# extract.schema

> Fill a JSON Schema you supply from a PDF with a language model, validated against the schema.

> Coming soon. The hosted API is not live yet, and this page describes the planned service as of 16 November 2026. [Get notified](https://pdfluent.com/contact/?topic=hosted) when it opens.

Source: https://pdfluent.com/docs/api/reference/extract-schema/

Fill a JSON Schema you supply from a PDF with a language model, validated against the schema.

`POST /v1/extract/schema`

| | |
|---|---|
| Input | one file, sent as `multipart/form-data`; the optional `options` part is a JSON object |
| Output | JSON |
| Credits | credits per page by quality: `fast` 1, `auto` 3 |
| Limits | [size, page and time limits: no claim ID yet] |
| Reads or changes the document | reads only |
| Error statuses | 400, 413, 422, 500, 501, 504 (see [Errors](https://pdfluent.com/docs/api/errors/)) |

## Options

| Option | Type | Required | Default | Description |
|---|---|---|---|---|
| `instructions` | string | no |  | Extra guidance for the model, such as a date format or a currency. [limit: no claim ID yet]. |
| `model` | string | no |  | The model id. Only with your own model key (`x-byok-model-key`); our route runs `gemini-2.5-flash-lite` and refuses any other id. |
| `pages` | array of integer | no |  | One-based pages. Default: all pages. |
| `password` | string | no |  | Password of an encrypted document. |
| `quality` | string | no |  | How the text is read before the model sees it. Default `fast`. `fast`: Geometric extraction, no model, no OCR. The default. `auto`: `fast` plus OCR of scanned pages. Answers `quality_unavailable` (501) on a deployment without an OCR engine; it never reads `fast` in its place. |
| `schema` | any | yes |  | The JSON Schema to fill: an object schema, [limit: no claim ID yet] KB. The answer is validated against it; a field the document does not state is left out rather than invented. |

## Example

### curl

```sh
curl -sS -f -X POST "$PDFLUENT_API_URL/v1/extract/schema" \
  -H "x-api-key: $PDFLUENT_API_KEY" \
  -F file=@structured.pdf \
  -F 'options={"schema":{"type":"object","properties":{"title":{"type":"string"}}}}' \
  -o result.json
```

### Python

```python
import json
import os

import requests

options = {"schema": {"type": "object", "properties": {"title": {"type": "string"}}}}

parts = [
    ("file", ("structured.pdf", open("structured.pdf", "rb"))),
    ("options", (None, json.dumps(options))),
]

response = requests.post(
    os.environ["PDFLUENT_API_URL"] + "/v1/extract/schema",
    headers={"x-api-key": os.environ["PDFLUENT_API_KEY"]},
    files=parts,
)
response.raise_for_status()

with open("result.json", "wb") as out:
    out.write(response.content)
```

### Node.js

```js
import { openAsBlob } from 'node:fs';
import { writeFile } from 'node:fs/promises';

const form = new FormData();
form.append('file', await openAsBlob("structured.pdf"), "structured.pdf");
form.append('options', JSON.stringify({"schema":{"type":"object","properties":{"title":{"type":"string"}}}}));

const response = await fetch(process.env.PDFLUENT_API_URL + "/v1/extract/schema", {
  method: 'POST',
  headers: { 'x-api-key': process.env.PDFLUENT_API_KEY },
  body: form,
});
if (!response.ok) throw new Error(`${response.status} ${await response.text()}`);

await writeFile("result.json", Buffer.from(await response.arrayBuffer()));
```

The key goes in the `x-api-key` header; see [Authentication](https://pdfluent.com/docs/api/authentication/). Every response carries `x-pdfluent-pages` and `x-pdfluent-credits`.
