OpenAI model check
GPT-5 watermark detector
Check GPT-5-related watermark, provenance, and AI text risk signals with provider-support caveats.
Run a signal check
No detector model loads until you press Check.
Current support
GPT-5 watermark verification for arbitrary pasted text is not a universal public signal, so the report prioritizes provenance, support status, and classifier uncertainty.
What this checks
- Model-specific pages help capture emerging search demand around new providers and models.
- Reports can include claimed model context without treating it as evidence.
- API and bulk workflows use the same normalized report schema.
What this does not prove
- Provider-specific watermark detection may require private verification access.
- Short prompts and short answers are especially hard to classify.
- No single classifier can determine GPT-5 authorship.
FAQ
- Can this prove whether content was written by AI?
No. AI Detect reports signals such as provenance metadata, watermark support status, and statistical text risk. It does not claim legal or authorship proof.
- Does text leave my browser during a local check?
Browser-default checks run local text features and provenance checks after you press Check. Server enhanced checks are separate and will be labelled before use.
- Why can a result be unknown?
Many providers do not expose public watermark detectors, and metadata can be absent or stripped. Unknown is a valid result when no reliable public signal exists.
Workflow upgrade
Need repeatable reviews?
Move from one-off checks to saved reports, batch review, and API-ready signal records when the workflow needs it.