openapi: 3.1.0
info:
  title: Friendli Suite API Reference Container.Audio Dedicated.Endpoint API
  description: This is an OpenAPI reference of Friendli Suite API.
  termsOfService: https://friendli.ai/terms-of-service
  contact:
    name: FriendliAI Support Team
    email: support@friendli.ai
  version: 0.1.0
servers:
- url: https://api.friendli.ai
tags:
- name: Dedicated.Endpoint
paths:
  /dedicated/endpoint/wandb-artifact-create:
    post:
      tags:
      - Dedicated.Endpoint
      summary: Create endpoint from W&B artifact
      description: Create an endpoint from Weights & Biases artifact. If the idempotency key is provided, the API will check if the endpoint already exists, and rollout the existing endpoint if it does. In such cases, the project id must be provided.
      operationId: dedicatedEndpointWandbArtifactCreate
      security:
      - token: []
      parameters:
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DedicatedEndpointWandbArtifactCreateBody'
      responses:
        '200':
          description: Successfully created the endpoint from W&B artifact.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointWandbArtifactCreateResponse'
              examples:
                Example:
                  value:
                    endpointId: endpoint-id
                    endpointName: endpoint-name
                    projectId: project-id
                    projectName: project-name
                    teamId: team-id
                    teamName: team-name
        '400':
          description: Bad Request
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: wandbArtifactCreate
      x-mint:
        metadata:
          title: Dedicated Create Endpoint from W&B Artifact
          sidebarTitle: Create Endpoint from W&B Artifact
          og:title: Dedicated Create Endpoint from W&B Artifact
          description: Create a Friendli Dedicated Endpoint from a Weights & Biases artifact via the API. Deploy W&B-managed models directly to dedicated GPU hardware.
          og:description: Create a Friendli Dedicated Endpoint from a Weights & Biases artifact via the API. Deploy W&B-managed models directly to dedicated GPU hardware.
        href: /openapi/dedicated/endpoint/wandb-artifact-create
        content: 'Create an endpoint from Weights & Biases artifact.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.'
  /dedicated/beta/endpoint:
    post:
      tags:
      - Dedicated.Endpoint
      summary: Create a new endpoint
      description: Create a new endpoint and return its status
      operationId: dedicatedCreateEndpoint
      security:
      - token: []
      parameters:
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DedicatedEndpointCreateBody'
      responses:
        '200':
          description: Successfully created the endpoint.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: INITIALIZING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
                    phase: DOWNLOADING_MODEL
        '400':
          description: Bad Request
        '422':
          description: Unprocessable Entity
        '500':
          description: Internal Server Error
      x-speakeasy-name-override: create
      x-mint:
        metadata:
          title: Dedicated Create Endpoint
          sidebarTitle: Create an Endpoint with Hugging Face Model
          og:title: Dedicated Create Endpoint
          description: Create a Friendli Dedicated Endpoint deployment for a Hugging Face model via the API. Specify GPU type, replica count, and model configuration.
          og:description: Create a Friendli Dedicated Endpoint deployment for a Hugging Face model via the API. Specify GPU type, replica count, and model configuration.
        href: /openapi/dedicated/endpoint/create
        content: 'Create a Dedicated Endpoint deployment for a Hugging Face model.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
    get:
      tags:
      - Dedicated.Endpoint
      summary: List all endpoints
      description: List all endpoint statuses
      operationId: dedicatedListEndpoints
      security:
      - token: []
      parameters:
      - name: project_id
        in: query
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: The ID of the project. If omitted, query all endpoints under the team.
          default: ''
          title: Project Id
        description: The ID of the project. If omitted, query all endpoints under the team.
      - name: cursor
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: binary
          - type: 'null'
          description: Cursor for pagination
          title: Cursor
        description: Cursor for pagination
      - name: limit
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
            maximum: 100
            minimum: 1
          - type: 'null'
          description: Limit of items per page
          default: 20
          title: Limit
        description: Limit of items per page
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully listed endpoints.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointListResponse'
              examples:
                Example:
                  value:
