Head to head · Scraping · October 2026 research run

Jina Reader vs Scrape.do

Jina Reader scores 54.1 (C) on agent readiness against Scrape.do's 44.5 (E), and leads in 6 of 7 scored categories. Both do scraping.

Best web scraping and crawling APIs for AI agents · All 567 scrapers comparisons

Which one, for what

Jina Reader C

Best for Agents that read the web a page at a time and want to bound the tokens.

Ahead on

  • Reliability, 70 against 40
  • Schema & documentation, 77 against 57
  • Agent ergonomics, 80 against 62
  • Security & auth, 32 against 23
  • Maintenance & community, 45 against 25
  • Transparency & trust, 62 against 49

Also in its favour

  • Open source

Watch for

No price per token in any currency on the public page

Scrape.do E

Best for Cheap bulk fetching through rotating proxies when you call HTTP directly and keep the token server-side.

Also in its favour

  • Free to start without a card
  • Rated higher by the reviewer agents, 3.5 against 2.5 out of 5
  • No incidents deducted, where Jina Reader loses 7 points for them

Watch for

Token travels in the query string on the main API

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Reliability Jina Reader +30

Jina Reader 70

Atlassian Statuspage at status.jina.ai with automated incidents per service (per the 1 October check, not re-read on 5 November because Jina's terms bar automated extraction from its website) (20). On 1 October the feed reached back only to 15 September 2026. In that window r.jina.ai had no incidents and s.jina.ai had eight five-minute ones. Minor only, less 5 for the short window. The rest of the 90 days couldn't be read, so the recorded award is carried (15 of 30). Rate limits published, Reader 20 a minute without a key, 500 with a key and 5,000 premium, Search 100 and 1,000, and the API reference repeats the keyed figures (15). Jina's merged OpenAPI file (docs.jina.ai/openapi.json), published on 14 October 2026 and linked from the API reference, read from the jina-ai/meta-prompt repository that builds the docs, types the 429 answer for Reader as RateLimitTriggeredError with retryAfter seconds and a retryAfterDate. No backoff guidance, and Reader takes no writes (10). No SLA found (0). GA (10).

Scrape.do 40

No public status page. status.scrape.do returned 403 on 30 September and 1 October and the site doesn't link it (0). No readable incident history, so 5 by the rubric (5). Concurrency published per plan, 5 on Free, 10 on Hobby, 50 on Pro, 100 on Business and 200 on Advanced (15). A 429 means the concurrency limit was hit and isn't billed, a 502 says to try again, and the service retries failed requests itself unless disableRetry=true, with no Retry-After or backoff guidance (10). No SLA on the pricing page, which claims a 99.98 per cent success rate instead (0). GA (10). All per the 1 October check, not re-read on 5 November, since Scrape.do's terms bar automated access to its website. 0+5+15+10+0+10 = 40.

Schema & documentation Jina Reader +20

Jina Reader 77

Jina's merged OpenAPI file (docs.jina.ai/openapi.json), published on 14 October 2026 and linked from the API reference, read from the jina-ai/meta-prompt repository that builds the docs, covers the Reader paths (GET and POST on r.jina.ai) with 98 typed parameters each and a typed response for every status. The Markdown reference at docs.jina.ai/api.md, read on that host on 2 November 2026 for the Jina Embeddings listing before Jina's terms paused it, names the file in its text, which the repository's history shows it has carried since 14 October (25). The reference is also published as Markdown at docs.jina.ai/api.md, and docs.jina.ai answers curl with a plain-text guide written for coding agents, per the same repository. The Reader README is a full Markdown reference of every header (10). The README says when to use each option and gives a troubleshooting order (key, no cache, browser engine, proxy) (14 of 20). Options are headers or query parameters with documented values, such as engine browser, direct or cf-browser-rendering, though many spec parameters carry no description, and the MCP tools have typed schemas (11 of 15). curl examples and a cookbook, and the spec names an error body for each status, among them BudgetExceededError and RateLimitTriggeredError with a code and a readable message, but no recovery prose (11 of 15). No API changelog. The README carries a dated updates list, last April 2026, and the spec version is 2026.10.13.1624 (6 of 15).

Scrape.do 57

No OpenAPI file found (0 of 25). llms.txt at scrape.do/documentation/llms.txt with Markdown pages (10). The docs say when to switch on super or render and which domains turn them on server-side (12 of 20). Parameters documented with ranges, such as retry timeout 5,000 to 55,000 ms, but they're query strings with no schema (10 of 15). A status-code table that says which codes consume credits, and examples in several languages. The error body format isn't documented (13 of 15). Dated public changelog, no API versioning (12 of 15, held as a partial). All per the 1 October check, not re-read on 5 November. 0+10+12+10+13+12 = 57.

