AWS Bedrock LLM

Overview

AWSBedrockLLMService provides access to Amazon’s foundation models including Anthropic Claude and Amazon Nova, with streaming responses, function calling, and multimodal capabilities through Amazon’s managed AI service for enterprise-grade LLM deployment.

AWS Bedrock LLM API Reference

Pipecat’s API methods for AWS Bedrock integration

Example Implementation

Complete example with function calling

AWS Bedrock Documentation

Official AWS Bedrock documentation and features

AWS Console

Access foundation models and manage IAM

Installation

To use AWS Bedrock services, install the required dependencies:

uv add "pipecat-ai[aws]"

Prerequisites

AWS Account Setup

Before using AWS Bedrock LLM services, you need:

AWS Account: Sign up at AWS Console
IAM User: Create an IAM user with Amazon Bedrock permissions
Model Access: Request access to foundation models in your AWS region
Credentials: Set up AWS access keys and region configuration

Required Environment Variables

AWS_ACCESS_KEY_ID: Your AWS access key ID
AWS_SECRET_ACCESS_KEY: Your AWS secret access key
AWS_SESSION_TOKEN: Session token (if using temporary credentials)
AWS_REGION: AWS region (defaults to “us-east-1”)

Configuration

str

default:"None"

deprecated

Deprecated since 0.0.105, removed in 2.0.0. Use settings=AWSBedrockLLMService.Settings(...) instead.

str

default:"None"

AWS access key ID. If None, falls back to environment variables and the default botocore credential chain (instance profiles, IRSA, ECS task roles, SSO, etc.). Temporary credentials from the chain are renewed automatically before they expire.

str

default:"None"

AWS secret access key. Same fallback behaviour as aws_access_key.

str

default:"None"

AWS session token for temporary credentials.

str

default:"None"

AWS region for the Bedrock service. If None, uses the AWS_REGION environment variable, defaulting to "us-east-1".

AWSBedrockLLMService.Settings

default:"None"

Runtime-configurable model settings. See Settings below.

InputParams

default:"None"

deprecated

Deprecated since 0.0.105, removed in 2.0.0. Use settings=AWSBedrockLLMService.Settings(...) instead.

List[str]

default:"None"

deprecated

List of strings that stop generation when encountered. Deprecated in v0.0.105. Use settings=AWSBedrockLLMService.Settings(stop_sequences=...) instead.

botocore.config.Config

default:"None"

Custom botocore client configuration. If None, uses defaults with 5-minute connect/read timeouts and 3 retry attempts.

float

default:"5.0"

Request timeout in seconds. Used when retry_on_timeout is enabled to determine when to retry.

bool

default:"False"

Whether to retry the request once if it times out. The retry attempt has no timeout limit.

Settings

Runtime-configurable settings passed via the settings constructor argument using AWSBedrockLLMService.Settings(...). These can be updated mid-conversation with LLMUpdateSettingsFrame. See Service Settings for details.

Parameter	Type	Default	Description
`model`	`str`	`"us.amazon.nova-lite-v1:0"`	AWS Bedrock model identifier. (Inherited from base settings.)
`system_instruction`	`str`	`None`	System instruction/prompt for the model. (Inherited from base settings.)
`max_tokens`	`int`	`None`	Maximum number of tokens to generate.
`temperature`	`float`	`None`	Sampling temperature (0.0 to 1.0). Lower values are more focused, higher values are more creative.
`top_p`	`float`	`None`	Top-p (nucleus) sampling (0.0 to 1.0). Controls diversity of output.
`top_k`	`int`	`None`	Top-k sampling parameter. Not sent by this service, so it has no effect.
`seed`	`int`	`None`	Random seed for deterministic outputs. Not sent by this service, so it has no effect.
`stop_sequences`	`List[str]`	`None`	List of strings that stop generation when encountered.
`effort`	`str`	`None`	How much reasoning the model spends before answering: `"low"`, `"medium"`, `"high"`, `"xhigh"`, or `"max"`. Sent as Converse’s `outputConfig.effort`; only reasoning models accept it. See AWS docs.
`latency`	`str`	`None`	Performance mode: `"standard"` or `"optimized"`. Any other value isn’t sent.
`enable_prompt_caching`	`bool`	`False`	Whether to enable prompt caching by adding cachePoint markers to system prompts and tool definitions. Can reduce TTFT by up to 85% for multi-turn conversations. See AWS docs.
`additional_model_request_fields`	`dict`	`{}`	Additional model-specific parameters passed directly to the API.

