> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cloudraker.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cloudraker.com/_mcp/server.

# Extract structured data from documents

POST https://api.cloudraker.com/v1/spaces/{spaceId}/extract
Content-Type: application/json

Runs JSON-Schema extraction with per-field citations over one or more files.

Send exactly one of `file` or `files`, and at most one output shape:

* **`schema`** — an inline JSON Schema object, written in the [extraction schema dialect](https://docs.cloudraker.com/capabilities/extract/schema).
* **`action`** — a [saved action](https://docs.cloudraker.com/api/cloud-raker-api/actions/get-action) by id or slug. Inline config fields (`instructions`, `unit`, `judge`, …) are merged over the saved action's, so one saved action can be refined per call.
* **neither** — the shape is inferred from the documents themselves. Add `hints` to steer it in prose. The finished run reports what was inferred as `config.schema`, ready to save as an action for the next run.

**What you get back.** `output.value` holds the extracted object for a single-document run, `output.documents[]` one entry per file. Send `citations: true` to ground the result: `output.citations` then maps each extracted field to where it came from — `fileId` plus page and bounding box, or a timecode for audio, or `notFound: true` for a value the documents do not contain.

Add `?output=inline` to include each source file's parsed `markdown` and `json` alongside the extracted value. Signed `markdownUrl` / `jsonUrl` fields remain available; when the combined parsed source exceeds 1 MiB, the response falls back to those URLs only.

```json
{
  "file": { "url": "https://www.irs.gov/pub/irs-pdf/fw9.pdf" },
  "schema": {
    "type": "object",
    "properties": {
      "business_name": { "type": ["string", "null"] },
      "tax_classification": { "type": ["string", "null"] }
    }
  }
}
```

### Waiting for the result

Sync by default: the call holds open until the run finishes, up to `?wait=` seconds (default `60`, max `120`, `0` returns immediately).

| Outcome                    | Response                                                 |
| -------------------------- | -------------------------------------------------------- |
| Finished inside the window | `200` with the full run                                  |
| Still running at the cap   | `202` with `{object, id, status, statusUrl}`             |
| Parked for a human         | `202` right away, `status: "needs_input"` plus `tasks[]` |

The `202` is a graceful degrade, never an error — poll [the run](https://docs.cloudraker.com/api/cloud-raker-api/runs/get-run) or wait for a [webhook](https://docs.cloudraker.com/api/cloud-raker-api/webhooks/create-webhook-endpoint). Replaying an `idempotency-key` returns the original run alongside an `idempotent-replay: true` response header.

**Learn more:** [Extraction guide](https://docs.cloudraker.com/capabilities/extract) · [Schema dialect](https://docs.cloudraker.com/capabilities/extract/schema)

Reference: https://docs.cloudraker.com/api/cloud-raker-api/spaces/space-extract

## Authentication

- `Authorization` header (bearer token, required)

## Request

### Path parameters

- `spaceId` (string, required)

### Query parameters

- `wait` (integer, optional, default: 60) — How many seconds to hold the request open waiting for the run to finish. Finishing inside the window returns `200` with the full run; running past it returns `202` with a `statusUrl` to poll. Send `0` to skip waiting entirely and always get the `202`.
- `output` (enum, optional, default: urls) — How parsed source content is returned. `urls` returns signed download URLs. `inline` also returns markdown and parsed JSON when their combined payload is at most 1 MiB; larger content falls back to the URLs only.
  - Allowed values: `urls`, `inline`

