Plans for every release.

One run of audit_url on one URL, from any client you connect. It is counted against your organisation's plan before anything is fetched. Refused addresses and sites that cannot be reached are not counted.

Every plan audits against all 138, and on a verified site every one of them gets a state, a guide and an evidence path. The full 105 automatic, 29 assisted and 4 guided needs the sources connected: a crawl, renders in the plan, Search Console, server logs and the CI action. Without a source, the requirements that depend on it fall back to guided, and the coverage table says which source to connect.

One candidate that Claude, as the assistant judge, looks at: for example a block of text that may be hidden. Claude proposes a verdict with verbatim quotes and never fails a page on its own; a person confirms. Above the plan's monthly cap, the item stays unjudged and the finding says so.

At the start of every calendar month, in UTC. The get_usage tool shows your plan, the audits used and left, and the reset date.

Regensbot refuses the audit with a tool error your assistant can read, never a broken connection. That holds for the monthly quota, the hourly limit and refused addresses.

Monthly or yearly, in EUR and net of VAT, through Stripe. Paying yearly gives you 3 months free.

It is quoted after a scoping call, for the scope your site needs: its size, its templates and the access you grant. It is a service by our team, separate from the plans.

10 audits a month, up to 5 an hour and 1 at a time, 5 different sites a day, 1 API key and 7 days of audit history. It also includes 1 verified site, with 1 crawl a month of up to 100 pages, and 50 MB of evidence storage. It runs the same audit as every other plan; renders, monitors, URL Inspection calls, items judged by Claude, and log uploads come with the paid plans.