Amazon Bedrock Provisioned Throughput API

Operations for managing provisioned model throughput.

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools

Call it yourself

curl for this page
This API
curl "https://apis.io/api/v1/apis/amazon-bedrock-provisioned-throughput-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

amazon-bedrock-provisioned-throughput-api-openapi.yml Raw ↑
openapi: 3.1.0
info:
  title: Amazon Bedrock Converse Provisioned Throughput 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: Provisioned Throughput
  description: Operations for managing provisioned model throughput.
paths:
  /provisioned-model-throughput:
    post:
      operationId: CreateProvisionedModelThroughput
      summary: Amazon Bedrock Create provisioned model throughput
      description: Creates a provisioned throughput with dedicated capacity for a foundation model or custom model. Provisioned throughput provides guaranteed inference performance.
      tags:
      - Provisioned Throughput
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateProvisionedModelThroughputRequest'
      responses:
        '201':
          description: Provisioned throughput created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateProvisionedModelThroughputResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationException'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerException'
    get:
      operationId: ListProvisionedModelThroughputs
      summary: Amazon Bedrock List provisioned model throughputs
      description: Lists the provisioned throughputs that you have created.
      tags:
      - Provisioned Throughput
      parameters:
      - name: maxResults
        in: query
        description: Maximum number of results to return.
        schema:
          type: integer
          minimum: 1
          maximum: 100
      - name: nextToken
        in: query
        description: Token for pagination.
        schema:
          type: string
      - name: statusEquals
        in: query
        description: Filter by status.
        schema:
          type: string
          enum:
          - Creating
          - InService
          - Updating
          - Failed
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListProvisionedModelThroughputsResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ValidationException'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerException'
components:
  schemas:
    CreateProvisionedModelThroughputResponse:
      type: object
      properties:
        provisionedModelArn:
          type: string
          description: The ARN of the provisioned throughput.
    ValidationException:
      type: object
      properties:
        message:
          type: string
    CreateProvisionedModelThroughputRequest:
      type: object
      required:
      - modelUnits
      - provisionedModelName
      - modelId
      properties:
        modelUnits:
          type: integer
          description: Number of model units to allocate.
        provisionedModelName:
          type: string
          description: A name for the provisioned throughput.
        modelId:
          type: string
          description: The ID of the model to provision.
        commitmentDuration:
          type: string
          enum:
          - OneMonth
          - SixMonths
          description: The commitment duration.
    InternalServerException:
      type: object
      properties:
        message:
          type: string
    ListProvisionedModelThroughputsResponse:
      type: object
      properties:
        provisionedModelSummaries:
          type: array
          items:
            type: object
            properties:
              provisionedModelArn:
                type: string
              provisionedModelName:
                type: string
              modelArn:
                type: string
              status:
                type: string
              modelUnits:
                type: integer
              creationTime:
                type: string
                format: date-time
        nextToken:
          type: string