                    data:
                      endpoint-id-1:
                        status: INITIALIZING
                        createdAt: '2025-01-01T00:00:00Z'
                        updatedAt: '2025-01-01T00:00:00Z'
                        phase: DOWNLOADING_MODEL
                      endpoint-id-2:
                        status: RUNNING
                        createdAt: '2025-01-01T00:00:00Z'
                        updatedAt: '2025-01-01T00:00:00Z'
        '400':
          description: Bad Request
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: list
      x-mint:
        metadata:
          title: Dedicated List Endpoints
          sidebarTitle: List Endpoints
          og:title: Dedicated List Endpoints
          description: List all Friendli Dedicated Endpoint deployments in your project. Returns endpoint IDs, statuses, model names, and GPU configurations.
          og:description: List all Friendli Dedicated Endpoint deployments in your project. Returns endpoint IDs, statuses, model names, and GPU configurations.
        href: /openapi/dedicated/endpoint/list
        content: 'List Dedicated Endpoint deployments.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}:
    get:
      tags:
      - Dedicated.Endpoint
      summary: Get endpoint specification
      description: Get the specification of an endpoint
      operationId: dedicatedGetEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully retrieved the endpoint specification.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointSpec'
              examples:
                Example:
                  value:
                    name: endpoint-name
                    gpuType: NVIDIA H100
                    numGpu: 1
                    instanceId: instance-id
                    projectId: project-id
                    creatorId: creator-id
                    teamId: team-id
                    autoscalingMin: 0
                    autoscalingMax: 1
                    autoscalingCooldown: 300
                    maxBatchSize: 10
                    maxInputLength: 1024
                    tokenizerSkipSpecialTokens: true
                    tokenizerAddSpecialTokens: true
                    currReplicaCnt: 1
                    desiredReplicaCnt: 1
                    updatedReplicaCnt: 1
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: getSpec
      x-mint:
        metadata:
          title: Dedicated Get Endpoint
          sidebarTitle: Retrieve an Endpoint Specification
          og:title: Dedicated Get Endpoint
          description: Retrieve the full specification of a Friendli Dedicated Endpoint by ID, including model config, GPU type, replica count, and deployment settings.
          og:description: Retrieve the full specification of a Friendli Dedicated Endpoint by ID, including model config, GPU type, replica count, and deployment settings.
        href: /openapi/dedicated/endpoint/get-spec
        content: 'Given an endpoint ID, return its specification.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
    put:
      tags:
      - Dedicated.Endpoint
      summary: Update endpoint spec
      description: Update the specification of a specific endpoint
      operationId: dedicatedUpdateEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/DedicatedEndpointUpdateBody'
      responses:
        '200':
          description: Successfully updated the endpoint specification.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointSpec'
              examples:
                Example:
                  value:
                    name: endpoint-name
                    gpuType: NVIDIA H100
                    numGpu: 1
                    instanceId: instance-id
                    projectId: project-id
                    creatorId: creator-id
                    teamId: team-id
                    autoscalingMin: 0
                    autoscalingMax: 1
                    autoscalingCooldown: 300
                    maxBatchSize: 10
                    maxInputLength: 1024
                    tokenizerSkipSpecialTokens: true
                    tokenizerAddSpecialTokens: true
                    currReplicaCnt: 1
                    desiredReplicaCnt: 1
                    updatedReplicaCnt: 1
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: update
      x-mint:
        metadata:
          title: Dedicated Update Endpoint
          sidebarTitle: Update an Endpoint with New Configuration
          og:title: Dedicated Update Endpoint
          description: Update a Friendli Dedicated Endpoint with a new model, GPU type, or replica count. Changes are applied as a new version in the deployment history.
          og:description: Update a Friendli Dedicated Endpoint with a new model, GPU type, or replica count. Changes are applied as a new version in the deployment history.
        href: /openapi/dedicated/endpoint/update
        content: 'Update a Dedicated Endpoint deployment with new configuration.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
    delete:
      tags:
      - Dedicated.Endpoint
      summary: Delete endpoint
