Skip to main content
POST
/
extract
/
ebook
Extract ebooks
curl --request POST \
  --url https://api.horizon.new/v1/extract/ebook \
  --header 'Content-Type: application/json' \
  --data '{
  "sourceUrl": "<string>",
  "sourceName": "<string>",
  "options": {},
  "webhookUrl": "<string>"
}'
{
  "jobId": "job_01hx9q9",
  "status": "queued",
  "statusUrl": "<string>",
  "result": {},
  "etaSeconds": 123,
  "jobType": "extract/pdf"
}
Turn EPUB and MOBI ebooks into normalized text chunks. Horizon parses chapters and front/back matter to preserve structure for downstream retrieval and question-answering.

​
Request body

  • sourceUrl — HTTPS or signed URL pointing to the ebook archive. Required if file is not provided.
  • file — Optional uploaded EPUB or MOBI file (multipart/form-data).
  • sourceName — Optional label saved with the extracted records.
  • options — Optional object. Supported keys:
    • segmentLength — Target characters per chunk (default 1000).
    • includeTableOfContents — Boolean; append TOC entries to each chunk (default true).
    • language — ISO language hint for sentence segmentation.
  • webhookUrl — Optional HTTPS URL Horizon should call when the extraction finishes.

​
Sample request

curl https://api.horizon.new/v1/extract/ebook \
  -H "Content-Type: application/json" \
  -d '{
    "sourceUrl": "https://cdn.example.com/library/field-guide.epub",
    "sourceName": "Field Guide to Horizon",
    "options": {
      "segmentLength": 1600,
      "includeTableOfContents": true,
      "language": "en"
    }
  }'

# or upload the raw EPUB/MOBI

curl https://api.horizon.new/v1/extract/ebook \
  -H "Content-Type: application/json" \
  -d '{
    "file": "data:application/epub+zip;base64,UEsDBBQAAAAIA...",
    "sourceName": "Field Guide to Horizon",
    "options": {
      "segmentLength": 1600,
      "includeTableOfContents": true,
      "language": "en"
    }
  }'

​
Response

Returns 202 Accepted with jobId, status, and statusUrl. When processing finishes quickly, the normalized chapter chunks appear in result.

​
Notes

  • Inline images are ignored; image captions are captured when present.
  • TOC entries are mapped into chunk attributes (chapter, section).
  • Use signed URLs that remain valid for several minutes; larger ebooks can take up to 5 minutes to process.
  • Poll GET /jobs/{jobId} (identical to statusUrl) if you need to check progress or refetch the normalized chunks.
  • To upload the ebook directly, send multipart/form-data with a file field instead of sourceUrl.

​
x402 flow

Ebook extraction is billed per archive through Coinbase’s x402 protocol. If funding is required, Horizon issues: 
HTTP/1.1 402 Payment Required
Content-Type: application/json

{
  "x402Version": 1,
  "accepts": [
    {
      "scheme": "exact",
      "network": "base-sepolia",
      "maxAmountRequired": "160000",
      "resource": "POST /extract/ebook",
      "description": "Horizon ebook extraction",
      "mimeType": "application/json",
      "payTo": "0xYourReceivingWallet",
      "maxTimeoutSeconds": 300,
      "asset": "0xYourUSDCContract",
      "extra": {
        "name": "USDC",
        "version": "1"
      }
    }
  ],
  "error": null
}
Forward the accepts data to your facilitator, complete the /verify and /settle cycle, then retry the call with the Base64 payload in X-PAYMENT. Horizon resumes the job and includes X-PAYMENT-RESPONSE when settlement succeeds.

Body

application/json

Provide either sourceUrl or file.

​
sourceUrl
string<uri>
​
sourceName
string
​
options
object

Extraction hints such as language, segmentLength, transcriptionModel, or sheet preferences depending on the endpoint.

​
webhookUrl
string<uri>

Webhook to call when the extraction completes.

​
file
file

Upload the raw file instead of providing sourceUrl.

Response

Extraction job accepted

​
jobId
string
required
Example:

"job_01hx9q9"

​
status
enum<string>
required
Available options:
queued,
processing,
completed,
failed
​
statusUrl
string<uri>
required

Canonical link to GET /jobs/{jobId} for this job.

​
jobType
string
required
Example:

"extract/pdf"

​
result
object | null

Present when the job completes synchronously.

​
etaSeconds
integer | null

Estimated seconds until completion.