None values are omitted from the inference config, letting the Bedrock API use its own defaults. Only parameters that are explicitly set are included in the request. This avoids conflicts with models that don’t allow certain parameter combinations (e.g., temperature and top_p together).

Usage

Basic Setup

import os

from pipecat.services.aws.llm import AWSBedrockLLMService

llm = AWSBedrockLLMService(
    settings=AWSBedrockLLMService.Settings(
        model="us.anthropic.claude-sonnet-4-5-20250929-v1:0"
    ),
    aws_access_key=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    aws_region=os.getenv("AWS_REGION", "us-east-1"),
)

With Custom Settings

from pipecat.services.aws.llm import AWSBedrockLLMService

llm = AWSBedrockLLMService(
    aws_access_key=os.getenv("AWS_ACCESS_KEY_ID"),
    aws_secret_key=os.getenv("AWS_SECRET_ACCESS_KEY"),
    aws_region="us-east-1",
    settings=AWSBedrockLLMService.Settings(
        model="us.amazon.nova-pro-v1:0",
        max_tokens=2048,
        temperature=0.7,
        latency="optimized",
    ),
)

Updating Settings at Runtime

Model settings can be changed mid-conversation using LLMUpdateSettingsFrame:

from pipecat.frames.frames import LLMUpdateSettingsFrame
from pipecat.services.aws.llm import AWSBedrockLLMSettings

await worker.queue_frame(
    LLMUpdateSettingsFrame(
        delta=AWSBedrockLLMSettings(
            temperature=0.3,
            max_tokens=1024,
        )
    )
)

Notes

No-op tool handling: AWS Bedrock requires at least one tool to be defined when tool content exists in the conversation. The service automatically adds a placeholder tool when needed to prevent API errors.
Model-specific parameters: Some models (e.g., Claude Sonnet 4.5) don’t allow certain parameter combinations. The service only includes explicitly set parameters in the inference config to avoid conflicts.
Reasoning content: Reasoning that a model returns, such as Claude with extended thinking or Nova 2 with reasoning enabled, is emitted as LLMThoughtStartFrame, LLMThoughtTextFrame, and LLMThoughtEndFrame. Signed reasoning from Claude is kept in the context and sent back on later turns, so Claude keeps its reasoning across tool calls. Amazon Nova (v1) models write <thinking>...</thinking> into the answer text; a block at the start of the response, or of any text the model writes between tool calls, is emitted as thought frames and isn’t sent to TTS.
Retry behavior: When retry_on_timeout=True, the first attempt uses the retry_timeout_secs timeout. If it times out, a second attempt is made with no timeout limit.
System instruction precedence: If both the system_instruction setting and an initial system message in the context are set, system_instruction takes precedence, the context system message isn’t sent, and a warning is logged.

Event Handlers

AWSBedrockLLMService supports the following event handlers, inherited from LLMService:

Event	Description
`on_completion_timeout`	Called when an LLM completion request times out
`on_function_calls_started`	Called when function calls are received and execution is about to start
`on_function_calls_cancelled`	Called after one or more in-progress function calls are cancelled

@llm.event_handler("on_completion_timeout")
async def on_completion_timeout(service):
    print("LLM completion timed out")

Get Started

Standards

Pipecat Server

Client SDKs

Pipecat Flows

Pipecat Cloud

CLI

Pipecat Context Hub

AWS Bedrock LLM

Overview

AWS Bedrock LLM API Reference

Example Implementation

AWS Bedrock Documentation

AWS Console

Installation

Prerequisites

AWS Account Setup

Required Environment Variables

Configuration

Settings

Usage

Basic Setup

With Custom Settings

Updating Settings at Runtime

Notes

Event Handlers