View a markdown version of this page

Inference endpoints supported by Amazon Bedrock - Amazon Bedrock

Inference endpoints supported by Amazon Bedrock

An endpoint is the URL that your application uses to send inference requests to Amazon Bedrock. Amazon Bedrock provides two inference endpoints. The endpoint you choose determines which APIs and features are available.

For most new applications, use the bedrock-runtime endpoint. Use bedrock-mantle when you specifically need capabilities that are currently available only there, such as server-side and pre-configured tools (including web search), background inference, Projects, or Workspaces. To see which endpoint each model supports, see Endpoint availability. The following table compares the two endpoints.

Endpoint Supported APIs Description
bedrock-runtime.{region}.amazonaws.com (recommended) InvokeModel / Converse / Chat Completions / Responses API / Messages API Region-specific endpoints for making inference requests for models hosted in Amazon Bedrock using the InvokeModel/Converse/Chat Completions/Responses/Messages APIs. For more information about the Bedrock-native operations, see Amazon Bedrock Runtime API operations. The OpenAI-compatible APIs are called on the /openai/v1 paths of this endpoint rather than through the AWS SDKs.
bedrock-mantle.{region}.api.aws Responses API / Chat Completions API / Messages API Region-specific endpoints for making inference requests for models hosted in Amazon Bedrock using the OpenAI-compatible endpoints and the Anthropic Messages API.
Note

Both endpoints use the same underlying Mantle inference engine and benefit from Mantle's zero operator access (ZOA) design. The bedrock-mantle name identifies an endpoint surface, not a different inference engine.

Existing applications that use bedrock-mantle continue to be fully supported and do not need to change. Both endpoints let you bring an existing OpenAI SDK codebase to Amazon Bedrock by changing only the base URL and API key, and both support the OpenAI-compatible Responses and Chat Completions APIs and the Anthropic Messages API.

API support
API bedrock-runtime bedrock-mantle
InvokeModel supported not-supported
Converse / ConverseStream supported not-supported
Chat Completions (OpenAI-compatible) supported supported
Responses API (OpenAI-compatible) supported supported
Messages API (Anthropic-native) supported supported
Note

The Messages API is available on both endpoints, but the two surfaces do not have identical feature support. In particular, structured outputs (the output_config.format parameter) are not supported on bedrock-mantle — requests that include output_config.format are rejected with a 400 error. To use structured outputs with Anthropic Claude models, call the Converse or InvokeModel APIs on bedrock-runtime.

Note

The Responses API is also available on both endpoints without identical feature support. On bedrock-runtime:

  • Requests are always synchronous. background=true is rejected with a 400 error. The store parameter is unaffected and keeps its default of true, so stored, multi-turn conversations work normally.

  • Server-side tool use and pre-configured tools are not available, including web search. Client-side tool use works on both endpoints.

  • Only the default project is supported. See Projects (OpenAI-compatible).

  • A stored response belongs to the AWS Region that served it. Retrieving, cancelling, or deleting it, and continuing the conversation with previous_response_id, are all handled by that Region.

Inference capabilities
Capability bedrock-runtime bedrock-mantle
Cross-region inference (geographic and global profiles) supported not-supported
Stateful conversation management supported supported
Asynchronous (long-running) inference not-supported supported
Client-side tool use supported supported
Server-side tool use not-supported supported
Pre-configured ready-to-use tools not-supported supported
Projects Default project only supported
Workspaces not-supported supported

Authentication does not grant access by itself. Whether you use SigV4 or a Bedrock API key, the associated IAM principal must have permission for the required action. For complete policy requirements and examples, see Prerequisites for running model inference.

Operational
Item bedrock-runtime bedrock-mantle