"
          }
        }.ToString());

      request.AdvancedResponseWriter = (responseStream, response) =>
      {
        if (response.StatusCode == HttpStatusCode.OK)
        {
          using (responseStream)
          {
            using var outputFileWriter = File.OpenWrite("result.md");
            responseStream.CopyTo(outputFileWriter);
          }
        }
        else
        {
          var responseStreamReader = new StreamReader(responseStream);
          Console.Write(responseStreamReader.ReadToEnd());
        }
      };

      client.Execute(request);
    }
  }
}

// This code requires Node.js. Do not run this code directly in a web browser.

const axios = require('axios')
const FormData = require('form-data')
const fs = require('fs')

const formData = new FormData()
formData.append('instructions', JSON.stringify({
  parts: [
    {
      file: "file"
    }
  ],
  output: {
    type: "markdown"
  }
}))
formData.append('file', fs.createReadStream('document.pdf'))

;(async () => {
  try {
    const response = await axios.post('https://api.nutrient.io/build', formData, {
      headers: formData.getHeaders({
        'Authorization': 'Bearer your_api_key_here'
      }),
      responseType: "stream"
    })

    response.data.pipe(fs.createWriteStream("result.md"))
  } catch (e) {
    const errorString = await streamToString(e.response.data)
    console.log(errorString)
  }
})()

function streamToString(stream) {
  const chunks = []
  return new Promise((resolve, reject) => {
    stream.on("data", (chunk) => chunks.push(Buffer.from(chunk)))
    stream.on("error", (err) => reject(err))
    stream.on("end", () => resolve(Buffer.concat(chunks).toString("utf8")))
  })
}

import requests
import json

response = requests.request(
  'POST',
  'https://api.nutrient.io/build',
  headers = {
    'Authorization': 'Bearer your_api_key_here'
  },
  files = {
    'file': open('document.pdf', 'rb')
  },
  data = {
    'instructions': json.dumps({
      'parts': [
        {
          'file': 'file'
        }
      ],
      'output': {
        'type': 'markdown'
      }
    })
  },
  stream = True
)

if response.ok:
  with open('result.md', 'wb') as fd:
    for chunk in response.iter_content(chunk_size=8096):
      fd.write(chunk)
else:
  print(response.text)
  exit()

<?php

$FileHandle = fopen('result.md', 'w+');

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://api.nutrient.io/build',
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_POSTFIELDS => array(
    'instructions' => '{
      "parts": [
        {
          "file": "file"
        }
      ],
      "output": {
        "type": "markdown"
      }
    }',
    'file' => new CURLFILE('document.pdf')
  ),
  CURLOPT_HTTPHEADER => array(
    'Authorization: Bearer your_api_key_here'
  ),
  CURLOPT_FILE => $FileHandle,
));

$response = curl_exec($curl);

curl_close($curl);

fclose($FileHandle);

POST https://api.nutrient.io/build HTTP/1.1
Content-Type: multipart/form-data; boundary=--customboundary
Authorization: Bearer your_api_key_here

--customboundary
Content-Disposition: form-data; name="instructions"
Content-Type: application/json

{
  "parts": [
    {
      "file": "file"
    }
  ],
  "output": {
    "type": "markdown"
  }
}
--customboundary
Content-Disposition: form-data; name="file"; filename="document.pdf"
Content-Type: application/pdf

(file data)
--customboundary--

PDF-to-markup API

Convert PDF files to HTML and Markdown using our PDF-to-markup API.

PDF-to-HTML API

Convert PDF files to HTML using our PDF-to-HTML API.

PDF-to-Markdown API

Convert PDF files to Markdown using our PDF-to-Markdown API.

One markup conversion hub

Use this page when the workflow is broadly about converting PDFs into markup outputs and the exact target format still needs to be chosen.

Built for API-driven output workflows

Connect broad markup-conversion questions to the exact HTML or Markdown task page. Then continue to onboarding, pricing, and Processor overview without dead ends.

Fast path to execution

Route markup workflows to getting started, Postman, and exact task pages so teams can move from evaluation to implementation quickly.

Choose the exact markup output

Move from broad markup conversion to HTML or Markdown

Continue to PDF-to-HTML when the workflow needs browser-ready markup, or to PDF-to-Markdown when the workflow needs Markdown output for RAG, search, and AI ingestion.

OPEN PDF-TO-HTML

Most common next steps

Connect markup conversion to getting started, pricing, and Processor overview

After identifying the right markup output, continue to getting started for API key setup, the Postman collection for the fastest first request, Processor API pricing for credits, or the Processor API overview for broader DWS evaluation.

OPEN GETTING STARTED

Choose the exact markup output

Move from broad markup conversion to HTML or Markdown

OPEN PDF-TO-HTML

Choose the exact output:

PDF to HTML For browser-ready markup

PDF to Markdown For RAG, search, and AI ingestion

Most common next steps:

Getting started For API key setup

Postman collection For the fastest first request

Processor API pricing For credits

Processor API overview For broader DWS evaluation