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

# Create task

> Submit a Runway task (text / image / video to video).

**Path:** `POST https://api.omniall.ai/v1/task/submit`

Also `POST /runway/v1/task/submit`. Body: `model` + `input` object.

**Use cases (same endpoint):** text-to-video · image-to-video · video-to-video — pick an example below.

Auth: `Authorization: Bearer sk-...`



## OpenAPI

````yaml openapi/runway-unified.yaml POST /v1/task/submit
openapi: 3.1.0
info:
  title: Omniall AI — Runway (unified task)
  version: 1.0.0
  description: >-
    Runway via unified task API (recommended).


    **Create:** `POST https://api.omniall.ai/v1/task/submit`


    Alias: `POST /runway/v1/task/submit`


    **Poll:** `GET /v1/task/{task_id}` (alias `GET /runway/v1/task/{task_id}`)


    Models (examples): `gen4_turbo`, `gen4_turbo/image-to-video`, `gen4_aleph`,
    `gen4_aleph/video-to-video`, `gen3a_turbo`, `gen4.5/image-to-video` — see
    [Model Square](https://omniall.ai/pricing).


    Auth: `Authorization: Bearer sk-...`
servers:
  - url: https://api.omniall.ai
security: []
paths:
  /v1/task/submit:
    post:
      tags:
        - Runway unified
      summary: Create task
      description: >-
        Submit a Runway task (text / image / video to video).


        **Path:** `POST https://api.omniall.ai/v1/task/submit`


        Also `POST /runway/v1/task/submit`. Body: `model` + `input` object.


        **Use cases (same endpoint):** text-to-video · image-to-video ·
        video-to-video — pick an example below.


        Auth: `Authorization: Bearer sk-...`
      operationId: runwayUnifiedSubmit
      parameters:
        - name: Authorization
          in: header
          required: true
          schema:
            type: string
            example: Bearer sk-...
          description: Bearer API key.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - model
                - input
              properties:
                model:
                  type: string
                  description: Model id, e.g. `gen4_turbo`, `gen4_aleph/video-to-video`.
                  example: gen4_turbo
                input:
                  type: object
                  description: Task input. Fields depend on text / image / video mode.
                  properties:
                    promptText:
                      type: string
                      maxLength: 1000
                      description: >-
                        Prompt text (max 1000 chars UTF-16). Required for most
                        modes.
                    promptImage:
                      oneOf:
                        - type: string
                        - type: array
                          items:
                            type: string
                      description: Reference image URL(s) for image-to-video.
                    videoUri:
                      type: string
                      description: >-
                        Source video HTTPS / Runway / data URI for
                        video-to-video.
                    ratio:
                      type: string
                      enum:
                        - '1280:720'
                        - '720:1280'
                        - '1104:832'
                        - '960:960'
                        - '832:1104'
                        - '1584:672'
                      description: Output ratio.
                    duration:
                      type: integer
                      minimum: 2
                      maximum: 10
                      description: Duration in seconds (2–10).
                    seed:
                      oneOf:
                        - type: string
                        - type: integer
                      description: Seed 0–4294967295.
                    references:
                      type: array
                      items:
                        type: object
                      description: Optional references (video-to-video).
                    contentModeration:
                      type: object
                      description: Content moderation options.
                callback_url:
                  type: string
                  description: Optional callback URL.
            examples:
              text_to_video:
                summary: Text-to-video
                value:
                  model: gen4_turbo
                  input:
                    promptText: A cat walking in the rain
                    ratio: '1280:720'
                    duration: 5
              image_to_video:
                summary: Image-to-video
                value:
                  model: gen4_turbo
                  input:
                    promptText: A cat walking in the rain
                    promptImage: https://example.com/cat.png
                    ratio: '1280:720'
                    duration: 5
              video_to_video:
                summary: Video-to-video
                value:
                  model: gen4_aleph/video-to-video
                  input:
                    videoUri: https://example.com/source.mp4
                    promptText: Cinematic color grade, slow motion
                    ratio: '1280:720'
                    duration: 5
      responses:
        '200':
          description: Task accepted
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnifiedTask'
              example:
                id: task_xxxxxxxxxxxxxxx
                status: pending
                created_at: 1743724770
components:
  schemas:
    UnifiedTask:
      type: object
      properties:
        id:
          type: string
        status:
          type: string
          description: pending / running / completed / failed …
        created_at:
          type: integer
        completed_at:
          type: integer
        outputs:
          type: array
          items:
            type: string
          description: Result URLs when completed.
        error:
          type: string
        message:
          type: string

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.