Claude Platform Docs
MessagesBuilding with Claude

Text watermark

What Anthropic’s text watermark leaves unchanged, where to find the models and platforms it covers, and which sampling parameters to omit if you rely on it.

Text generated by supported Claude models carries Anthropic’s text watermark. How Claude marks AI-generated content lists the models and platforms it covers, and How Claude’s text watermark works gives the background.

The watermark doesn’t change the meaning, quality, or readability of the output. It adds no tokens or hidden characters and carries no information about you or your organization. You don’t need to change your requests or response handling for it. If you rely on the watermark and set temperature, top_p, or top_k, see Sampling settings.

Sampling settings

This section applies to: Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, Claude Opus 3 (model access on request)

If you need your output to carry the watermark, omit temperature, top_p, and top_k from your requests. If a request sets any of them to a non-default value, the output might not carry the watermark.

Your framework or client library might set these parameters for you. If you need the watermark, check its settings and the request body it sends, and remove any of the three that it sets.

Was this page helpful?