What is Amazon Bedrock?

Amazon Bedrock is a fully managed service that makes leading foundation models from AI companies available through an API along with developer tooling to help build and scale generative AI applications.

Access the Amazon Bedrock models

Important

Amazon Bedrock offers easy access to a choice of high-performing foundation models from leading AI companies, including AI21 Labs, Anthropic, Cohere, Meta, Stability AI, and Amazon.

Before you can use any of the foundation models, you must request access to that model. If you try to use the model (with the API or within the console) before you have requested access to it, you will receive an error message. For more information, see Model access.

Features of Amazon Bedrock

With Amazon Bedrock, you can explore the following capabilities:

• Text playground – A hands-on text generation application in the AWS Management Console.

• Image playground – A hands-on image generation application in the console.

• Chat playground – A hands-on conversation generation application in the console.

• Examples library – Example use cases to load.

• Amazon Bedrock API – Explore with the AWS CLI, or use the API to access the base models.

• Embeddings – Use the API to generate embeddings from the Titan text and image models.

• Agents for Amazon Bedrock – Build agents to perform orchestration and carry out tasks for your customers.

• Knowledge base for Amazon Bedrock – Draw from data sources to help your agent find information for your customers.

• Provisioned Throughput – Purchase throughput to run inference on models at discounted rates.

• Fine-tuning and Continued Pre-training – Customize an Amazon Bedrock base model to improve its performance and create a better customer experience.

• Model invocation logging – Collect invocation logs, model input data, and model output data for all invocations in your AWS account used in Amazon Bedrock.

• Model versioning – Benefit from continuous updates and improvements in foundation models to enhance your applications' capabilities, accuracy, and safety.

The following capabilities are in public preview release. These features are subject to change.

• Batch inference – Run model inference on a large dataset of prompts. Currently available only through the API.

• Model evaluation – Create model evaluation jobs to evaluate the responses of 1 or models to either built-in or custom prompt datasets. To evaluate a model's response you can use either human workers or automatic metrics.

The following capabilities are in limited preview release. To request access, contact your AWS account manager.

• Guardrails – Implement safeguards for your generative AI applications.

Supported models in Amazon Bedrock

For information about the models that Amazon Bedrock supports, see Supported models in Amazon Bedrock.

Supported Regions

For information about the Regions that Amazon Bedrock supports, see Amazon Bedrock endpoints and quotas.

Amazon Bedrock pricing

When you sign up for AWS, your AWS account is automatically signed up for all services in AWS, including Amazon Bedrock. However, you are charged only for the services that you use.

To see your bill, go to the Billing and Cost Management Dashboard in the AWS Billing and Cost Management console. To learn more about AWS account billing, see the AWS Billing User Guide. If you have questions concerning AWS billing and AWS accounts, contact AWS Support.

With Amazon Bedrock, you pay to run inference on any of the third-party foundation models. Pricing is based on the volume of input tokens and output tokens, and on whether you have purchased provisioned throughput for the model. For more information, see the Model providers page in the Amazon Bedrock console. For each model, pricing is listed following the model version. For more information about purchasing Provisioned Throughput, see Provisioned Throughput.

For more information, see Amazon Bedrock Pricing.