Anthropic's watermark detection API is not out yet
By Claude Watermark Research · Updated
It does not exist yet. Anthropic has said in writing that it "will soon be offering a watermark detection API" and is "in the process of working out the details of its implementation" — but there is no endpoint, no ship date, no pricing and no word on who gets access. Until it ships, nobody outside Anthropic can verify whether text carries Claude's watermark, and any tool claiming to do so today is describing a check that cannot currently be run. When it does ship it will prove far less than most people expect: by Anthropic's own account it shows involvement, not authorship.
Check your own text for these artifacts. Runs in your browser, no account, nothing uploaded.
What Anthropic has actually said
Straight from its published notes, quoted rather than paraphrased, because the coverage around this is already looser than the source: "We will soon be offering a watermark detection API. We're in the process of working out the details of its implementation."
That is a commitment, not a product. No endpoint has been published, no date given, no pricing announced, and nothing said about whether access will be open to anyone or restricted to vetted partners. That last question matters more than it sounds: an open endpoint lets anyone verify a claim independently, and it equally lets anyone measure their way around the mark.
What a detection will prove, and what it will not
It will not prove somebody wrote something with Claude. Anthropic's own wording: a watermark "can only determine that Claude was likely involved with the content at some point" and "cannot distinguish 'Claude wrote this' from 'Claude heavily edited this'".
That is a provenance signal, not an authorship verdict, and the gap between the two is where unfair accusations live. A teacher or an employer treating a positive result as proof of cheating would be reading it as something its own vendor says it is not. Running a draft through Claude for grammar leaves the same signal as generating the draft outright.
It will not work on everything. Anthropic notes the mark is weaker on short samples and on factual passages where word choice is constrained — fewer decisions means fewer places to encode it. A paragraph is a much worse host than an essay.
It only covers Claude. It says nothing about GPT, Gemini or Grok output, and a clean result is not evidence that a human wrote something.
What this changes for the tools selling detection today
Every product currently advertising Claude watermark detection is claiming a capability no vendor has shipped. That does not necessarily make them useless — most are doing artifact checking, which is real — but the label is wrong, and the day the API lands the gap between the two gets a lot more visible.
The same applies in reverse to removal. Anthropic is direct about it: "Light editing probably won't remove the watermark completely; a complete rewrite where every word is replaced will." Stripping invisible characters does nothing to a statistical mark, because nothing was inserted.
What you can check right now
Everything that is actually in your text. Paste it at the top of this page and you get HTML class names, zero-width characters, exotic spaces and typography, each with a count and a position. It runs in your browser, needs no account, and nothing is uploaded.
Those findings are facts about the bytes rather than a probability, which is why they are worth acting on today while the watermark question is still unanswerable. If HTML class names containing "claude" are in your document, the text came out of a chat interface without passing through a plain-text editor, and one click removes them.
Questions
- Can I use Anthropic's watermark detection API today?
- No. Anthropic has committed to offering one and said it is still working out the implementation. There is no endpoint, no announced date and no published access tier.
- Will it tell me if a student or employee used Claude?
- Not reliably, and not in the way people expect. Anthropic says a watermark shows only that Claude was likely involved at some point and cannot separate Claude writing something from Claude editing it. It is also weaker on short and factual text.
- Does a clean result prove a human wrote it?
- No. The absence of a mark is not evidence of human authorship. The text may have been rewritten, may come from a model that does not watermark, or may be too short to carry a reliable signal.
- How do the tools claiming to detect it today work?
- They are doing something else. Most check for copy-paste artifacts, which is real and verifiable, or run a style classifier that returns a probability. Neither reads a vendor's watermark, and neither could, because verification needs a key that has not been released.
- Will the API detect Gemini or ChatGPT text?
- No. It is a Claude provenance detector. Gemini uses Google's SynthID and OpenAI has not deployed text watermarking publicly, so neither is covered.
Check your own text. Free, unlimited, no account, and it runs in your browser so nothing is uploaded.
Open the checker
