Reader /r/

Any public URL as Markdown in one GET. Add ?q= to keep only the chunks relevant to a question.

GET/r/{url}

Credits: 1

Any public URL as Markdown (text/markdown). Add ?q= to prune the page to the chunks relevant to a question.

Parameters

Name	In	Type	Required	Description
url	path	string	yes	Full http(s) URL. GitHub blob URLs are read as raw files, arXiv PDFs as their HTML versions.
q	query	string	no	Question or topic to prune to.

Example request

curl -si "https://api.contextfetch.dev/r/https://docs.python.org/3/library/asyncio-task.html?q=task+groups" \  -H "Authorization: Bearer YOUR_API_KEY"

Example response

HTTP/2 200
content-type: text/markdown; charset=utf-8
x-token-savings: 91.0
x-raw-tokens: 18240
x-output-tokens: 1650

## Task Groups
...

Response headers

Header	Meaning
X-Token-Savings	Percent saved: Markdown vs raw HTML, or pruned vs full Markdown when q is given.
X-Raw-Tokens	Tokens before, ceil(chars / 4).
X-Output-Tokens	Tokens returned.
X-Credits-Remaining	On every billable response: free requests left today for keyless calls, credits left for a paid key.

Errors

Status	Body	When
400	`{"error": "url_not_allowed"}`	The URL is not public http(s): private, loopback, link-local and similar addresses are rejected, also after redirects.
401	`{"error": "invalid_api_key"}`	The key is unknown.
402	`{"error": "insufficient_credits" \| "keyless_limit", "message": "...", "checkout_url": "...", "pricing": {...}, "packs": [...], "action": {"type": "payment_link", "url": "https://api.contextfetch.dev/buy/instant", "prompt_to_user": "..."}}`	Out of credits, or the keyless allowance is used up. Also sends X-Payment-URL.
502	`{"error": "fetch_failed", "message": "..."}`	The target page could not be fetched.