How to read this page
Every fact about HTPBE below carries the date it was read and names the page it came from — their home page, their pricing page and one dated post on their blog, all read 2026-08-06.
Neither company publishes a detection rate, and that is worth saying out loud rather than treating as our own idea. HTPBE and PDFChecker are the two vendors in these comparisons that publish no accuracy figure at all. In a market where nearly everyone publishes a "99%" with no method behind it, that is restraint.
Side by side
| Tamperlens | HTPBE | Stronger | |
|---|---|---|---|
| Free tier | 50 documents a month, every month, with an API key (/pricing, 2026-08-06). | "New accounts get 5 free checks on signup" (read 2026-08-06). | Tamperlens |
| Published plans | Free 50 a month; Solo $39 for 1,000; Team $199 for 10,000; Business $749 for 50,000 (2026-08-06). | Starter $15 for 30 checks a month; Growth $149 for 350; Pro $499 for 1,500; Enterprise custom (read 2026-08-06). | — |
| Price per document | $39 for 1,000 documents is $0.039 each. | $149 for 350 checks is $0.426 each; $499 for 1,500 is $0.333 each (arithmetic on their published figures, read 2026-08-06). | Tamperlens |
| Smallest paid unit | Free covers 50 a month; after that the smallest purchase is a 500-document pack at $25. | Pay-per-check with no subscription: 8 checks for $5, 25 for $15 (read 2026-08-06). | HTPBE |
| On-premise | None. There is no way to run the engine inside your own network. | Offered on Enterprise: "unlimited checks with on-premise deployment" (read 2026-08-06). | HTPBE |
| Speed | No published time. A 15-second hard deadline is the ceiling, after which the answer is an error rather than a wait. | "verdict in under 3 seconds" (read 2026-08-06). | HTPBE |
| Page content | Read, in memory, and discarded with the response — which is what makes recovered redactions, hidden instructions and running-balance arithmetic possible at all. | Not read: "we never read the page content, only the file structure" (read 2026-08-06). A narrower blast radius, and a narrower set of findings. | — |
| Where it runs, and what is kept | One server in the EU (Helsinki). The document is held in memory and discarded with the response; nothing about it survives the request (/security). | EU storage, stated as "Stored in the EU" (read 2026-08-06). We cannot establish from outside what is retained or for how long, so we do not state it. | — |
| Scope beyond PDF structure | 18 signal families on a PDF, plus nine image signal families and eight for Office files; redaction recovery, document-borne prompt injection, signature coverage and permissions, Brazilian identifiers. | Structure, metadata and digital signatures. Their site states they do not detect documents fabricated from scratch and do not do identity proofing (read 2026-08-06). | Tamperlens |
| Detection rate | None published. | None published. | — |
| False-positive rate | Published at /evidence, with its population and date. | None published (read 2026-08-06). | Tamperlens |
Their own check count, on two of their own pages
Two figures for the same thing are published at once, and a reader comparing products should know which one they are being quoted:
- 63 — "63 forensic checks across metadata, file structure, and digital signatures" on their home page, and "the same 63 forensic checks per file" on their pricing page (both read 2026-08-06).
- 35 — "HTPBE's 35-check forensic analysis", in their own blog post on API pricing, published May 2026 (read 2026-08-06).
We have no way to tell which number is current or how either is counted, so we draw no conclusion from it. We note it because a check count is the kind of figure a comparison gets quoted on, and because we would want the same noted about us. For what it is worth, a count of checks is a poor unit anyway: it says how many things were looked for, not how often the answer was right.
Where HTPBE is the better answer
- The documents cannot leave your network. They sell an on-premise deployment and we do not sell one at any price.
- You want an engine that never reads the words. "Only the file structure" is a stronger promise than "read and discarded", and for some documents that difference is the whole decision.
- You need a handful of checks, once. Eight checks for $5, with no subscription, is a shape we do not sell.
- You need a stated response time. They publish one; we do not.
Where Tamperlens is the better answer
- Volume. At their Growth tier a document costs about ten times what it costs on Solo. The arithmetic is in the table and it is theirs, not ours.
- Redaction. Replaying paint order recovers the words underneath a black rectangle that carries no redaction annotation at all — the failure behind the published redaction leaks, and the case a structure-only checker cannot see. See /redaction-check.
- Instructions hidden in the document. Text positioned, coloured or layered so that a person does not read it but the model reading the file does.
- Brazil. CPF, CNPJ and boleto identifiers checked by arithmetic on the check digits, looking nothing up about anybody, with prices quoted in reais.
- Beyond PDF. Images and Office files go through the same endpoint.
What we cannot do
- No on-premise build, and no customer-managed keys.
- Recall is unmeasured. We know how often we flag genuine documents. We do not know how often we catch real tampering.
- A document forged from scratch and never edited may carry no structural trace — the same limit HTPBE states about itself, and it is honest of them to state it.
- No identity proofing.
What none of us publishes
No vendor in the table above publishes a false-positive rate on legitimate documents — how often the system flags a genuine file. Declining to publish a detection rate, as both of us do, is the right instinct; it is not the same as publishing the number that tells a buyer what review will cost.
Ours is at /evidence, with the population it was measured on, the date, and the engine version that produced it. The other comparisons are at /alternatives.