AWS bedrock documentation change

Service: bedrock · 2025-04-11 · Documentation low

File: bedrock/latest/userguide/prompt-caching.md

Summary

Updated model availability status for Amazon Nova models from Preview to Generally Available, added token limits note, and included example request structure for Amazon Nova models

Security assessment

Changes focus on feature availability status updates, documentation of technical parameters (token limits), and API request examples. No security vulnerabilities, mitigations, or security features are mentioned in the diff.

Diff

diff --git a/bedrock/latest/userguide/prompt-caching.md b/bedrock/latest/userguide/prompt-caching.md
index 08d33bbc5..d15286c78 100644
--- a//bedrock/latest/userguide/prompt-caching.md
+++ b//bedrock/latest/userguide/prompt-caching.md
@@ -11 +11 @@ How it worksSupported models, Regions, and limitsGetting started
-Amazon Bedrock prompt caching is generally available with Claude 3.7 Sonnet and Claude 3.5 Haiku. Customers who were given access to Claude 3.5 Sonnet v2 during the prompt caching preview will retain their access, however no additional customers will be granted access to prompt caching on the Claude 3.5 Sonnet v2 model. Prompt caching for Amazon Nova models continues to operate in preview.
+Amazon Bedrock prompt caching is generally available with Claude 3.7 Sonnet, Claude 3.5 Haiku, Amazon Nova Micro, Amazon Nova Lite, and Amazon Nova Pro. Customers who were given access to Claude 3.5 Sonnet v2 during the prompt caching preview will retain their access, however no additional customers will be granted access to prompt caching on the Claude 3.5 Sonnet v2 model.
@@ -65,3 +65,7 @@ Claude 3.5 Sonnet v2 | anthropic.claude-3-5-sonnet-20241022-v2:0 | Preview | 1,0
-Amazon Nova Micro v1 | amazon.nova-micro-v1:0 | Preview | 1 | 4 | `system` and `messages`  
-Amazon Nova Lite v1 | amazon.nova-lite-v1:0 | Preview | 1 | 4 | `system` and `messages`  
-Amazon Nova Pro v1 | amazon.nova-pro-v1:0 | Preview | 1 | 4 | `system` and `messages`  
+Amazon Nova Micro v1 | amazon.nova-micro-v1:0 | Generally available | 1K1 | 4 | `system` and `messages`  
+Amazon Nova Lite v1 | amazon.nova-lite-v1:0 | Generally available | 1K1 | 4 | `system` and `messages`2  
+Amazon Nova Pro v1 | amazon.nova-pro-v1:0 | Generally available | 1K1 | 4 | `system` and `messages`2  
+  
+1: The Amazon Nova models support a maximum number of 32k tokens for prompt caching.
+
+2: Prompt caching is primarily for text prompts and also supports images embedded within text prompts.
@@ -168,0 +173,3 @@ Prompt caching is enabled by default when you call the [InvokeModel](https://doc
+Anthropic Claude
+    
+
@@ -201,0 +209,30 @@ The following example shows how to structure the body of your InvokeModel reques
+Amazon Nova
+    
+
+The following example shows how to structure the body of your InvokeModel request for the Amazon Nova model. Note that the exact format and fields of the body for InvokeModel requests may vary depending on the model you choose. To see the format and content of the request and response bodies for different models, see [Inference request parameters and response fields for foundation models](./model-parameters.html).
+    
+    
+    {
+        "system": [{
+            "text": "Reply Concisely"
+        }],
+        "messages": [{
+            "role": "user",
+            "content": [{
+                "text": "Describe the best way to learn programming"
+            },
+            {
+                "text": "Add additional context here for the prompt that meets the minimum token requirement for your chosen model.",
+                "cachePoint": {
+                    "type": "default"
+                }
+            }]
+        }],
+        "inferenceConfig": {
+            "maxTokens": 300,
+            "topP": 0.1,
+            "topK": 20,
+            "temperature": 0.3
+        }
+    }
+