### Body (application/json)

- `schema` (map from string to any, optional) — The shape to extract, as a JSON Schema object. Send `action` instead to use a saved shape, or neither to have one inferred. The root must be `{"type": "object"}`. The dialect is deliberately narrow — no `$ref`, `$defs`, `oneOf`, `anyOf`, `allOf`, `const` or `pattern` — with a maximum nesting depth of 5 and a 64 KB size limit. Make primitives nullable (`{"type": ["string", "null"]}`) so a missing value reads as `null` rather than a hallucination.
- `action` (string, optional) — A saved action to run, by id or slug. An alternative to `schema`. The action carries the output shape and any saved settings. Config you send inline on the same call is merged over it, so `action` plus `instructions` refines a saved action for one run without redefining it.
- `hints` (string, optional) — Prose guidance for **schema inference** — only valid when you send neither `schema` nor `action`. Say what the documents are and what matters in them ("freight bills of lading; I care about the load number, the shipper and the total") and the shape is inferred from the document itself. Sending `hints` alongside `schema` or `action` is a `400`: the shape is already decided.
- `instructions` (string, optional) — Free-form guidance for the extraction, applied on top of the schema — house rules, formatting preferences, how to handle ambiguity.
- `citations` (boolean, optional) — Whether to ground each extracted value in the source document. Off by default — grounding is an explicit add-on, so send `citations: true` to ask for it. When on, `output.citations` maps every extracted field to where it came from — `fileId` plus page and bounding box for documents, or a timecode for audio. A field the documents simply do not contain comes back as an entry with `notFound: true` and no location.
- `unit` (enum, optional) — What one extraction result covers. - `per_document` — one result object per file (the default). - `across_documents` — one result object for the whole set, read as a single body of evidence. - `rows_per_document` — a list of results per file, for documents that hold repeated records.
  - Allowed values: `per_document`, `across_documents`, `rows_per_document`
- `model` (string, optional) — Pin the extraction to a specific model. Leave it unset to use the current default, which tracks the best available.
- `judge` (boolean, optional) — Run a second review pass over the extracted values to catch mistakes. Slower and more thorough — worth it on documents where an error is expensive.
- `file` (object or object, optional) — A single input file. Send this or `files`, never both.
  - object
    - `url` (string, required)
    - `name` (string, optional)
    - `processing` (enum, optional)
      - Allowed values: `auto`, `ocr`, `simple`, `transcribe`, `transcribe_diarize`
  - object
    - `id` (string, required)
- `files` (list of object or object, optional) — Several input files, up to 100. Send this or `file`, never both. Each file gets its own entry in `output.documents[]` unless `unit` says otherwise.
  - object
    - `url` (string, required)
    - `name` (string, optional)
    - `processing` (enum, optional)
      - Allowed values: `auto`, `ocr`, `simple`, `transcribe`, `transcribe_diarize`
  - object
    - `id` (string, required)
- `metadata` (map from string to any, optional) — Arbitrary JSON you attach to the run and get back on every read of it. Use it to carry your own identifiers — an order number, a customer id — so a webhook or a polled run reconciles without a lookup table. Capped at 10 KB serialized.
- `webhook` (object or object, optional) — Where to deliver this run's events, given one of two ways. * `{ "url": "…" }` — a one-off https endpoint for this run only. * `{ "id": "whe_…" }` — a saved endpoint from `POST /v1/webhooks`. Runs hold the reference, so pausing or re-pointing that endpoint applies to this run too. Deliveries are at-least-once and signed — dedupe on `eventId` and verify against `GET /v1/webhooks/jwks.json`.
  - object
    - `url` (string, required)
  - object
    - `id` (string, required)
- `ttl` (integer, optional, default: 86400) — How long, in seconds, to keep this run and its files before purging them automatically. The maximum is 604800 (7 days). The deadline comes back as `expiresAt` on every read of the run. Call `POST /v1/runs/{id}/keep` before then to clear the TTL and move the results into a space permanently. E-signature runs are exempt — an envelope waits for its signers however long that takes.

## Response

### 200

The finished run.

