AWS bedrock documentation change

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

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

Summary

Updated model lifecycle to Legacy with EOL date of September 14, 2026, added prompt caching documentation with specifications, and updated API example structure

Security assessment

The changes are routine documentation updates including model lifecycle status, feature documentation for prompt caching (performance optimization), and API example formatting changes. No security vulnerabilities, incidents, or security-specific features are mentioned.

Diff

diff --git a/bedrock/latest/userguide/model-card-amazon-nova-premier.md b/bedrock/latest/userguide/model-card-amazon-nova-premier.md
index ffeec5502..597dc0c97 100644
--- a//bedrock/latest/userguide/model-card-amazon-nova-premier.md
+++ b//bedrock/latest/userguide/model-card-amazon-nova-premier.md
@@ -19 +19 @@ Nova Premier is Amazon's multimodal model for complex reasoning, agentic workflo
-  * **Model EOL date:** N/A
+  * **Model EOL date:** September 14, 2026
@@ -23 +23 @@ Nova Premier is Amazon's multimodal model for complex reasoning, agentic workflo
-  * **Model lifecycle:** Active
+  * **Model lifecycle:** Legacy
@@ -43,0 +44,10 @@ Nova Premier is Amazon's multimodal model for complex reasoning, agentic workflo
+**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._
+
@@ -123,2 +133,7 @@ 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
+                }