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

# List Deployment Options Route

> Return every deployable model's authored output-speed tiers and replica presets.



## OpenAPI

````yaml /openapi.json get /api/v1/deploy/options
openapi: 3.1.0
info:
  title: Trajectory API
  version: 0.1.0
servers:
  - url: https://api.trajectory.ai
security: []
paths:
  /api/v1/deploy/options:
    get:
      tags:
        - deployments
      summary: List Deployment Options Route
      description: >-
        Return every deployable model's authored output-speed tiers and replica
        presets.
      operationId: listDeploymentOptions
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DeploymentOptionsResponse'
        default:
          $ref: '#/components/responses/ApiErrorResponse'
components:
  schemas:
    DeploymentOptionsResponse:
      properties:
        models:
          items:
            $ref: '#/components/schemas/DeployableModelOptions'
          type: array
          title: Models
          description: >-
            Every deployable model's supported concurrency levels and
            output-speed tiers.
      type: object
      required:
        - models
      title: DeploymentOptionsResponse
    DeployableModelOptions:
      properties:
        base_model_id:
          $ref: '#/components/schemas/BaseModelSlug'
          description: Base model these options apply to.
        concurrency:
          items:
            $ref: '#/components/schemas/ExpectedConcurrency'
          type: array
          title: Concurrency
          description: Expected-concurrency levels this model can be deployed at.
        output_speed:
          items:
            $ref: '#/components/schemas/DeploymentSpeedOption'
          type: array
          title: Output Speed
          description: >-
            Output-speed tiers this model can be deployed at, with authored
            tok/s.
      type: object
      required:
        - base_model_id
        - concurrency
        - output_speed
      title: DeployableModelOptions
    ApiErrorEnvelope:
      properties:
        error:
          $ref: '#/components/schemas/ApiErrorBody'
      required:
        - error
      title: ApiErrorEnvelope
      type: object
    BaseModelSlug:
      type: string
      enum:
        - Qwen/Qwen3.5-4B
        - Qwen/Qwen3.5-397B-A17B
        - Qwen/Qwen3.6-35B-A3B
        - nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
        - nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16
        - nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16
        - openai/gpt-5-mini
        - openai/gpt-5.4-mini
        - openai/gpt-5.5
        - anthropic/claude-sonnet-4.6
        - google/gemini-3.1-pro-preview
      title: BaseModelSlug
    ExpectedConcurrency:
      type: string
      enum:
        - low
        - medium
        - high
      title: ExpectedConcurrency
      description: Traffic level a deployment is sized for; picks its replica count.
    DeploymentSpeedOption:
      properties:
        name:
          $ref: '#/components/schemas/OutputSpeed'
          description: Which output-speed tier this is.
        tokens_per_second:
          type: number
          title: Tokens Per Second
          description: Authored single-request output tokens/sec.
      type: object
      required:
        - name
        - tokens_per_second
      title: DeploymentSpeedOption
      description: >-
        One output-speed choice and its authored throughput. No pricing yet: see
        cost field TBD.
    ApiErrorBody:
      properties:
        type:
          $ref: '#/components/schemas/ErrorType'
        code:
          title: Code
          type: string
        message:
          type: string
          title: Message
        param:
          anyOf:
            - type: string
            - type: 'null'
          default: null
          title: Param
        doc_url:
          type: string
          title: Doc Url
        context:
          additionalProperties: true
          title: Context
          type: object
      required:
        - type
        - code
        - message
        - doc_url
        - context
      title: ApiErrorBody
      type: object
    OutputSpeed:
      type: string
      enum:
        - normal
        - turbo
      title: OutputSpeed
      description: 'Which GPU tier a deployment runs on: H100 (normal) or B200 (turbo).'
    ErrorType:
      enum:
        - invalid_request_error
        - authentication_error
        - permission_error
        - conflict_error
        - rate_limit_error
        - dependency_error
        - api_error
      title: ErrorType
      type: string
  responses:
    ApiErrorResponse:
      description: >-
        Common API error. Possible codes: `authentication_required`,
        `permission_denied`, `validation_error`, `rate_limited`,
        `internal_error`, `service_unavailable`.
      headers:
        X-Request-ID:
          $ref: '#/components/headers/RequestId'
        Trajectory-Should-Retry:
          $ref: '#/components/headers/TrajectoryShouldRetry'
        Retry-After:
          $ref: '#/components/headers/RetryAfter'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ApiErrorEnvelope'
  headers:
    RequestId:
      schema:
        type: string
    TrajectoryShouldRetry:
      schema:
        type: boolean
    RetryAfter:
      schema:
        type: string

````