AWS bedrock: Claude Opus 4.8 model card: icon alt-text cleanup and Watermarking support
Summary
Replaced verbose image alt text (e.g. "Green circle with white checkmark icon.") with short "supported"/"not-supported" labels across the modality and feature-support tables, and added a new supported-feature entry linking to the Watermarking documentation for Claude Opus 4.8.
Security assessment
The change is limited to accessibility alt-text rewording of yes/no icons and the addition of a Watermarking feature link in the model card's supported-features list. No authentication, encryption, IAM, logging, or vulnerability content is introduced or fixed; the only substantive addition is a documentation cross-reference to the watermarking feature, which is content-provenance rather than a security control.
Evidence
+ *  [Watermarking](watermarking.html)
Diff
diff --git a/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.md b/bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.md index 55b5825..a0d57ac 100644 --- a//bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.md +++ b//bedrock/latest/userguide/model-card-anthropic-claude-opus-4-8.md @@ -50,5 +50,5 @@ Claude Opus 4.8 only supports `thinking.type: "adaptive"` for extended thinking. - Audio|  Embedding - Image|  Image - Speech|  Speech - Text|  Text - Video|  Video + Audio|  Embedding + Image|  Image + Speech|  Speech + Text|  Text + Video|  Video @@ -92,12 +92,13 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) - *  [Explicit Prompt Caching](prompt-caching.html#prompt-caching-explicit) - *  [Abuse detection](abuse-detection.html) - *  [Guardrails](guardrails.html) - *  [Prompt optimization](prompt-management-optimize.html) - *  [Knowledge base](knowledge-base.html) - *  [Model evaluation](evaluation.html) - *  [Prompt management](prompt-management.html) - *  [Flows](flows.html) - *  [Agents](agents.html) - *  [Computer use](computer-use.html) - *  [Structured outputs](./structured-output.html) + *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) + *  [Explicit Prompt Caching](prompt-caching.html#prompt-caching-explicit) + *  [Abuse detection](abuse-detection.html) + *  [Guardrails](guardrails.html) + *  [Prompt optimization](prompt-management-optimize.html) + *  [Knowledge base](knowledge-base.html) + *  [Model evaluation](evaluation.html) + *  [Prompt management](prompt-management.html) + *  [Flows](flows.html) + *  [Agents](agents.html) + *  [Computer use](computer-use.html) + *  [Structured outputs](./structured-output.html) + *  [Watermarking](watermarking.html) @@ -107,3 +108,3 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Intelligent prompt routing](prompt-routing.html) - *  [Count tokens](count-tokens.html) - *  [Implicit Prompt Caching](prompt-caching.html#prompt-caching-implicit) + *  [Intelligent prompt routing](prompt-routing.html) + *  [Count tokens](count-tokens.html) + *  [Implicit Prompt Caching](prompt-caching.html#prompt-caching-implicit) @@ -118,6 +119,7 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) - *  [Explicit Prompt Caching](prompt-caching.html#prompt-caching-explicit) - *  [Abuse detection](abuse-detection.html) - *  [Count tokens](count-tokens.html) - *  [Computer use](computer-use.html) - *  [Structured outputs](./structured-output.html) + *  [Response streaming](/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html) + *  [Explicit Prompt Caching](prompt-caching.html#prompt-caching-explicit) + *  [Abuse detection](abuse-detection.html) + *  [Count tokens](count-tokens.html) + *  [Computer use](computer-use.html) + *  [Structured outputs](./structured-output.html) + *  [Watermarking](watermarking.html) @@ -127,9 +129,9 @@ Whenever possible, we recommend using the `bedrock-runtime` endpoint for new app - *  [Guardrails](guardrails.html) - *  [Prompt optimization](prompt-management-optimize.html) - *  [Knowledge base](knowledge-base.html) - *  [Model evaluation](evaluation.html) - *  [Prompt management](prompt-management.html) - *  [Flows](flows.html) - *  [Agents](agents.html) - *  [Intelligent prompt routing](prompt-routing.html) - *  [Implicit Prompt Caching](prompt-caching.html#prompt-caching-implicit) + *  [Guardrails](guardrails.html) + *  [Prompt optimization](prompt-management-optimize.html) + *  [Knowledge base](knowledge-base.html) + *  [Model evaluation](evaluation.html) + *  [Prompt management](prompt-management.html) + *  [Flows](flows.html) + *  [Agents](agents.html) + *  [Intelligent prompt routing](prompt-routing.html) + *  [Implicit Prompt Caching](prompt-caching.html#prompt-caching-implicit) @@ -184 +186 @@ Amazon Bedrock offers multiple service tiers to match your workload requirements - |  |  |  + |  |  | 