Extract

POST /v1/extract

Base URL https://api.tilion.dev. Every request needs Authorization: Bearer $TILION_API_KEY. Extract runs the same pipeline as Fetch, then converts the result to clean markdown instead of raw text. Use it when the content is headed for a model context.

Field	Type	Default	Notes
`session_id`	string	required	An existing session
`url`	string	required	Public `http`/`https` only

Request

{ "session_id": "sess_...", "url": "https://example.com" }

Response

{
  "session_id": "sess_...",
  "final_url": "https://example.com/",
  "status": "ok",
  "title": "Example Domain",
  "markdown": "# Example Domain\n\n...",
  "markdown_len": 812,
  "tokens_estimate": 203
}

tokens_estimate is a rough token count for budgeting the context window before you send the markdown to a model. A successful call returns status: "ok" with non-empty markdown. Extract is synchronous and does not take async_mode. Errors match Fetch.

curl -X POST https://api.tilion.dev/v1/extract \
  -H "Authorization: Bearer $TILION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"session_id":"'"$SESSION_ID"'","url":"https://example.com"}'

Get started

MCP

Sessions

Fetch & jobs

Content

Agent & tasks

Live view & recordings

Account

Reference

Request

Response

​Request

​Response

Request

Response