AWS bedrock: Claude Sonnet 4.5 model card: alt-text cleanup and watermarking row
Summary
Replaced verbose image alt text (e.g. 'Green circle with white checkmark icon.') with short 'supported'/'not-supported' labels across the model card's capability tables, and added a new 'Watermarking' entry marked as not supported.
Security assessment
The diff only rewrites image alt text for accessibility/consistency and adds a capability-matrix row indicating Watermarking is unsupported for this model. No authentication, encryption, IAM, or vulnerability-fix content is present; the only security-adjacent mention (Abuse detection, Guardrails) is unchanged text whose alt attribute was shortened.
Evidence
+ *  [Watermarking](watermarking.html)
Diff
diff --git a/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md b/bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md index f8787bb..f0984cb 100644 --- a//bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md +++ b//bedrock/latest/userguide/model-card-anthropic-claude-sonnet-4-5.md @@ -50,5 +50,5 @@ Claude Sonnet 4.5 is Anthropic's model optimized for agents, coding, and compute - Audio|  Embedding - Image|  Image - Speech|  Speech - Text|  Text - Video|  Video + Audio|  Embedding + Image|  Image + Speech|  Speech + Text|  Text + Video|  Video @@ -92,12 +92,12 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) - *  [Abuse detection](abuse-detection.html) - *  [Guardrails](guardrails.html) - *  [Prompt optimization](prompt-management-optimize.html) - *  [Count tokens](count-tokens.html) - *  [Knowledge base](knowledge-base.html) - *  [Model evaluation](evaluation.html) - *  [Prompt management](prompt-management.html) - *  [Flows](flows.html) - *  [Agents](agents.html) - *  [Structured outputs](./structured-output.html) - *  [Computer use](computer-use.html) + *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) + *  [Abuse detection](abuse-detection.html) + *  [Guardrails](guardrails.html) + *  [Prompt optimization](prompt-management-optimize.html) + *  [Count tokens](count-tokens.html) + *  [Knowledge base](knowledge-base.html) + *  [Model evaluation](evaluation.html) + *  [Prompt management](prompt-management.html) + *  [Flows](flows.html) + *  [Agents](agents.html) + *  [Structured outputs](./structured-output.html) + *  [Computer use](computer-use.html) @@ -107 +107,2 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Intelligent prompt routing](prompt-routing.html) + *  [Intelligent prompt routing](prompt-routing.html) + *  [Watermarking](watermarking.html) @@ -147 +148 @@ Amazon Bedrock offers multiple service tiers to match your workload requirements - |  |  |  + |  |  | 