      description: Delete a specific endpoint
      operationId: dedicatedDeleteEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema: {}
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      x-speakeasy-name-override: delete
      x-mint:
        metadata:
          title: Dedicated Delete Endpoint
          sidebarTitle: Delete an Endpoint
          og:title: Dedicated Delete Endpoint
          description: Permanently delete a Friendli Dedicated Endpoint deployment by ID. This stops the endpoint and releases all associated GPU resources immediately.
          og:description: Permanently delete a Friendli Dedicated Endpoint deployment by ID. This stops the endpoint and releases all associated GPU resources immediately.
        href: /openapi/dedicated/endpoint/delete
        content: 'Delete an endpoint.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/version:
    get:
      tags:
      - Dedicated.Endpoint
      summary: Get endpoint version history
      description: Get version history of a specific endpoint
      operationId: dedicatedGetEndpointVersionHistory
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: cursor
        in: query
        required: false
        schema:
          anyOf:
          - type: string
            format: binary
          - type: 'null'
          description: Cursor for pagination
          title: Cursor
        description: Cursor for pagination
      - name: limit
        in: query
        required: false
        schema:
          anyOf:
          - type: integer
            maximum: 100
            minimum: 1
          - type: 'null'
          description: Limit of items per page
          default: 20
          title: Limit
        description: Limit of items per page
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully retrieved the endpoint version history.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointVersionHistoryResponse'
              examples:
                Example:
                  value:
                    data:
                      '0':
                        name: endpoint-name
                        gpuType: NVIDIA H100
                        numGpu: 1
                        instanceId: instance-id
                        projectId: project-id
                        creatorId: creator-id
                        teamId: team-id
                        autoscalingMin: 0
                        autoscalingMax: 1
                        autoscalingCooldown: 300
                        maxBatchSize: 10
                        maxInputLength: 1024
                        tokenizerSkipSpecialTokens: true
                        tokenizerAddSpecialTokens: true
                        currReplicaCnt: 1
                        desiredReplicaCnt: 1
                        updatedReplicaCnt: 1
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: getVersionHistory
      x-mint:
        metadata:
          title: Dedicated Get Endpoint Version
          sidebarTitle: Retrieve Endpoint Version History
          og:title: Dedicated Get Endpoint Version
          description: Retrieve the version history of a Friendli Dedicated Endpoint by ID. View past configurations and rollback points for deployment tracking.
          og:description: Retrieve the version history of a Friendli Dedicated Endpoint by ID. View past configurations and rollback points for deployment tracking.
        href: /openapi/dedicated/endpoint/get-version
        content: 'Given an endpoint ID, return its version history.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/status:
    get:
      tags:
      - Dedicated.Endpoint
      summary: Get endpoint status
      description: Get the status of a specific endpoint
      operationId: dedicatedGetEndpointStatus
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully retrieved the endpoint status.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: INITIALIZING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
                    phase: DOWNLOADING_MODEL
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: getStatus
      x-mint:
        metadata:
          title: Dedicated Get Endpoint Status
          sidebarTitle: Retrieve an Endpoint Status
          og:title: Dedicated Get Endpoint Status
          description: Check the current status of a Friendli Dedicated Endpoint by ID. Returns the lifecycle state such as running, sleeping, initializing, or terminated.
          og:description: Check the current status of a Friendli Dedicated Endpoint by ID. Returns the lifecycle state such as running, sleeping, initializing, or terminated.
        href: /openapi/dedicated/endpoint/get-status
        content: 'Given an endpoint ID, return its current status.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/sleep:
    put:
      tags:
      - Dedicated.Endpoint
      summary: Sleep endpoint
      description: Put a specific endpoint to sleep
      operationId: dedicatedSleepEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully requested to put the endpoint to sleep.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: SLEEPING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: sleep
