AWS bedrock documentation change

Service: bedrock · 2026-04-22 · Documentation low

File: bedrock/latest/userguide/model-card-amazon-nova-pro.md

Summary

Added prompt caching feature documentation with specifications, added structured outputs feature (marked as not supported), and updated API example structure

Security assessment

Changes add feature documentation for prompt caching and structured outputs, and update API examples. These are routine feature documentation updates without any security context or vulnerability mentions.

Diff

diff --git a/bedrock/latest/userguide/model-card-amazon-nova-pro.md b/bedrock/latest/userguide/model-card-amazon-nova-pro.md
index 8bba54fbd..77b709ebf 100644
--- a//bedrock/latest/userguide/model-card-amazon-nova-pro.md
+++ b//bedrock/latest/userguide/model-card-amazon-nova-pro.md
@@ -57,0 +58 @@ Nova Pro is Amazon's balanced multimodal model offering strong accuracy, speed,
+  * ![Yes](/images/bedrock/latest/userguide/images/icons/icon-yes.png) [Prompt caching](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html)
@@ -60,0 +62 @@ Nova Pro is Amazon's balanced multimodal model offering strong accuracy, speed,
+  * ![No](/images/bedrock/latest/userguide/images/icons/icon-no.png) [Structured outputs](https://docs.aws.amazon.com/bedrock/latest/userguide/structured-outputs.html)
@@ -67,0 +70,10 @@ Nova Pro is Amazon's balanced multimodal model offering strong accuracy, speed,
+**Prompt caching using`bedrock-runtime` endpoint**
+
+For more information, see [Prompt caching for faster model inference](https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html).
+
+**Prompt caching supported** | **Min tokens per cache checkpoint** | **Max cache checkpoints per request** | **Supported TTL** | **Fields that accept prompt cache checkpoints**  
+---|---|---|---|---  
+Yes | 1K* | 4 | 5 minutes | `system` and `messages`  
+  
+_* Amazon Nova models support a maximum of 20K tokens for prompt caching. Prompt caching is primarily for text prompts._
+
@@ -175,2 +187,7 @@ Invoke API
-                'messages': [{ 'role': 'user', 'content': 'Can you explain the features of Amazon Bedrock?'}],
-                'max_tokens': 1024
+                'messages': [{
+                    'role': 'user',
+                    'content': [{'text': 'Can you explain the features of Amazon Bedrock?'}]
+                }],
+                'inferenceConfig': {
+                    'maxTokens': 1024
+                }