- `object` ("extract_run", required)
- `id` (string, required)
- `status` (enum, required) — Where the run is in its life. | Status | Meaning | | --- | --- | | `queued` | Accepted, not started | | `processing` | Work in flight | | `needs_input` | Parked for a person — see `tasks[]` | | `processed` | Finished; `output` is populated | | `failed` | Finished unsuccessfully | | `cancelled` | Stopped on request | | `expired` | TTL elapsed and the data was purged | The last four are terminal.
  - Allowed values: `queued`, `processing`, `processed`, `failed`, `cancelled`, `expired`, `needs_input`
- `expiresAt` (string, required, nullable)
- `statusUrl` (string, required)
- `files` (list of object, required)
  - `id` (string, required)
  - `name` (string, required)
  - `status` (string, required)
  - `error` (string, optional)
- `file` (object, optional)
  - `id` (string, required)
  - `name` (string, required)
  - `status` (string, required)
  - `error` (string, optional)
- `error` (object, optional) — Why the run failed. Present whenever `status` is `failed`, and only then. `code` is the stable, snake_case reason (`input_unavailable`, `parse_failed`, …); `message` is the human-readable detail. Per-file and per-step failures are also reported in `files[].error` and, for a pipeline, `steps[].error`.
  - `code` (string, required)
  - `message` (string, required)
- `metadata` (map from string to any, optional)
- `tasks` (list of object, optional) — The human steps currently blocking the run. Present while `status` is `needs_input`. Each task has a `url` — a ready-made page you can send a person to — or you can drive it yourself through `GET` and `POST /v1/runs/{id}/task`. E-signature runs never carry `tasks[]`: their signing links are signer-held secrets, so use `envelopeUrl` instead.
  - `id` (string, required)
  - `title` (string, required)
  - `url` (string, required)
- `config` (object, optional) — The output shape this run actually applied. On an inference run — one sent with neither `schema` nor `action` — this is where you read the schema that was inferred, ready to review and save as an action for the next run.
  - `schema` (map from string to any, required)
- `output` (object, optional) — The extracted data. Present once `status` is `processed`. `documents[]` always has one entry per input file. For a single-document run, `value`, `citations` and any parsed source fields are lifted to the top as aliases of `documents[0]` so the common case reads without indexing. Parsed source fields are present only when requested with `?output=inline`. The signed URLs remain as a fallback; `markdown` and `json` are omitted when the combined inline source exceeds 1 MiB.
  - `documents` (list of object, required)
    - `fileId` (string, required)
    - `name` (string, required)
    - `status` (string, required)
    - `error` (string, optional)
    - `value` (any, optional)
    - `citations` (map from string to list of object, optional) — Where each extracted value came from, keyed by the field it backs. Keys are the top-level field keys of `value` (`load_number`); for a `rows_per_document` run they are prefixed with the row index, `[0].description`. Each entry names the `fileId` and, when known, the `page` and `bbox` — or a `timecode` for audio — plus the matched `text` and a `confidence` score. An entry with `notFound: true` instead records that the value is not present in the documents at all. Present whenever the run was grounded. Send `citations: true` on the request to ask for it.
      - `fileId` (string, required)
      - `page` (double, optional)
      - `bbox` (object, optional)
        - `x` (double, required)
        - `y` (double, required)
        - `width` (double, required)
        - `height` (double, required)
      - `timecode` (double or string, optional)
      - `text` (string, optional)
      - `confidence` (double, optional)
      - `notFound` (boolean, optional) — The value is not present in the source. The entry names the `fileId` it was checked against but carries no `page`, `bbox`, `timecode` or `text`.
    - `markdownUrl` (string, optional)
    - `jsonUrl` (string, optional)
    - `markdown` (string, optional)
    - `json` (any, optional)
  - `value` (any, optional)
  - `citations` (map from string to list of object, optional) — Where each extracted value came from, keyed by the field it backs. Keys are the top-level field keys of `value` (`load_number`); for a `rows_per_document` run they are prefixed with the row index, `[0].description`. Each entry names the `fileId` and, when known, the `page` and `bbox` — or a `timecode` for audio — plus the matched `text` and a `confidence` score. An entry with `notFound: true` instead records that the value is not present in the documents at all. Present whenever the run was grounded. Send `citations: true` on the request to ask for it.
    - `fileId` (string, required)
    - `page` (double, optional)
    - `bbox` (object, optional)
      - `x` (double, required)
      - `y` (double, required)
      - `width` (double, required)
      - `height` (double, required)
    - `timecode` (double or string, optional)
    - `text` (string, optional)
    - `confidence` (double, optional)
    - `notFound` (boolean, optional) — The value is not present in the source. The entry names the `fileId` it was checked against but carries no `page`, `bbox`, `timecode` or `text`.
  - `citationsOmitted` (boolean, optional) — The citations were dropped because the result exceeded the size budget.
  - `markdownUrl` (string, optional)
  - `jsonUrl` (string, optional)
  - `markdown` (string, optional)
  - `json` (any, optional)

### 202

Accepted — still running, or awaiting human input.

- `object` (string, required)
- `id` (string, required)
- `status` (enum, required) — Where the run is in its life. | Status | Meaning | | --- | --- | | `queued` | Accepted, not started | | `processing` | Work in flight | | `needs_input` | Parked for a person — see `tasks[]` | | `processed` | Finished; `output` is populated | | `failed` | Finished unsuccessfully | | `cancelled` | Stopped on request | | `expired` | TTL elapsed and the data was purged | The last four are terminal.
  - Allowed values: `queued`, `processing`, `processed`, `failed`, `cancelled`, `expired`, `needs_input`
- `statusUrl` (string, required)
- `envelopeUrl` (string, optional)
- `tasks` (list of object, optional)
  - `id` (string, required)
  - `title` (string, required)
  - `url` (string, required)

