AWS bedrock: Claude Haiku 5.5 model card: alt-text cleanup and Watermarking support
Summary
Replaces verbose image alt text ("Green circle with white checkmark icon...") with short "supported"/"not-supported" labels throughout the model card's capability tables, and adds a new supported-feature entry for Watermarking in both the base-model and inference-profile feature lists.
Security assessment
The diff is a documentation/accessibility edit: alt text is shortened to "supported"/"not-supported" and a Watermarking capability row is added to the model's supported-feature list. No vulnerability, credential, IAM, encryption, or exposure guidance is described, and no CVE or advisory is referenced; the only security-adjacent element is the mention of content watermarking, which is a provenance feature rather than a security control documented here.
Evidence
+ *  [Watermarking](watermarking.html)
Diff
diff --git a/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.md b/bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.md index 8f55964..8b5cbd4 100644 --- a//bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.md +++ b//bedrock/latest/userguide/model-card-anthropic-claude-haiku-5-5.md @@ -46,5 +46,5 @@ Claude Haiku 5.5 is the fastest, most efficient model in the Claude 5.5 family, - Audio|  Embedding - Image|  Image - Speech|  Speech - Text|  Text - Video|  Video + Audio|  Embedding + Image|  Image + Speech|  Speech + Text|  Text + Video|  Video @@ -88,16 +88,17 @@ 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) - *  [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) - *  [Prompt optimization](prompt-management-optimize.html) (base model ID `anthropic.claude-haiku-5-5` only) - *  [Client-side tool calling](tool-use.html) - *  [Server-side tool use](tool-use.html) (tool search only; regex and BM25) - *  [Application inference profiles](cost-mgmt-application-inference-profiles.html) - *  [Invocation logs](model-invocation-logging.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) + *  [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) + *  [Prompt optimization](prompt-management-optimize.html) (base model ID `anthropic.claude-haiku-5-5` only) + *  [Client-side tool calling](tool-use.html) + *  [Server-side tool use](tool-use.html) (tool search only; regex and BM25) + *  [Application inference profiles](cost-mgmt-application-inference-profiles.html) + *  [Invocation logs](model-invocation-logging.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) @@ -204 +206 @@ Amazon Bedrock offers multiple service tiers to match your workload requirements - |  |  |  |  + |  |  |  | 