      x-mint:
        metadata:
          title: Dedicated Sleep Endpoint
          sidebarTitle: Sleep an Endpoint
          og:title: Dedicated Sleep Endpoint
          description: Put a Friendli Dedicated Endpoint into sleep mode by ID. The endpoint stops serving but retains its configuration for quick wake-up later.
          og:description: Put a Friendli Dedicated Endpoint into sleep mode by ID. The endpoint stops serving but retains its configuration for quick wake-up later.
        href: /openapi/dedicated/endpoint/sleep
        content: 'Put a Dedicated Endpoint to sleep mode.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/wake:
    put:
      tags:
      - Dedicated.Endpoint
      summary: Wake endpoint
      description: Wake up a specific endpoint
      operationId: dedicatedWakeEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully requested to wake up the endpoint.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: AWAKING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
                    phase: ENGINE_INITIALIZING
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
        '500':
          description: Internal Server Error
      x-speakeasy-name-override: wake
      x-mint:
        metadata:
          title: Dedicated Wake Endpoint
          sidebarTitle: Wake Up an Endpoint
          og:title: Dedicated Wake Endpoint
          description: Wake up a sleeping Friendli Dedicated Endpoint by ID. The endpoint resumes serving with its previous model and GPU configuration intact.
          og:description: Wake up a sleeping Friendli Dedicated Endpoint by ID. The endpoint resumes serving with its previous model and GPU configuration intact.
        href: /openapi/dedicated/endpoint/wake
        content: 'Wake up a sleeping Dedicated Endpoint.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/terminate:
    put:
      tags:
      - Dedicated.Endpoint
      summary: Terminate endpoint
      description: Terminate a specific endpoint
      operationId: dedicatedTerminateEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully requested to terminate the endpoint.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: TERMINATING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
      x-speakeasy-name-override: terminate
      x-mint:
        metadata:
          title: Dedicated Terminate Endpoint
          sidebarTitle: Terminate an Endpoint
          og:title: Dedicated Terminate Endpoint
          description: Terminate a running Friendli Dedicated Endpoint by ID. Stops all inference and releases GPU resources while preserving the endpoint configuration.
          og:description: Terminate a running Friendli Dedicated Endpoint by ID. Stops all inference and releases GPU resources while preserving the endpoint configuration.
        href: /openapi/dedicated/endpoint/terminate
        content: 'Terminate an endpoint.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
  /dedicated/beta/endpoint/{endpoint_id}/restart:
    put:
      tags:
      - Dedicated.Endpoint
      summary: Restart endpoint
      description: Restart a FAILED or TERMINATED endpoint
      operationId: dedicatedRestartEndpoint
      security:
      - token: []
      parameters:
      - name: endpoint_id
        in: path
        required: true
        schema:
          type: string
          description: The ID of the endpoint
          title: Endpoint Id
        description: The ID of the endpoint
      - name: X-Friendli-Team
        in: header
        required: false
        schema:
          anyOf:
          - type: string
          - type: 'null'
          description: ID of team to run requests as (optional parameter).
          title: X-Friendli-Team
        description: ID of team to run requests as (optional parameter).
      responses:
        '200':
          description: Successfully requested to restart the endpoint.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DedicatedEndpointStatus'
              examples:
                Example:
                  value:
                    status: INITIALIZING
                    createdAt: '2025-01-01T00:00:00Z'
                    updatedAt: '2025-01-01T00:00:00Z'
                    phase: DOWNLOADING_MODEL
        '400':
          description: Bad Request
        '404':
          description: Not Found
        '422':
          description: Unprocessable Entity
        '500':
          description: Internal Server Error
      x-speakeasy-name-override: restart
      x-mint:
        metadata:
          title: Dedicated Restart Endpoint
          sidebarTitle: Restart an Endpoint
          og:title: Dedicated Restart Endpoint
          description: Restart a failed or terminated Friendli Dedicated Endpoint by ID. The endpoint re-initializes with the same model and GPU configuration.
          og:description: Restart a failed or terminated Friendli Dedicated Endpoint by ID. The endpoint re-initializes with the same model and GPU configuration.
        href: /openapi/dedicated/endpoint/restart
        content: 'Restart a failed or terminated Dedicated Endpoint.


