Together AI Queue API

openapi: 3.0.3
info:
  title: remediation.proto Audio Queue API
  version: version not set
servers:
- url: https://api.together.xyz/v1
security:
- bearerAuth: []
tags:
- name: Queue
paths:
  /queue/cancel:
    post:
      description: 'Cancel a pending job. Only jobs in pending status can be canceled.

        Running jobs cannot be stopped. Returns the job status after the

        attempt. If the job is not pending, returns 409 with the current status

        unchanged.

        '
      operationId: cancelQueueJob
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/QueueCancelRequest'
        description: Cancel request
        required: true
      responses:
        '200':
          description: Successfully canceled
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueCancelResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '404':
          description: Request not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '409':
          description: Job could not be canceled (already completed/failed)
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueCancelResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
      summary: Cancel a queued job
      tags:
      - Queue
  /queue/metrics:
    get:
      description: Get the current queue statistics for a model, including pending and running job counts.
      operationId: getQueueMetrics
      parameters:
      - name: model
        in: query
        required: true
        schema:
          description: Model name to get metrics for
          type: string
      responses:
        '200':
          description: Queue metrics
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueMetricsResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
      summary: Get queue metrics
      tags:
      - Queue
  /queue/status:
    get:
      description: Poll the current status of a previously submitted job. Provide the request_id and model as query parameters.
      operationId: getQueueJobStatus
      parameters:
      - name: request_id
        in: query
        required: true
        schema:
          description: Request ID returned from the submit endpoint
          type: string
      - name: model
        in: query
        required: true
        schema:
          description: Model name the job was submitted to
          type: string
      responses:
        '200':
          description: Status information
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueJobStatusResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '404':
          description: Request not found
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
      summary: Get job status
      tags:
      - Queue
  /queue/submit:
    post:
      description: 'Submit a new job to the queue for asynchronous processing. Jobs are

        processed in strict priority order (higher priority first, FIFO within

        the same priority). Returns a request ID that can be used to poll status

        or cancel the job.

        '
      operationId: submitQueueJob
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/QueueJobRequest'
        description: Job request
        required: true
      responses:
        '200':
          description: Successfully queued request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueJobResponse'
        '400':
          description: Invalid request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '401':
          description: Unauthorized
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/QueueError'
      summary: Submit a queued job
      tags:
      - Queue
components:
  schemas:
    QueueMetricsResponse:
      type: object
      required:
      - messages_running
      - messages_waiting
      - total_jobs
      properties:
        messages_running:
          description: Number of jobs currently being processed
          type: integer
        messages_waiting:
          description: Number of jobs waiting to be claimed by a worker
          type: integer
        total_jobs:
          description: Total number of active jobs (waiting + running)
          type: integer
    QueueJobStatusResponse:
      required:
      - request_id
      - model
      - status
      properties:
        claimed_at:
          description: Timestamp when a worker claimed the job
          format: date-time
          type: string
        created_at:
          description: Timestamp when the job was created
          format: date-time
          type: string
        done_at:
          description: Timestamp when the job completed (done or failed)
          format: date-time
          type: string
        info:
          description: 'Job metadata. Contains keys from the submit request, plus any

            modifications from the model or system (e.g. progress, retry

            history).

            '
          additionalProperties: true
          type: object
        inputs:
          description: Freeform model input, as submitted
          additionalProperties: true
          type: object
        model:
          description: Model identifier the job was submitted to
          type: string
        outputs:
          description: Freeform model output, populated when the job reaches done status. Contents are model-specific.
          additionalProperties: true
          type: object
        priority:
          description: Job priority. Higher values are processed first.
          type: integer
        request_id:
          description: The request ID that was returned from the submit endpoint
          type: string
        retries:
          description: 'Number of times this job has been retried. Workers set a claim

            timeout and must send periodic status updates to keep the job alive.

            If no update is received within the timeout, the job is returned to

            the queue and retried. After 3 retries the job is permanently

            failed. Jobs explicitly failed by the model are not retried.

            '
          type: integer
        status:
          description: 'Current job status. Transitions: pending → running → done/failed. A pending job may also be canceled.

            '
          enum:
          - pending
          - running
          - done
          - failed
          - canceled
          type: string
        warnings:
          description: Non-fatal messages about the request (e.g. deprecation notices)
          items:
            type: string
          type: array
      type: object
    QueueJobResponse:
      properties:
        error:
          $ref: '#/components/schemas/QueueError'
        requestId:
          description: Unique identifier for the submitted job. Use this to poll status or cancel.
          type: string
      type: object
    QueueError:
      properties:
        code:
          description: Machine-readable error code
          type: string
        message:
          description: Human-readable error message
          type: string
        param:
          description: The parameter that caused the error, if applicable
          type: string
        type:
          description: Error category (e.g. "invalid_request_error", "not_found_error")
          type: string
      type: object
    QueueCancelResponse:
      type: object
      required:
      - status
      properties:
        status:
          description: 'Job status after the cancel attempt. Only pending jobs can be

            canceled. If the job is already running, done, or failed, the status

            is returned unchanged.

            '
          type: string
          enum:
          - canceled
          - running
          - done
          - failed
    QueueJobRequest:
      properties:
        info:
          description: 'Arbitrary JSON metadata stored with the job and returned in status

            responses. The model and system may add or update keys during

            processing.

            '
          additionalProperties: true
          type: object
        model:
          description: Required model identifier
          type: string
        payload:
          description: Freeform model input. Passed unchanged to the model. Contents are model-specific.
          additionalProperties: true
          type: object
        priority:
          default: 0
          description: 'Job priority. Higher values are processed first (strict priority

            ordering). Jobs with equal priority are processed in submission

            order (FIFO).

            '
          type: integer
      required:
      - model
      - payload
      type: object
    QueueCancelRequest:
      properties:
        model:
          description: Model identifier the job was submitted to
          type: string
        request_id:
          description: The request ID returned from the submit endpoint
          type: string
      required:
      - model
      - request_id
      type: object
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      x-bearer-format: bearer
      x-default: default