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

# Kling 3.0 API Documentation

> Kling 3.0 API delivers hyper-realistic textures, complex motion modeling, and superior prompt adherence. It utilizes advanced physical simulation to ensure fluid, lifelike movements across intricate cinematic sequences. Integrate the Kling 3.0 API now.

Check out Kling 3.0 API pricing [here](https://api.pollo.ai/pricing?modelName=kling-v3\&modelType=video), cheaper than Fal AI.


## OpenAPI

````yaml POST /v1/generation/kling-ai/kling-v3/video
openapi: 3.0.3
info:
  title: Pollo | AI Video Collection
  description: >-
    ✨RESTful API Document. Model discovery: GET /api/v1/model-specs (public,
    keyless).
  version: 1.0.0
servers:
  - url: https://pollo.ai/api/platform
security: []
externalDocs:
  url: https://pollo.ai/api/platform/api/openapi.json
paths:
  /v1/generation/kling-ai/kling-v3/video:
    post:
      tags:
        - Video
      summary: kling-v3
      operationId: v1-kling-ai/kling-v3/video
      parameters: []
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              required:
                - input
              properties:
                input:
                  oneOf:
                    - type: object
                      properties:
                        prompt:
                          type: string
                          maxLength: 2500
                          minLength: 1
                          description: Text prompt describing the content to generate.
                        negativePrompt:
                          type: string
                          maxLength: 2500
                          description: >-
                            Text describing elements to avoid in the generated
                            output.
                        image:
                          type: string
                          description: >-
                            First-frame / reference image URL (HTTP(S); base64
                            not allowed). Supported formats: JPG/JPEG, PNG.
                            Aspect ratio must be within 1:4 to 4:1.
                        imageTail:
                          type: string
                          description: >-
                            Tail (end-frame) image URL (HTTP(S); base64 not
                            allowed). Supported formats: JPG/JPEG, PNG. Aspect
                            ratio must be within 1:4 to 4:1.
                        duration:
                          type: integer
                          minimum: 3
                          maximum: 15
                          default: 5
                          description: The duration of the generated video, in seconds.
                        mode:
                          type: string
                          enum:
                            - std
                            - pro
                            - 4K
                          default: std
                          description: >-
                            Generation mode of the model (e.g. a faster or
                            higher-quality tier).
                        multiShot:
                          type: boolean
                          default: false
                          description: >-
                            Generate a multi-shot video (multiple scene cuts
                            with automatic transitions) instead of a single
                            continuous shot.
                        generateAudio:
                          type: boolean
                          description: >-
                            Generate natural-sounding, fitting audio for the
                            output video.
                      required:
                        - image
                      title: Image To Video
                    - type: object
                      properties:
                        prompt:
                          type: string
                          maxLength: 2500
                          minLength: 1
                          description: Text prompt describing the content to generate.
                        negativePrompt:
                          type: string
                          maxLength: 2500
                          description: >-
                            Text describing elements to avoid in the generated
                            output.
                        aspectRatio:
                          type: string
                          enum:
                            - '16:9'
                            - '9:16'
                            - '1:1'
                          default: '16:9'
                          description: Output aspect ratio, as width:height (e.g. 16:9).
                        duration:
                          type: integer
                          minimum: 3
                          maximum: 15
                          default: 5
                          description: The duration of the generated video, in seconds.
                        mode:
                          type: string
                          enum:
                            - std
                            - pro
                            - 4K
                          default: std
                          description: >-
                            Generation mode of the model (e.g. a faster or
                            higher-quality tier).
                        multiShot:
                          type: boolean
                          default: false
                          description: >-
                            Generate a multi-shot video (multiple scene cuts
                            with automatic transitions) instead of a single
                            continuous shot.
                        generateAudio:
                          type: boolean
                          description: >-
                            Generate natural-sounding, fitting audio for the
                            output video.
                      required:
                        - prompt
                      title: Text To Video
                webhookUrl:
                  type: string
                  format: uri
                  description: >-
                    Webhook URL (HTTP(S)) that receives status callbacks when
                    the generation succeeds or fails.
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                type: object
                properties:
                  taskId:
                    type: string
                  status:
                    type: string
                    enum:
                      - waiting
                      - succeed
                      - failed
                      - processing
                required:
                  - taskId
                  - status
                additionalProperties: false
        default:
          $ref: '#/components/responses/error'
      security:
        - ApiKeyAuth: []
components:
  responses:
    error:
      description: Error response
      content:
        application/json:
          schema:
            type: object
            properties:
              message:
                type: string
              code:
                type: string
              issues:
                type: array
                items:
                  type: object
                  properties:
                    message:
                      type: string
                  required:
                    - message
                  additionalProperties: false
            required:
              - message
              - code
            additionalProperties: false
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key
      description: API key to authorize requests

````