          To request successfully, it is mandatory to enter a **Personal API Key** (e.g. flp_XXX) value in the **Bearer Token** field.

          Refer to the [authentication section](/openapi/introduction#authentication) on our introduction page to learn how to acquire this variable and [visit here](https://friendli.ai/suite/~/setting/keys) to generate your API Key.


          <Info>

          This API is currently in **Beta**.

          While we strive to provide a stable and reliable experience, this feature is still under active development.

          As a result, you may encounter unexpected behavior or limitations.

          We encourage you to provide feedback to help us improve the feature before its official release.


          - [Feature request & feedback](mailto:support@friendli.ai)

          - [Contact support](mailto:support@friendli.ai)


          </Info>'
components:
  schemas:
    EndpointSimplescaleConfig:
      properties:
        replicas:
          type: integer
          minimum: 1.0
          title: Replicas
      type: object
      required:
      - replicas
      title: EndpointSimplescaleConfig
      description: Simple scaling options.
    DedicatedEndpointStatus:
      properties:
        status:
          $ref: '#/components/schemas/InferenceDeploymentStatus'
          title: Status
          description: The current status of the endpoint deployment.
        errorCode:
          anyOf:
          - $ref: '#/components/schemas/InferenceDeploymentErrorCode'
          - type: 'null'
          title: Error Code
          description: Error code if deployment failed.
        createdAt:
          type: string
          format: date-time
          title: Created At
          description: When the endpoint was created.
        updatedAt:
          anyOf:
          - type: string
            format: date-time
          - type: 'null'
          title: Updated At
          description: When the endpoint was last updated.
        phase:
          anyOf:
          - type: string
            enum:
            - REQUESTING_VIRTUAL_MACHINE
            - DOWNLOADING_MODEL
            - ENGINE_INITIALIZING
          - type: 'null'
          title: Phase
          description: The current phase of the endpoint.
      type: object
      required:
      - status
      - createdAt
      title: DedicatedEndpointStatus
      description: Dedicated endpoint status.
    DedicatedEndpointListResponse:
      properties:
        data:
          additionalProperties:
            $ref: '#/components/schemas/DedicatedEndpointStatus'
          type: object
          title: Data
          description: The response data containing endpoint statuses.
          default: {}
        nextCursor:
          anyOf:
          - type: string
            format: binary
          - type: 'null'
          title: Next Cursor
          description: The next cursor for pagination.
      type: object
      title: DedicatedEndpointListResponse
      description: Dedicated endpoint list response.
    AcceleratorRequirement:
      properties:
        type:
          type: string
          title: Type
          description: Specifies the instance type.
        count:
          type: integer
          title: Count
          description: Specifies the number of instances.
      type: object
      required:
      - type
      - count
      title: AcceleratorRequirement
      description: Accelerator requirement.
    DedicatedEndpointUpdateBody:
      properties:
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: The name of the endpoint.
        advanced:
          anyOf:
          - $ref: '#/components/schemas/EndpointAdvancedConfig'
          - type: 'null'
          title: Advanced
          description: The advanced configuration of the endpoint.
        simplescale:
          anyOf:
          - $ref: '#/components/schemas/EndpointSimplescaleConfig'
          - type: 'null'
          title: Simple Scale
          description: The simple scaling configuration of the endpoint.
        autoscalingPolicy:
          anyOf:
          - $ref: '#/components/schemas/AutoscalingPolicy'
          - type: 'null'
          title: Auto Scale Policy
          description: The auto scaling configuration of the endpoint.
        hfModelRepo:
          anyOf:
          - type: string
          - type: 'null'
          title: HF Model Repo
          description: HF ID of the model.
        hfModelRepoRevision:
          anyOf:
          - type: string
          - type: 'null'
          title: HF Model Repo Revision
          description: HF commit hash of the model.
        newVersionComment:
          anyOf:
          - type: string
          - type: 'null'
          title: New Version Comment
          description: Comment for the new version.
        instanceOptionId:
          anyOf:
          - type: string
          - type: 'null'
          title: Instance Option ID
          description: 'The ID of the instance option.


            Available options:

