---
title: Anthropic expands text watermarking to more Claude models
url: https://www.dataloco.com/en/anthropic-expands-text-watermarking-to-more-claude-models
published: 2026-11-03T18:21:21+00:00
language: en
section: AI
source: https://the-decoder.de/anthropic-api-nutzer-koennen-wasserzeichen-bei-aelteren-claude-modellen-mit-einem-trick-umgehen/
organizations: Anthropic, Amazon Bedrock, Google DeepMind, Amazon Web Services, Google Cloud, Microsoft Foundry
publisher: Dataloco
---

# Anthropic expands text watermarking to more Claude models

Anthropic is extending its text watermarking to four additional Claude models. The company informed its API customers via email that Claude Mythos 5, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 will receive the watermark starting November 3, 2026. The rollout on Amazon Bedrock may take a few additional days.

The watermark is described as an imperceptible pattern in word choice that does not change the meaning, quality, or readability of responses. It does not add extra characters or tokens, does not affect pricing or request and response formats, and has a negligible effect on output speed. Anthropic stated that the watermark contains no information about the user, their organization, or their conversations with Claude.

For the older models, Claude Opus 4.6 and Claude Sonnet 4.6, the watermark is only applied if the temperature, top_p, and top_k parameters remain at their default values. API users can potentially avoid the watermark by making slight adjustments to these sampling parameters. Anthropic advised customers who rely on the watermark for their own compliance to keep the default settings. This limitation was not mentioned for Claude Mythos 5 and Claude Opus 4.7, suggesting the watermark applies regardless of sampling settings for those models.

Anthropic cited the December deadline of the EU AI Act as the reason for the watermarking. Models released after August 2, 2026, already include the watermark. Older models are being retrofitted gradually. Because the marking is embedded at the model level, it applies across all platforms where the models are offered, including Amazon Web Services, Google Cloud, and Microsoft Foundry. Customers cannot disable the marking.

Technically, the company uses a version of the SynthID Text method from Google DeepMind, which alters the random source during word selection to create a statistically detectable pattern. Anthropic has a detection API in private preview to identify the watermark.

## This story in other languages

- [Português (Brasil)](https://www.dataloco.com/pt-br/anthropic-expande-marcacao-de-texto-para-quatro-modelos-claude-mas-falha-em-versoes-antigas-permite-contorno)