Patronus AI
Hosted platform for LLM evaluation experiments, logs and traces, plus an agent-trace failure analysis assistant.
By Patronus AI ยท www.patronus.ai
Package download activity
Patronus AI has no PyPI or npm package that maps to it (Closed-source (no public package or repository)). This is not a zero.
GitHub stars
No public repository is linked from Patronus AI's own site. This is not a zero.
Facts
| Categories | Evaluation, Tracing & observability | |
|---|---|---|
| Status | Generally available | |
| Licence | Proprietary | source, checked 2026-10-07 |
| Self-host | Enterprise only | source, checked 2026-10-07 |
| OpenTelemetry | Unknown (no OTel statement on public pages; docs require a login (HTTP 401), checked 2026-10-07) | source, checked 2026-10-07 |
| Pricing model | usage | |
| Entry price | not published in USD; Developer plan: no credit card, $10 free credits, then usage billing ($10 per 1k small evaluator calls, $20 per 1k large evaluator calls, $10 per 1k eval explanations); Enterprise by contact. The page also renders a second table (Individual free / Base $25 per month, counted in 'pages') that looks like a template remnant and does not match the Developer/Enterprise plan blocks, so no entry price recorded. | source, checked 2026-10-07 |
| Free tier | Yes | |
| Measurability | Closed-source (no public package or repository) |
Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.
Compare
Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.