---
title: "Context API / Parse Bytes"
description: "Context.dev tool context-dev-parse on looot: input fields, $0.0025 per call, output shape, and code to run it with curl, JavaScript or Python."
sidebar:
  hidden: true
---

{/* Generated by scripts/generate-api-reference.mjs from data/api-reference.json. Do not edit. */}

Converts raw text, source code, web/data, PDF, Microsoft Office, and image bytes into LLM-usable Markdown.

- **Tool id:** `context-dev-parse`
- **Provider:** [Context.dev](/providers/context-dev)
- **Job:** [Get parse](/reference/jobs/parse-get) (`parse.get`)
- **Price:** $0.0025 per call. A call that fails at the provider costs $0.

## Inputs

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `client` | string | no | Optional client identifier used for usage attribution. |
| `extension` | string | no | Optional file extension hint, such as pdf, docx, xlsx, pptx, html, json, csv, md, py, rtf, jpg, png, or txt. |
| `includeImages` | boolean | no | Include image references in Markdown output |
| `includeLinks` | boolean | no | Preserve hyperlinks in Markdown output |
| `ocr` | boolean | no | When true for PDF inputs, OCR the selected pages that have no usable text layer (scans), replacing each recovered page's text with the OCR result while pages with a real text layer keep it. pdf.start/pdf.end limit the inclusive page range. Billed at 1 credit per page OCR actually recovered, on top of the base request cost. When false, no OCR runs. |
| `pdf` | string | no | PDF page-range options as a JSON object, e.g. \{"start": 2, "end": 5\}. |
| `shortenBase64Images` | boolean | no | Shorten base64-encoded image data in the Markdown output |
| `tags` | array | no | Optional tags for tracking usage. Up to 20 tags, each 1 to 50 characters. |
| `useMainContentOnly` | boolean | no | Extract only the main content from HTML-like inputs |
| `zdr` | string | no | Set to enabled to bypass shared caches and omit request and response content from retained usage logs. Requires zero data retention to be enabled for your organization (contact support@context.dev), otherwise the request fails with ZDR_NOT_ENABLED. Successful ZDR responses include X-Context-ZDR: true. |

## Output

The run's `result` holds the provider's answer. Signed in, `looot inspect context-dev-parse` prints its fields.

## Run it

Every call needs your API token in `LOOOT_TOKEN`; [Sign in](/get-started/sign-in#use-the-token-in-scripts-and-agents) shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With `wait: 30` the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll `GET /v1/runs/<runId>`.

Example input with placeholder values:

<CodeGroup>

```bash curl
curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"context-dev-parse","input":{"tags":["production","team-alpha"]},"wait":30}'
```

```js JavaScript
const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "context-dev-parse",
    input: {
      tags: ["production", "team-alpha"],
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);
```

```python Python
import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "context-dev-parse",
        "input": {
            "tags": ["production", "team-alpha"],
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))
```

</CodeGroup>

To let looot pick among every provider of this job instead, send `job:parse.get` as `endpointId`; see [the job page](/reference/jobs/parse-get).