## Examples

### Example 1

**Request**

```json
{}
```

**Response**

```json
{
  "object": "string",
  "id": "string",
  "status": "queued",
  "expiresAt": "string",
  "statusUrl": "string",
  "files": [
    {
      "id": "string",
      "name": "string",
      "status": "string",
      "error": "string"
    }
  ],
  "file": {
    "id": "string",
    "name": "string",
    "status": "string",
    "error": "string"
  },
  "error": {
    "code": "string",
    "message": "string"
  },
  "metadata": {},
  "tasks": [
    {
      "id": "string",
      "title": "string",
      "url": "string"
    }
  ],
  "config": {
    "schema": {}
  },
  "output": {
    "documents": [
      {
        "fileId": "string",
        "name": "string",
        "status": "string",
        "error": "string",
        "citations": {},
        "markdownUrl": "string",
        "jsonUrl": "string",
        "markdown": "string"
      }
    ],
    "citations": {},
    "citationsOmitted": true,
    "markdownUrl": "string",
    "jsonUrl": "string",
    "markdown": "string"
  }
}
```

**SDK Code**

```typescript
import { CloudRakerClient } from "@cloudraker/api";

async function main() {
    const client = new CloudRakerClient({
        token: "YOUR_TOKEN_HERE",
    });
    await client.spaces.spaceExtract({
        spaceId: "spaceId",
        body: {},
    });
}
main();

```

```python
from cloudraker import CloudRaker

client = CloudRaker(
    token="YOUR_TOKEN_HERE",
)

client.spaces.space_extract(
    space_id="spaceId",
)

```

```go
package main

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

func main() {

	url := "https://api.cloudraker.com/v1/spaces/spaceId/extract"

	payload := strings.NewReader("{}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.cloudraker.com/v1/spaces/spaceId/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.cloudraker.com/v1/spaces/spaceId/extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.cloudraker.com/v1/spaces/spaceId/extract', [
  'body' => '{}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.cloudraker.com/v1/spaces/spaceId/extract");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.cloudraker.com/v1/spaces/spaceId/extract")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```

### Example 2

**Request**

```json
{}
```

**Response**

```json
{
  "object": "string",
  "id": "string",
  "status": "queued",
  "expiresAt": "string",
  "statusUrl": "string",
  "files": [
    {
      "id": "string",
      "name": "string",
      "status": "string",
      "error": "string"
    }
  ],
  "file": {
    "id": "string",
    "name": "string",
    "status": "string",
    "error": "string"
  },
  "error": {
    "code": "string",
    "message": "string"
  },
  "metadata": {},
  "tasks": [
    {
      "id": "string",
      "title": "string",
      "url": "string"
    }
  ],
  "config": {
    "schema": {}
  },
  "output": {
    "documents": [
      {
        "fileId": "string",
        "name": "string",
        "status": "string",
        "error": "string",
        "citations": {},
        "markdownUrl": "string",
        "jsonUrl": "string",
        "markdown": "string"
      }
    ],
    "citations": {},
    "citationsOmitted": true,
    "markdownUrl": "string",
    "jsonUrl": "string",
    "markdown": "string"
  }
}
```

**SDK Code**

```typescript
import { CloudRakerClient } from "@cloudraker/api";

async function main() {
    const client = new CloudRakerClient({
        token: "YOUR_TOKEN_HERE",
    });
    await client.spaces.spaceExtract({
        spaceId: "spaceId",
        body: {},
    });
}
main();

```

```python
from cloudraker import CloudRaker

client = CloudRaker(
    token="YOUR_TOKEN_HERE",
)

client.spaces.space_extract(
    space_id="spaceId",
)

```

```go
package main

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

func main() {

	url := "https://api.cloudraker.com/v1/spaces/spaceId/extract"

	payload := strings.NewReader("{}")

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

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.cloudraker.com/v1/spaces/spaceId/extract")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{}"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.cloudraker.com/v1/spaces/spaceId/extract")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{}")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.cloudraker.com/v1/spaces/spaceId/extract', [
  'body' => '{}',
  'headers' => [
    'Authorization' => 'Bearer <token>',
    'Content-Type' => 'application/json',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.cloudraker.com/v1/spaces/spaceId/extract");
var request = new RestRequest(Method.POST);
request.AddHeader("Authorization", "Bearer <token>");
request.AddHeader("Content-Type", "application/json");
request.AddParameter("application/json", "{}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
let parameters = [] as [String : Any]

let postData = JSONSerialization.data(withJSONObject: parameters, options: [])

let request = NSMutableURLRequest(url: NSURL(string: "https://api.cloudraker.com/v1/spaces/spaceId/extract")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```