Trace Amazon Bedrock applications

This guide shows you how to trace Amazon Bedrock model calls using LangSmith. Amazon Bedrock is a fully managed service that offers a choice of high-performing foundation models from leading AI companies via an API. By integrating LangSmith tracing, you can monitor, debug, and optimize your Bedrock applications with detailed observability into model interactions, latency, token usage, and custom metadata. LangSmith automatically captures traces when you use LangChain’s Bedrock integrations, providing insights into:

Request and response payloads
Token usage and costs
Latency and performance metrics
Custom tags and metadata for filtering and analysis
Multi-step chains and agent workflows

Installation

pip install -qU langchain-aws

npm install @langchain/community @langchain/core @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types

yarn add @langchain/community @langchain/core @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types

pnpm add @langchain/community @langchain/core @aws-crypto/sha256-js @aws-sdk/credential-provider-node @smithy/protocol-http @smithy/signature-v4 @smithy/eventstream-codec @smithy/util-utf8 @aws-sdk/types

The Python integration requires langchain-aws, which provides the ChatBedrockConverse class for interacting with Bedrock models. The JavaScript integration requires @langchain/community for the Bedrock chat model, plus several AWS SDK packages for authentication, request signing, and streaming support.

Setup

To enable LangSmith tracing, configure your LangSmith API key and project settings. You’ll also need to set up your AWS credentials to authenticate with Bedrock.

LangSmith configuration

export LANGSMITH_API_KEY=<your_langsmith_api_key>
export LANGSMITH_PROJECT=<your_project_name> # optional, defaults to "default"
export LANGSMITH_TRACING=true

You can obtain your LangSmith API key from smith.langchain.com by navigating to Settings > API Keys. The LANGSMITH_PROJECT variable allows you to organize traces into different projects.

AWS credentials

Configure your AWS credentials to authenticate with Bedrock. You’ll need an AWS account with Bedrock access enabled. Follow the AWS setup instructions to create your credentials and enable model access:

export AWS_ACCESS_KEY_ID=<your_aws_access_key_id>
export AWS_SECRET_ACCESS_KEY=<your_aws_secret_key>
export AWS_SESSION_TOKEN=<your_session_token> # only if using temporary credentials
export AWS_DEFAULT_REGION=<your_bedrock_region> # e.g., us-east-1 or us-west-2

Configure tracing

Once your environment variables are set, LangSmith will automatically trace all Bedrock model calls made through LangChain. You can enhance traces with custom tags and metadata to make filtering and analysis easier. Tags help you categorize traces (e.g., by environment, feature, or test type), while metadata allows you to attach arbitrary key-value pairs for detailed context. The following example shows you how to invoke a Bedrock model with tracing enabled and custom metadata attached:

from langchain_aws import ChatBedrockConverse

# Initialize the Bedrock chat model
model = ChatBedrockConverse(
    model="us.anthropic.claude-sonnet-4-5-20250929-v1:0"
)

# Invoke the model with tracing metadata
response = model.invoke(
    "Hello! How can I use LangSmith with Bedrock?",
    config={
        "tags": ["aws-bedrock", "langsmith", "integration-test"],
        "metadata": {
            "env": "dev",
            "model_provider": "bedrock",
            "model_id": "claude-sonnet-4.5"
        }
    }
)

print(response)

import { ChatBedrockConverse } from "@langchain/community/chat_models/bedrock";

// Initialize the Bedrock Claude model
const model = new ChatBedrockConverse({
  model: "us.anthropic.claude-sonnet-4-5-20250929-v1:0",
  region: process.env.AWS_DEFAULT_REGION || "us-east-1",
});

// Invoke the model with LangSmith tracing metadata
const response = await model.invoke(
  "Hello! How can I use LangSmith with Bedrock?",
  {
    tags: ["aws-bedrock", "langsmith", "integration-test"],
    metadata: {
      env: "dev",
      model_provider: "bedrock",
      model_id: "claude-sonnet-4.5"
    }
  }
);

console.log(response);

View traces in LangSmith

After running your code, navigate to your LangSmith project at smith.langchain.com to view the traces. Each trace includes:

Request details: Input messages, model parameters, and configuration
Response details: Model output, token usage, and response metadata
Performance metrics: Latency, tokens per second, and cost estimates
Custom metadata: Tags and metadata you provided in the config parameter

You can filter traces by tags (e.g., aws-bedrock or integration-test), search by metadata fields, or drill into specific traces to debug issues.

Next steps

Learn more about LangSmith features including evaluation, datasets, and feedback
Explore Bedrock model capabilities like tool calling, streaming, and prompt caching
Review LangChain Bedrock integration documentation for advanced features like extended thinking and citations

Edit this page on GitHub or file an issue.

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Tracing setup

Configuration & troubleshooting

Viewing & managing traces

Automations

Feedback & evaluation

Monitoring & alerting

Data type reference

Trace Amazon Bedrock applications

Installation

Setup

LangSmith configuration

AWS credentials

Configure tracing

View traces in LangSmith

Next steps

​Installation

​Setup

​LangSmith configuration

​AWS credentials

​Configure tracing

​View traces in LangSmith

​Next steps

Installation

Setup

LangSmith configuration

AWS credentials

Configure tracing

View traces in LangSmith

Next steps