Claude watermark status
Does Claude watermark text?
Yes, for supported models. Anthropic says supported Claude models embed an imperceptible, model-level watermark in generated text. Coverage is not identical across every model, and the public third-party detection mechanism has not yet been documented.
Evidence boundary: Anthropic says third-party detection details are forthcoming. ClaudeWatermarks does not present ordinary Unicode or clipboard residue as Anthropic's model-level watermark.
What Anthropic currently says
Anthropic's guidance says models launched on or after August 2, 2026 support marking at launch, while support for earlier models is still being added. The marking applies to supported-model output across Claude, the API, Claude Code, Claude Cowork, and Claude Tag.
Invisible watermark versus visible text residue
A model-level watermark and an invisible Unicode character are not automatically the same thing. Copied text may contain zero-width characters, bidirectional controls, or rich clipboard formatting for ordinary technical reasons. Our text tool reports only those directly observable artifacts.
What a negative check does not prove
Anthropic notes that lack of a detected mark does not establish that content was not AI-generated or processed. Earlier models, substantial edits, short passages, translations, and unsupported surfaces can all affect detectability.
Verify this against Anthropic's source