# Endpoints supported by Amazon Bedrock
<a name="endpoints"></a>

Amazon Bedrock supports various endpoints depending on whether you want to perform control plane operators or [inference](inference.md) operations.

**Control Plane operations**

Amazon Bedrock control plane operations can be used with the endpoint: `bedrock.{region}.amazonaws.com.` It can be used for managing resources, such as listing available [models](models.md), creating [custom model](custom-models.md) jobs, and managing [provisioned throughput](prov-throughput.md). Read more on our control plane API [here](https://docs.aws.amazon.com/general/latest/gr/bedrock.html).

**Inference operations**

Amazon Bedrock supports the following primary two end points for performing inference programmatically:


| **Endpoint** | **Supported APIs** | **Description** | 
| --- | --- | --- | 
| bedrock-mantle.{region}.api.aws | [Responses API](bedrock-mantle.md) / [Chat Completions API](bedrock-mantle.md) / [Messages API](model-parameters-anthropic-claude-messages.md) | Region-specific endpoints for making inference requests for models hosted in Amazon Bedrock using the OpenAI-compatible endpoints and the Anthropic Messages API. | 
| bedrock-runtime.{region}.amazonaws.com | [InvokeModel](inference-invoke.md) / [Converse](conversation-inference.md) / [Chat Completions](inference-chat-completions.md) / [Messages API](model-parameters-anthropic-claude-messages.md) | Region-specific endpoints for making inference requests for models hosted in Amazon Bedrock using the InvokeModel/Converse/Chat Completions/Messages APIs. Read more on Amazon Bedrock Runtime APIs [here](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_Operations_Amazon_Bedrock_Runtime.html). | 

**Which service endpoint should you use for your inference?**

The endpoint you use depends on your use-case.


| **Endpoint** | **Features and Use Cases** | 
| --- | --- | 
| bedrock-mantle | Supports OpenAI-compatible APIs ([Responses API](bedrock-mantle.md), [Chat Completions API](bedrock-mantle.md)) and the Anthropic-native [Messages API](model-parameters-anthropic-claude-messages.md).<br />**Use for:** Easily migrating from other models that use the OpenAI-compatible APIs.<br />**Features:** Supports both client and server side tool use with Lambda functions and comes configured with ready-to-use tools in your applications.<br />**Recommended for:** New users to Amazon Bedrock. | 
| bedrock-runtime | Supports Amazon Bedrock native APIs ([Invoke API](inference-invoke.md), [Converse API](conversation-inference.md)), the Anthropic-native [Messages API](model-parameters-anthropic-claude-messages.md), and the OpenAI-compatible [Chat Completions API](inference-chat-completions.md).<br />**Use for:** Running any model supported by Amazon Bedrock. The [Converse API](conversation-inference.md) provides a unified interface for interacting with all models in Amazon Bedrock and the [Invoke API](inference-invoke.md) provides direct access to models with more ability to control the request and response format. You can also use [Chat Completions API](inference-chat-completions.md) to interact with your models.<br />**Features:** Supports only client-side tool use with Lambda functions and does not come pre-configured with ready-to-use tools. Allows you to track usage and costs when invoking a model. | 

If you are new to Amazon Bedrock, we recommend using open APIs such as the Messages API, Chat Completions API, or Responses API. These APIs are available on both endpoints, but we recommend the `bedrock-mantle` endpoint.

**Reduce data egress costs with VPC interface endpoints**  
If you are calling Amazon Bedrock from within a VPC, consider using [VPC interface endpoints (AWS PrivateLink)](vpc-interface-endpoints.md) to keep traffic within the AWS network and avoid data egress charges associated with NAT gateways or internet gateways.