Maintenance & community Jina Reader +20

Jina Reader 45

The API reference Jina builds in the jina-ai/meta-prompt repository records dated changes to Reader's published interface since it first appeared on 14 October, with /echo paths added on 21 October and the webBotAuth parameter and Web Bot Auth paths on 23 October 2026, the newest dated API change. The MCP server's last version, 1.10.0, is dated 18 September (30). The MCP versions 1.5.0 to 1.10.0 between 11 August and 18 September are untagged bumps in package.json with no changelog, and the 14 and 15 October MCP commits carry no version, so none count as releases. The reference changes carry no version or changelog entry either (0). 22 open Reader issues on 1 October, including the two SSRF reports from June and a token-usage spike from April, with no fix in the repository, not re-read because the issue pages refuse us (5 of 25). No official SDK, the MCP server is the maintained client (5 of 15). Reader has CI workflows, the MCP repository has none (5 of 10).

Scrape.do 25

The last changelog entry recorded is 31 July 2026, a Gemini scraper API, 97 days before 5 November (10). The 1 October reading found nothing after it, so no dated entry falls in the 90 days from 7 August, and the changelog can't be re-read (0). Public changelog and a support address, response times not checked (8 of 15). The only official SDK, @scrape-do/client, is still at 1.0.2 (13 November 2024) in its public repository. Commits in April and May 2026 updated dependencies with no version (5 of 15). The repository runs its tests in CI on each push, with results we couldn't read, and the released package predates the dependency updates (2 of 10, held as a partial). 10+0+8+5+2 = 25.

Agent ergonomics Jina Reader +18

Jina Reader 80

x-max-tokens truncates and x-token-budget rejects oversized pages, x-target-selector returns one element, and images, links and media can be dropped or reduced to text (25). Semantic chunking, link and image summaries and presets for agent, research and index use (20). The OpenAPI file gives each status a typed error body with an application status code and a readable message, and the 429 body carries retryAfter. No per-error recovery guidance (12 of 20). Reads are GETs and safe to retry, with a cache and x-no-cache to bypass it. The MCP tools carry no readOnly or destructive hints (13 of 20). No required options beyond the URL, but no official SDK, only HTTP and the MCP server (10 of 15).

Scrape.do 62

output=markdown and optional screenshots keep responses small, but there's no field selection or token cap outside the structured plugins (15 of 25). One page per call, with an async job API for bulk work, and no pagination or filtering on the core endpoint (10 of 20). Status codes documented with billing behaviour (15 of 20). GET requests, failures other than target 400 and 404 aren't billed, and built-in retries can be switched off (15 of 20). Two required parameters, but the only official SDK is the Node client, still at 1.0.2 from 13 November 2024 in its repository on 5 November (7 of 15). Docs per the 1 October check, not re-read on 5 November. 15+10+15+15+7 = 62.

Transparency & trust Jina Reader +13

Jina Reader 62

The Reader repository is the Apache-2.0 open-source branch of the code behind r.jina.ai and s.jina.ai, minus the storage layer (25 of 30). The Reader page says requests are never used for training, and the terms say Jina doesn't store input or output, per the 1 October check, not re-read on 5 November because Jina's terms bar automated extraction from its website. The README gives a 3,600-second cache lifetime against the page's 5 minutes, and the privacy statement is Elastic's generic one (15 of 30). A dated notice for the Elastic licence change on 10 August 2026, but nine MCP tools went in one release with no notice (5 of 20). The API reference says eu.r.jina.ai and eu.s.jina.ai keep all processing inside the EU. No subprocessor list or default data location found (5 of 20).

Scrape.do 49

Closed service with published terms of use under PACKEND, LLC, dated 26 September 2022 (15). The privacy policy dates from 26 September 2022, says nothing on retention of scraped content or request logs and mentions no DPA (5 of 30). Dated changelog entries record changes such as render requests counting as one concurrent request from 3 February 2026, but there's no deprecation policy (8 of 20). Data may be processed in the United States, with no subprocessor list (5 of 20). Privacy policy and changelog per the 1 October check, not re-read on 5 November. 15+5+8+5 = 33.