            - 1x NVIDIA A100 80GB: `ShbPuOs4tfGb`

            - 2x NVIDIA A100 80GB: `mrAHuYt7T40o`

            - 4x NVIDIA A100 80GB: `JkNob0NMdoF3`

            - 8x NVIDIA A100 80GB: `sYH4kHmAcA5P`

            - 1x NVIDIA H100: `TwD5AqnBSVN0`

            - 2x NVIDIA H100: `zfTutSiLn0Hq`

            - 4x NVIDIA H100: `lfkRz5G48REc`

            - 8x NVIDIA H100: `GUA4qYFmsYz8`

            - 1x NVIDIA H200: `LnK1wTaKc7WO`

            - 2x NVIDIA H200: `Tu6GjBnfHPe4`

            - 4x NVIDIA H200: `OhTzYtZuomzI`

            - 8x NVIDIA H200: `ahBzWtOuomsI`

            - 1x NVIDIA B200: `8GiQTLKfJNOr`

            - 2x NVIDIA B200: `brTZGIuYgVrs`

            - 4x NVIDIA B200: `AFoZMFXZnAdD`

            - 8x NVIDIA B200: `drbc6G9FxJWZ`'
      type: object
      title: DedicatedEndpointUpdateBody
      description: Dedicated endpoint update request.
    DedicatedEndpointWandbArtifactCreateBody:
      properties:
        wandbArtifactVersionName:
          type: string
          title: Wandb Artifact Version Name
          description: The specific model artifact version from Weights & Biases. The referred artifact will be used to create a new endpoint in Friendli Dedicated Endpoints or rollout an existing one.
        accelerator:
          anyOf:
          - $ref: '#/components/schemas/AcceleratorRequirement'
          - type: 'null'
          title: Accelerator
          description: Specifies the instance type for the endpoint.
        name:
          anyOf:
          - type: string
          - type: 'null'
          title: Name
          description: Specifies the name of your endpoint. If not provided, a name will be automatically generated for you.
        projectId:
          anyOf:
          - type: string
          - type: 'null'
          title: Project Id
          description: Specifies where endpoint will be created in your Friendli Dedicated Endpoints. If not provided, a new project will be created within your default team.
        idempotencyKey:
          anyOf:
          - type: string
          - type: 'null'
          title: Idempotency Key
          description: Used by Friendli Dedicated Endpoints to track which webhook automation triggered an endpoint rollout. If the `idempotencyKey` is provided, the API will check if the endpoint already exists, and rollout the existing endpoint if it does. In such cases, the `projectId` must be provided. Any unique value can be used.
        autoscalingPolicy:
          anyOf:
          - $ref: '#/components/schemas/AutoscalingPolicy'
          - type: 'null'
          title: Autoscaling Policy
          description: Defines autoscaling settings for the endpoint.
      type: object
      required:
      - wandbArtifactVersionName
      title: DedicatedEndpointWandbArtifactCreateBody
      description: Endpoint create request.
      example:
        wandbArtifactVersionName: org/registry/name:v0
    DedicatedEndpointWandbArtifactCreateResponse:
      properties:
        endpointId:
          type: string
          title: Endpoint Id
          description: The ID of the created endpoint.
        endpointName:
          type: string
          title: Endpoint Name
          description: The name of the created endpoint.
        projectId:
          type: string
          title: Project Id
          description: The ID of the project where the endpoint was created.
        projectName:
          type: string
          title: Project Name
          description: The name of the project where the endpoint was created.
        teamId:
          type: string
          title: Team Id
          description: The ID of the team where the endpoint was created.
        teamName:
          anyOf:
          - type: string
          - type: 'null'
          title: Team Name
          description: The name of the team where the endpoint was created.
      type: object
      required:
      - endpointId
      - endpointName
      - projectId
      - projectName
      - teamId
      - teamName
      title: DedicatedEndpointWandbArtifactCreateResponse
      description: Endpoint create response.
    AutoscalingPolicy:
      properties:
        minReplica:
          type: integer
          minimum: 0.0
          title: Minimum Replica
          description: Setting `minReplica` to 0 allows the endpoint to sleep when idle, reducing costs. The minimum value is 0.
          default: 0
        maxReplica:
          type: integer
          maximum: 10.0
          title: Maximum Replica
          description: The maximum replicas that the endpoint can scale up to. The maximum value is 10.
          default: 1
        cooldownPeriod:
