AWS bedrock documentation change

Service: bedrock · 2026-04-28 · Documentation low

File: bedrock/latest/userguide/getting-started.md

Summary

Added documentation for Anthropic Messages API integration including setup instructions and code samples

Security assessment

Changes focus on API integration instructions without any security fixes or security-specific features. The added content is purely functional documentation.

Diff

diff --git a/bedrock/latest/userguide/getting-started.md b/bedrock/latest/userguide/getting-started.md
index 863bc0a94..56461404f 100644
--- a//bedrock/latest/userguide/getting-started.md
+++ b//bedrock/latest/userguide/getting-started.md
@@ -9 +9 @@
-In this section, we will show you how to get started with Amazon Bedrock within a few minutes. We will use the OpenAI-compatible APIs: [Responses API](./bedrock-mantle.html) and [Chat Completions API](./inference-chat-completions.html), and the [Invoke](./inference-invoke.html) and [Converse API](./conversation-inference.html) to show you how run an inference request. See [Build](./build.html) for list of complete APIs.
+In this section, we will show you how to get started with Amazon Bedrock within a few minutes. We will use the OpenAI-compatible APIs: [Responses API](./bedrock-mantle.html) and [Chat Completions API](./inference-chat-completions.html), the Anthropic-native [Messages API](./model-parameters-anthropic-claude-messages.html), and the [Invoke](./inference-invoke.html) and [Converse API](./conversation-inference.html) to show you how run an inference request. See [Build](./build.html) for list of complete APIs.
@@ -22,0 +23,6 @@ Responses/Chat Completions API
+Messages API
+    
+    
+    
+    pip install boto3 anthropic
+
@@ -37,0 +44,7 @@ Responses/Chat Completions API
+Messages API
+    
+    
+    
+    ANTHROPIC_API_KEY="<provide your Bedrock API key>"
+    ANTHROPIC_BASE_URL="https://bedrock-mantle.<your-region>.api.aws/anthropic"
+
@@ -73,0 +87,15 @@ Chat Completions API
+Messages API
+    
+    
+    
+    import anthropic
+    
+    client = anthropic.Anthropic()
+    
+    response = client.messages.create(
+        model="anthropic.claude-opus-4-7",
+        max_tokens=1024,
+        messages=[{"role": "user", "content": "Can you explain the features of Amazon Bedrock?"}]
+    )
+    print(response)
+