Does ChatGPT Watermark Text?

Starting 5 October 2026, API customers worldwide can opt in to text watermarking for select models. It stays off by default in the API. Over the coming weeks, an invisible watermark is added to eligible ChatGPT and Codex text in the European Union, on every plan. OpenAI is not making text watermarking a global default at launch.

Images and audio stay on the older stack: C2PA Content Credentials plus SynthID, with public verification. That stack is not the text watermark.

OpenAI names the method textGrain. It adds an invisible statistical signal to the model's word choices. A detector looks for that signal and needs a secret key. Nothing is inserted as a hidden character.

The ChatGPT watermark remover page is where we describe the clean: a rewrite changes the words the signal lives in. OpenAI's own numbers are the reason that works better than a character scan.

Copied text still picks up zero-width characters from pages, editors and chat clients. Those are not textGrain. Finding one does not mean ChatGPT watermarked the passage, and deleting them does not remove the word-choice signal.

They are still worth removing when they break search, diffs, validation or pasted code. The invisible character remover does that locally and reports each code point by name.

OpenAI is direct about the limits. A watermark can indicate that an OpenAI system generated or processed part of a passage. It does not say who used the system, who owns the text, or whether the content is accurate. If no watermark is detected, that does not prove a person wrote it. The text may be short, edited, translated, from an unsupported model, or from before the rollout.

There is no public checker. Detector access opens first to approved researchers and expert organizations. Until that changes, nobody outside that group can measure whether a specific passage still carries textGrain.