          type: integer
          title: Cooldown Period
          description: Determines how long the endpoint waits before scaling down after the last request.
          default: 300
      type: object
      title: AutoscalingPolicy
      description: Autoscaling policy.
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
            - type: string
            - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
      - loc
      - msg
      - type
      title: ValidationError
    DedicatedEndpointSpec:
      properties:
        name:
          type: string
          title: Name
          description: The name of the endpoint.
        gpuType:
          type: string
          title: GPU Type
          description: The type of GPU to use for the endpoint.
        numGpu:
          type: integer
          title: Number of GPUs
          description: The number of GPUs to use per replica.
        instanceId:
          anyOf:
          - type: string
          - type: 'null'
          title: Instance ID
          description: The ID of the instance.
        projectId:
          type: string
          title: Project ID
          description: The ID of the project that owns the endpoint.
        creatorId:
          type: string
          title: Creator ID
          description: The ID of the user who created the endpoint.
        teamId:
          type: string
          title: Team ID
          description: The ID of the team that owns the endpoint.
        autoscalingMin:
          type: integer
          title: Minimum Replicas
          description: The minimum number of replicas to maintain.
        autoscalingMax:
          type: integer
          title: Maximum Replicas
          description: The maximum number of replicas allowed.
        autoscalingCooldown:
          type: integer
          title: Autoscaling Cooldown
          description: The cooldown period in seconds between scaling operations.
        maxBatchSize:
          type: integer
          title: Maximum Batch Size
          description: The maximum batch size for inference requests.
        maxInputLength:
          anyOf:
          - type: integer
          - type: 'null'
          title: Maximum Input Length
          description: The maximum allowed input length.
        tokenizerSkipSpecialTokens:
          type: boolean
          title: Skip Special Tokens
          description: Whether to skip special tokens in tokenizer output.
        tokenizerAddSpecialTokens:
          type: boolean
          title: Add Special Tokens
          description: Whether to add special tokens in tokenizer input.
        currReplicaCnt:
          anyOf:
          - type: integer
          - type: 'null'
          title: Current Replica Count
          description: The current number of replicas.
        desiredReplicaCnt:
          anyOf:
          - type: integer
          - type: 'null'
          title: Desired Replica Count
          description: The desired number of replicas.
        updatedReplicaCnt:
          anyOf:
          - type: integer
          - type: 'null'
          title: Updated Replica Count
          description: The updated number of replicas.
      type: object
      required:
      - name
      - gpuType
      - numGpu
      - projectId
      - creatorId
      - teamId
      - autoscalingMin
      - autoscalingMax
      - autoscalingCooldown
      - maxBatchSize
      - tokenizerSkipSpecialTokens
      - tokenizerAddSpecialTokens
      title: DedicatedEndpointSpec
      description: Dedicated endpoint specification.
    DedicatedEndpointVersionHistoryResponse:
      properties:
        data:
          additionalProperties:
            $ref: '#/components/schemas/DedicatedEndpointSpec'
          type: object
          title: Data
          description: The response data containing endpoint versions.
          default: {}
        nextCursor:
          anyOf:
          - type: string
            format: binary
          - type: 'null'
          title: Next Cursor
          description: The next cursor for pagination.
      type: object
      title: DedicatedEndpointVersionHistoryResponse
      description: Dedicated endpoint version history response.
    DedicatedEndpointCreateBody:
      properties:
        projectId:
          type: string
          title: Project ID
          description: The ID of the project that owns the endpoint.
        name:
          type: string
          title: Name
          description: The name of the endpoint.
        instanceOptionId:
          type: string
          title: Instance Option ID
          description: 'The ID of the instance option.


