Amazon Bedrock Inference API

openapi: 3.1.0
info:
  title: Amazon Bedrock Converse Inference API
  description: The Amazon Bedrock management API provides operations for managing foundation models, custom models, model customization jobs, provisioned throughput, and other Bedrock resources.
  version: '2023-04-20'
  contact:
    name: AWS Support
    url: https://aws.amazon.com/support/
  license:
    name: Apache 2.0
    url: https://www.apache.org/licenses/LICENSE-2.0.html
servers:
- url: https://bedrock.{region}.amazonaws.com
  description: Amazon Bedrock Management API
  variables:
    region:
      default: us-east-1
      description: The AWS region
      enum:
      - us-east-1
      - us-west-2
      - eu-west-1
      - ap-southeast-1
tags:
- name: Inference
  description: Operations for invoking models and running inference.
paths:
  /model/{modelId}/invoke:
    post:
      operationId: InvokeModel
      summary: Amazon Bedrock Invoke a model
      description: Invokes the specified Amazon Bedrock model to run inference using the prompt and inference parameters provided in the request body. The response is returned in a single response body.
      tags:
      - Inference
      parameters:
      - name: modelId
        in: path
        required: true
        description: The identifier of the model to invoke (e.g., anthropic.claude-3-sonnet-20240229-v1:0).
        schema:
          type: string
      - name: Content-Type
        in: header
        description: The MIME type of the input data in the request body.
        schema:
          type: string
          default: application/json
      - name: Accept
        in: header
        description: The desired MIME type of the inference body in the response.
        schema:
          type: string
          default: application/json
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/InvokeModelRequest'
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InvokeModelResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationException'
        '403':
          description: Access denied
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AccessDeniedException'
        '404':
          description: Resource not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceNotFoundException'
        '429':
          description: Too many requests
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ThrottlingException'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerException'
  /model/{modelId}/invoke-with-response-stream:
    post:
      operationId: InvokeModelWithResponseStream
      summary: Amazon Bedrock Invoke a model with response streaming
      description: Invokes the specified Amazon Bedrock model to run inference using the prompt and parameters provided in the request body. The response is streamed back in real time, allowing the client to begin processing results before the full response is generated.
      tags:
      - Inference
      parameters:
      - name: modelId
        in: path
        required: true
        description: The identifier of the model to invoke.
        schema:
          type: string
      - name: Content-Type
        in: header
        description: The MIME type of the input data in the request body.
        schema:
          type: string
          default: application/json
      - name: X-Amzn-Bedrock-Accept
        in: header
        description: The desired MIME type of the inference body in the response.
        schema:
          type: string
          default: application/json
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/InvokeModelRequest'
      responses:
        '200':
          description: Successful streaming response
          content:
            application/vnd.amazon.eventstream:
              schema:
                $ref: '#/components/schemas/InvokeModelWithResponseStreamResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationException'
        '429':
          description: Too many requests
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ThrottlingException'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerException'
components:
  schemas:
    ThrottlingException:
      type: object
      properties:
        message:
          type: string
    InvokeModelResponse:
      type: object
      description: The response from the model invocation.
      properties:
        body:
          type: string
          format: byte
          description: The inference response from the model, encoded as a JSON string.
        contentType:
          type: string
          description: The MIME type of the response body.
    AccessDeniedException:
      type: object
      properties:
        message:
          type: string
    InvokeModelWithResponseStreamResponse:
      type: object
      description: The streaming response from the model invocation.
      properties:
        body:
          type: object
          description: The streaming response body as an event stream.
          properties:
            chunk:
              type: object
              properties:
                bytes:
                  type: string
                  format: byte
                  description: A chunk of the streamed response.
    ResourceNotFoundException:
      type: object
      properties:
        message:
          type: string
    InvokeModelRequest:
      type: object
      description: The request body for invoking a model. The structure depends on the model being invoked. This is passed as an opaque blob to the model.
      properties:
        body:
          type: string
          format: byte
          description: The prompt and inference parameters encoded as a JSON string, in the format required by the specified model.
        contentType:
          type: string
          description: The MIME type of the input data.
        accept:
          type: string
          description: The desired MIME type of the response.
    ValidationException:
      type: object
      properties:
        message:
          type: string
    InternalServerException:
      type: object
      properties:
        message:
          type: string