> ## Documentation Index
> Fetch the complete documentation index at: https://docs.together.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# List inference instance types

> Lists hardware instance types currently available to inference deployments, including GPU resources, pricing, regions, and best-effort capacity headroom.



## OpenAPI

````yaml GET /public/inference-instance-types
openapi: 3.1.0
info:
  title: Together APIs
  description: The Together REST API. See https://docs.together.ai for more details.
  version: 2.0.0
  termsOfService: https://www.together.ai/terms-of-service
  contact:
    name: Together Support
    url: https://www.together.ai/contact
  license:
    name: MIT
    url: https://github.com/togethercomputer/openapi/blob/main/LICENSE
servers:
  - url: https://api.together.ai/v1
    description: Default environment for APIs
  - url: https://api-inference.together.ai/v2
    description: Optimized environment for inference
security:
  - bearerAuth: []
paths:
  /public/inference-instance-types:
    get:
      tags:
        - InstanceTypeService
      summary: List inference instance types
      description: >-
        Lists hardware instance types currently available to inference
        deployments, including GPU resources, pricing, regions, and best-effort
        capacity headroom.
      operationId: InstanceTypeService_ListInferenceInstanceTypes
      responses:
        '200':
          description: OK
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DE.ListInferenceInstanceTypesResponse'
        default:
          description: Default error response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorData'
      servers:
        - url: https://api.together.ai/v2
components:
  schemas:
    DE.ListInferenceInstanceTypesResponse:
      type: object
      description: Hardware instance types available for inference deployments.
      required:
        - data
        - object
      properties:
        data:
          type: array
          items:
            $ref: '#/components/schemas/DE.InferenceInstanceType'
          description: Instance types available for inference.
        next_cursor:
          type: string
          description: >-
            Cursor for the next page. Always null today because this catalog is
            returned in full.
        object:
          const: list
          description: Object type. Always `list`.
    ErrorData:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          properties:
            message:
              type: string
              nullable: false
            type:
              type: string
              nullable: false
            param:
              type: string
              nullable: true
              default: null
            code:
              type: string
              nullable: true
              default: null
          required:
            - type
            - message
    DE.InferenceInstanceType:
      type: object
      required:
        - id
        - name
        - description
        - gpuType
        - gpuCount
        - gpuMemoryGib
        - priceCentsPerHour
        - regions
      properties:
        id:
          type: string
          description: Stable hardware instance type identifier used by deployment configs.
        name:
          type: string
          description: Human-readable instance type name.
        description:
          type: string
          description: Human-readable summary of the hardware configuration.
        gpuType:
          type: string
          description: GPU accelerator model, such as `H100` or `B200`.
        gpuCount:
          type: integer
          description: Number of GPUs in one replica of this instance type.
        gpuMemoryGib:
          type: integer
          description: Memory available on each GPU, in GiB.
        priceCentsPerHour:
          type: integer
          description: On-demand price for one running replica, in US cents per hour.
        regions:
          type: array
          items:
            $ref: '#/components/schemas/DE.Region'
          description: Regions where this instance type is offered.
      description: GPU hardware configuration on which one inference replica can run.
    DE.Region:
      type: object
      required:
        - name
      properties:
        name:
          type: string
          description: Region name where an instance type is offered.
        headroom:
          allOf:
            - $ref: '#/components/schemas/DE.Headroom'
          description: >-
            Best-effort replica headroom for this region. Omitted when
            unavailable.
      description: Region where an instance type is offered.
    DE.Headroom:
      type: object
      required:
        - relation
      properties:
        value:
          type: integer
          description: Capped count of replicas that currently fit.
        relation:
          enum:
            - RELATION_EQ
            - RELATION_GTE
          type: string
          description: Whether the value is exact or a lower bound.
      description: >-
        Best-effort estimate of how many additional replicas currently fit in a
        region.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      x-bearer-format: bearer
      x-default: default

````