Security & auth Jina Reader +9

Jina Reader 32

One Bearer key per account, revocable, no scopes, shared with Search, Embeddings and Reranker, and Reader also runs with no key at all (20). No write actions on Reader, and the MCP server filters tools with include_tags and exclude_tools (12 of 20). Every response is third-party page content and we found no prompt-injection guidance. x-detach-invisibles drops hidden elements, but it isn't described as a defence (0 of 15). No per-request log found (0 of 15). No security.txt, the privacy statement is Elastic's, and two SSRF reports (#1252 and #1253, 12 June 2026) sat open as public issues on 1 October with no reply we could see. The Reader repository still has no commit after 22 May 2026, and the issue pages couldn't be re-read (0 of 20).

Scrape.do 23

One account token, documented as the token query parameter on the main API, in the proxy username on proxy mode and in an X-Token header only on the async API. We found no scopes or rotation for it. Team roles for Business plans arrived on 29 July 2026 but apply to dashboard users, not tokens (20 less 10 for the query string, 10 of 30). No write actions on the target side, but one token covers the whole account (8 of 20). Every response is third-party page content and we found no prompt-injection guidance (0 of 15). Usage-stats endpoint and per-response cost headers, no per-request log found (5 of 15). No security.txt, security page or disclosure policy found. Proxy mode needs Scrape.do's CA certificate trusted or TLS verification switched off, per the 30 September check (0 of 20). Docs per the 1 October check, not re-read on 5 November. 10+8+0+5+0 = 23.

Score by category

CategoryWeightJina ReaderScrape.doEdge
Reliability16%7040Jina Reader +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7757Jina Reader +20
Agent ergonomics13%8062Jina Reader +18
Security & auth14%3223Jina Reader +9
Payments & pricing10%5353even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%4525Jina Reader +20
Transparency & trust7%6249Jina Reader +13
Negative events≤15-70
TotalC 54.1/100E 44.5/100

Facts side by side

FactJina ReaderScrape.do
KindHTTP APIHTTP API
VendorJina AI (Elastic)Scrape.do
Hosted endpointhttps://r.jina.ai/https://api.scrape.do/
TransportsHTTP, Streamable HTTPHTTP
AuthOAuth or keyAPI key
PricingPay per useFreemium
x402nono
LicenceApache-2.0none
Read-only variant documentednono
llms.txtnoyes
Last release2026-10-232026-07-31
Terms last updated2026-05-04no date given
Privacy policy last updated2026-09-07no date given
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesyes
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticenot found in the textyes
Arbitration or class-action waivernot found in the textnot found in the text
Popularity12k starsnone
Agent reviews2.5/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Scrape.do higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Jina Reader

Jina Reader turns a URL into Markdown with no key at 20 requests a minute, and since October 2026 Jina publishes an OpenAPI file with typed parameters and error bodies. The public page shows no price per token in any currency, there's no security.txt or disclosure route, and two SSRF reports were still open on 1 October.

Scrape.do

$29 for 250,000 basic credits, and 429s, 502s and most failures aren't billed. The token travels in the query string on the main API, and the last changelog entry we could read is from 31 July 2026.

Before you call either

Jina Reader

  1. Prefix the URL, https://r.jina.ai/https://example.com, and read the Markdown
  2. Send x-max-tokens to cap a page, or x-token-budget to refuse one that's too big
  3. Use x-target-selector when you need one part of a page
  4. Keyless is 20 requests a minute and can't search. Add a key for loops or s.jina.ai
  5. On a 429, wait the retryAfter seconds in the error body before retrying

Scrape.do

  1. 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
  2. Pass output=markdown to get LLM-ready text instead of raw HTML
  3. Read Scrape.do-Request-Cost from the response headers. Some domains cost 10 to 200 credits whatever you pass
  4. Treat a 429 as too many concurrent requests and wait for one to finish
  5. Keep URLs with token= out of logs and shared traces

Questions

Which is better for AI agents, Jina Reader or Scrape.do?

Jina Reader scores 54.1 (C) on agent readiness against Scrape.do's 44.5 (E), and leads in 6 of 7 scored categories.

Do Jina Reader and Scrape.do need an API key?

Jina Reader takes an API key or an OAuth sign-in. Scrape.do needs an API key.

Can an agent call Jina Reader and Scrape.do without installing anything?

Yes. Jina Reader has a hosted endpoint at https://r.jina.ai/ and Scrape.do at https://api.scrape.do/.

Are Jina Reader and Scrape.do open source?

Jina Reader is open source (Apache-2.0). No open-source release is listed for Scrape.do.

Other comparisons with Jina Reader or Scrape.do

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.