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

# Create a video generation job

> Generate a video from a prompt and optional input reference.



## OpenAPI

````yaml /api-reference/openapi.json post /v1/videos
openapi: 3.1.0
info:
  title: SynapsAI Inference API
  version: 1.0.0
servers:
  - url: https://api.synapsai.cloud
    description: Production server
security: []
paths:
  /v1/videos:
    post:
      summary: Create a video generation job
      description: Generate a video from a prompt and optional input reference.
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VideoCreateRequest'
      responses:
        '200':
          description: Video generation job created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Video'
components:
  schemas:
    VideoCreateRequest:
      type: object
      description: Video creation request
      properties:
        model:
          type: string
          description: Model ID to use
        prompt:
          type: string
          description: Text prompt describing the video
        input_reference:
          type:
            - string
            - 'null'
          description: >-
            Optional reference video or asset as URL, data URI, base64 string,
            or file path
        seconds:
          type: integer
          default: 4
        size:
          oneOf:
            - type: string
            - type: array
              items:
                type: integer
          default: 1280x720
        fps:
          type: integer
          default: 16
        num_inference_steps:
          type: integer
          default: 25
        guidance_scale:
          type: number
          default: 5
      required:
        - model
        - prompt
    Video:
      type: object
      description: Structured information describing a generated video job
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - video
          default: video
        created_at:
          type: integer
        completed_at:
          type:
            - integer
            - 'null'
        error:
          $ref: '#/components/schemas/VideoCreateError'
        expires_at:
          type:
            - integer
            - 'null'
        model:
          type: string
        prompt:
          type:
            - string
            - 'null'
        seconds:
          type: integer
        size:
          type: string
        status:
          $ref: '#/components/schemas/VideoStatus'
      required:
        - id
        - object
        - created_at
        - model
        - seconds
        - size
        - status
    VideoCreateError:
      type: object
      description: Video generation error details
      properties:
        code:
          type: string
          nullable: true
        message:
          type: string
          nullable: true
    VideoStatus:
      type: string
      description: Video generation lifecycle states
      enum:
        - queued
        - in_progress
        - completed
        - failed

````