Extract data from URL

Authorization

bearerAuth

AuthorizationBearer <token>

API key authentication. Include your API key in the Authorization header as Bearer rf_your_key.

In: header

Request Body

application/json

cleaner_chain?array<>|

Content cleaner chain (default: [markdown])

fetch_mode?string

Fetch mode: auto, static, or dynamic

Default"auto"

Value in"auto" | "static" | "dynamic"

llm_config?

Optional LLM configuration override

schema*unknown

Extraction instructions - either a structured schema (YAML/JSON with 'name' and 'fields') or freeform natural language prompt. The API auto-detects the format and returns 'input_format' in the response.

Length1 <= length

url*string

URL to extract data from

Length1 <= length

webhook?

Inline ephemeral webhook configuration

webhook_id?string

ID of a saved webhook to call on completion

webhook_url?string

Simple webhook URL (backward compatible)

Formaturi

[key: string]?never

Response Body

`application/json`

`application/problem+json`

curl -X POST "https://api.refyne.uk/api/v1/extract" \
  -H "Content-Type: application/json" \
  -d '{
    "schema": "string",
    "url": "string"
  }'

curl -X POST "https://api.refyne.uk/api/v1/extract" \  -H "Content-Type: application/json" \  -d '{    "schema": "string",    "url": "string"  }'

{
  "data": null,
  "fetched_at": "string",
  "input_format": "string",
  "job_id": "string",
  "metadata": {
    "extract_duration_ms": 0,
    "fetch_duration_ms": 0,
    "model": "string",
    "provider": "string"
  },
  "url": "string",
  "usage": {
    "cost_usd": 0.1,
    "input_tokens": 0,
    "is_byok": true,
    "llm_cost_usd": 0.1,
    "output_tokens": 0
  }
}

{
  "detail": "Property foo is required but is missing.",
  "errors": [
    {
      "location": "string",
      "message": "string",
      "value": null
    }
  ],
  "instance": "https://example.com/error-log/abc123",
  "status": 400,
  "title": "Bad Request",
  "type": "https://example.com/errors/example"
}