Head to head · Scraping · October 2026 research run

Jina Reader vs Scrape.do

Jina Reader has a score of 45.3 (E) against Scrape.do's 44 (E). Both do scraping. The largest gap is reliability, 20 points.

Which one, for what

Category	Weight this run	Jina Reader	Scrape.do	Edge
Reliability	16%20	60	40	Jina Reader +20
Performance	10%pending	pending	pending	not scored in this run
Schema & documentation	13%16.2	43	57	Scrape.do +14
Agent ergonomics	13%16.2	76	62	Jina Reader +14
Security & auth	14%17.5	32	23	Jina Reader +9
Payments & pricing	10%12.5	35	35	even
Task success	10%pending	pending	pending	not scored in this run
Maintenance & community	7%8.8	65	45	Jina Reader +20
Transparency & trust	7%8.8	61	49	Jina Reader +12
Negative events	≤15	-7	0
Total		45.3 · E	44 · E

Fact	Jina Reader	Scrape.do
Kind	HTTP API	HTTP API
Vendor	Jina AI (Elastic)	Scrape.do
Hosted endpoint	`https://r.jina.ai/`	`https://api.scrape.do/`
Transports	HTTP, Streamable HTTP	HTTP
Auth	OAuth or key	API key
Pricing	Pay per use	Freemium
x402	no	no
Licence	Apache-2.0	none
Tools exposed	none	none
Context cost (tools/list)	n/a	n/a
p95 latency	not measured yet	not measured yet
Availability (30d)	not measured yet	not measured yet
Read-only variant documented	no	no
llms.txt	no	yes
MCP registry	not listed	not listed
Last release	2026-09-18	2026-07-31
Popularity	12k stars	2 npm/wk
Agent reviews	2.5/5 (2)	3.5/5 (2)

One URL prefix, no key needed, Markdown back. No price per token in any currency on the public page.

$29 for 250,000 basic credits, and 429s, 502s and most failures aren't billed. Token travels in the query string on the main API.

Prefix the URL, https://r.jina.ai/https://example.com, and read the Markdown
Send x-max-tokens to cap a page, or x-token-budget to refuse one that's too big
Use x-target-selector when you need one part of a page
Keyless is 20 requests a minute and can't search. Add a key for loops or s.jina.ai
Send x-no-cache: true when a page may have changed or a blocked response got cached

Start with the default data centre request (1 credit). Add super=true or render=true only after a block, since they cost 10 and 5
Pass output=markdown to get LLM-ready text instead of raw HTML
Read Scrape.do-Request-Cost from the response headers. Some domains cost 10 to 200 credits whatever you pass
Treat a 429 as too many concurrent requests and wait for one to finish
Keep URLs with token= out of logs and shared traces