
Amazon Bedrock
Fast-track your generative AI applications and agents from prototype to production with confidence
Foundation models and agent tools at your fingertips
Amazon Bedrock is a comprehensive, secure, and flexible service for building generative AI applications and agents. Amazon Bedrock connects you to leading foundation models, services to deploy and operate agents, tools for fine-tuning, safeguarding, and optimizing models along with knowledge bases to connect applications to your latest data so you have everything you need to move fast from experimentation to real-world deployment--fast.
Meet Amazon Bedrock
Capabilities and services for all your AI development needs

Capabilities
With the flexibility to choose and best-in-class security, Amazon Bedrock leads the way in your AI journey
Choose the best model for your use case
Amazon Bedrock gives you access to over one hundred foundation models from leading AI companies, along with evaluation tools to pick the best model based on your unique performance and cost needs. Future-proof your AI strategy as your needs evolve and new models emerge.

Securely customize with your data
Move from generic AI to AI that knows your customer and your business by customizing models with your data. By combining multiple data customization tools—Knowledge Bases, Bedrock Data Automation, prompt engineering, and fine-tuning—you can optimize your AI applications to your business, while ensuring you’re always in control of sensitive information.

Apply security, privacy, and responsible AI checks
Amazon Bedrock provides industry-leading security, privacy, and compliance for generative AI applications. Guardrails can help block up to 88% of harmful content and filter out 75% of hallucinations with Automated Reasoning checks. Bedrock never stores or uses your data to train models, ensuring complete privacy.

Optimize for cost, latency, and accuracy
Ensure your AI applications are optimized for the perfect balance of cost, speed, and accuracy. Features like Model Distillation, Prompt caching, and Intelligent Prompt Routing can reduce expenses while maintaining performance. For example, distilled models run up to 500% faster and cost up to 75% less, with minimal impact on accuracy. Intelligent Prompt Routing can cut costs by up to 30% while maintaining quality. With flexible options for both real-time and batch processing, Bedrock helps you build smart, efficient, and cost-effective AI systems.

Build and orchestrate agents
With Amazon Bedrock Agents you can build and experiment with AI agents quickly and securely. Amazon Bedrock Flows provides a visual builder tool to connect Prompts, Agents, Guardrails, Knowledge Bases, andother AWS services into complete agentic AI applications.

Move agents from proof of concept to production faster
With Amazon Bedrock AgentCore, developers can accelerate AI agents into production with the scale, reliability, and security critical to real-world deployment. AgentCore includes foundational tools required by agents to execute real-world workflows:
- AgentCore Gateway. Enable agents to seamlessly discover and securely connect to tools, data, and other agents.
- AgentCore Memory. Allow agents to retain both short-term and long-term memory with high accuracy.
- AgentCore Runtime. Deploy agents securely at scale. Built for dynamic agentic workload demands including the longest session runtime in the industry for asynchronous workloads.
- AgentCore Identity. Enable seamless and secure agent authentication.
- AgentCore Observability. Ensure your agents operate securely and reliably.
Do more with Amazon Bedrock
Get from idea to production fast