            Available options:

            - 1x NVIDIA A100 80GB: `ShbPuOs4tfGb`

            - 2x NVIDIA A100 80GB: `mrAHuYt7T40o`

            - 4x NVIDIA A100 80GB: `JkNob0NMdoF3`

            - 8x NVIDIA A100 80GB: `sYH4kHmAcA5P`

            - 1x NVIDIA H100: `TwD5AqnBSVN0`

            - 2x NVIDIA H100: `zfTutSiLn0Hq`

            - 4x NVIDIA H100: `lfkRz5G48REc`

            - 8x NVIDIA H100: `GUA4qYFmsYz8`

            - 1x NVIDIA H200: `LnK1wTaKc7WO`

            - 2x NVIDIA H200: `Tu6GjBnfHPe4`

            - 4x NVIDIA H200: `OhTzYtZuomzI`

            - 8x NVIDIA H200: `ahBzWtOuomsI`

            - 1x NVIDIA B200: `8GiQTLKfJNOr`

            - 2x NVIDIA B200: `brTZGIuYgVrs`

            - 4x NVIDIA B200: `AFoZMFXZnAdD`

            - 8x NVIDIA B200: `drbc6G9FxJWZ`'
        advanced:
          $ref: '#/components/schemas/EndpointAdvancedConfig'
          title: Advanced
          description: The advanced configuration of the endpoint.
        simplescale:
          anyOf:
          - $ref: '#/components/schemas/EndpointSimplescaleConfig'
          - type: 'null'
          title: Simple Scale
          description: The simple scaling configuration of the endpoint.
        autoscalingPolicy:
          anyOf:
          - $ref: '#/components/schemas/AutoscalingPolicy'
          - type: 'null'
          title: Auto Scale Policy
          description: The auto scaling configuration of the endpoint.
        hfModelRepo:
          type: string
          title: HF Model Repo
          description: HF ID of the model.
        hfModelRepoRevision:
          anyOf:
          - type: string
          - type: 'null'
          title: HF Model Repo Revision
          description: HF commit hash of the model.
        initialVersionComment:
          anyOf:
          - type: string
          - type: 'null'
          title: Initial Version Comment
          description: The comment for the initial version.
      type: object
      required:
      - projectId
      - name
      - instanceOptionId
      - advanced
      - hfModelRepo
      title: DedicatedEndpointCreateBody
      description: Dedicated endpoint create request.
    EndpointAdvancedConfig:
      properties:
        max_batch_size:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Batch Size
        tokenizer_skip_special_tokens:
          type: boolean
          title: Tokenizer Skip Special Tokens
        tokenizer_add_special_tokens:
          type: boolean
          title: Tokenizer Add Special Tokens
        max_token_count:
          type: integer
          title: Max Token Count
          default: 2560
        enable_content_logging:
          anyOf:
          - type: boolean
          - type: 'null'
          title: Enable Content Logging
        max_input_length:
          anyOf:
          - type: integer
          - type: 'null'
          title: Max Input Length
        queue_timeout_ms:
          anyOf:
          - type: integer
          - type: 'null'
          title: Queue Timeout Ms
        queue_backpressure_metric_kind:
          anyOf:
          - $ref: '#/components/schemas/QueueBackpressureMetricKind'
          - type: 'null'
        queue_backpressure_metric_threshold:
          anyOf:
          - type: number
          - type: 'null'
          title: Queue Backpressure Metric Threshold
      type: object
      required:
      - tokenizer_skip_special_tokens
      - tokenizer_add_special_tokens
      title: EndpointAdvancedConfig
      description: Endpoint advanced config.
    InferenceDeploymentErrorCode:
      type: string
      enum:
      - WORKLOAD_INIT_UNKNOWN_ERROR
      - WORKLOAD_INIT_SETTINGS_ERROR
      - WORKLOAD_INIT_GRPC_ERROR
      - WORKLOAD_INIT_MANIFEST_NOT_FOUND_ERROR
      - WORKLOAD_INIT_MANIFEST_TYPE_ERROR
      - WORKLOAD_INIT_DOWNLOAD_ERROR
      - WORKLOAD_INIT_INVALID_TOKEN_ERROR
      - WORKLOAD_INIT_CANNOT_ACCESS_REPO_ERROR
      - WORKLOAD_INIT_HF_WANDB_API_ERROR
      - WORKLOAD_INIT_INSUFFICIENT_DISK_ERROR
      - INFERENCE_ENGINE_UNKNOWN_ERROR
      - INFERENCE_ENGINE_INVALID_ARGUMENT_ERROR
      - INFERENCE_ENGINE_MEMORY_ERROR
      - INFERENCE_ENGINE_METERING_CLIENT_CONFIG_ERROR
      title: InferenceDeploymentErrorCode
      description: ErrorCode type.
    QueueBackpressureMetricKind:
      type: string
      enum:
      - TPOT_MS
      - TTFT_MS
      - REQUEST_COUNT
      - WORKSPACE_UTILIZATION
      - QUEUED_PREFILL_TOKENS
      title: QueueBackpressureMetricKind
      description: Queue backpressure metric kind.
    InferenceDeploymentStatus:
      type: string
      enum:
      - UNKNOWN
      - INITIALIZING
      - RUNNING
      - UPDATING
      - SLEEPING
      - AWAKING
      - FAILED
      - STOPPING
      - TERMINATING
      - TERMINATED
      - READY
      title: InferenceDeploymentStatus
      description: Status of inference deployment.
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
  securitySchemes:
    token:
      type: http
      description: 'When using Friendli Suite API for inference requests, you need to provide a **Friendli Token** for authentication and authorization purposes.


        For more detailed information, please refer [here](https://friendli.ai/docs/openapi/introduction#authentication).'
      scheme: bearer
x-speakeasy-retries:
  strategy: backoff
  backoff:
    initialInterval: 500
    maxInterval: 60000
    maxElapsedTime: 3600000
    exponent: 1.5
  statusCodes:
  - 429
  - 500
  - 502
  - 503
  - 504
  retryConnectionErrors: true