> ## Documentation Index > Fetch the complete documentation index at: https://docs.ninjachat.ai/llms.txt > Use this file to discover all available pages before exploring further. # Video Generation > Start a video generation job. Supports 6 models. **$5.00/video:** `veo-3.1` (Google best quality). **$3.00/video:** `seedance-2` (default, uncensored, 5–15s), `kling-video` (motion quality, 5–10s), `google-veo-2` (fast cinematic, 5/6/8s), `veo-3.1-fast` (speed-optimized, 4/6/8s), `google-veo-3-fast` (budget Veo, 4/6/8s). Poll the status endpoint with the returned `request_id` to retrieve the result. ## OpenAPI ````yaml /openapi.json post /api/v1/video openapi: 3.1.0 info: title: NinjaChat API version: 1.0.0 description: >- Access 40+ AI models through a unified API — chat, image generation, video generation, and web search. One API key, one endpoint per type, just change the `model` parameter. servers: - url: https://www.ninjachat.ai security: - bearerAuth: [] paths: /api/v1/video: post: tags: - Endpoints summary: Video Generation description: >- Start a video generation job. Supports 6 models. **$5.00/video:** `veo-3.1` (Google best quality). **$3.00/video:** `seedance-2` (default, uncensored, 5–15s), `kling-video` (motion quality, 5–10s), `google-veo-2` (fast cinematic, 5/6/8s), `veo-3.1-fast` (speed-optimized, 4/6/8s), `google-veo-3-fast` (budget Veo, 4/6/8s). Poll the status endpoint with the returned `request_id` to retrieve the result. operationId: generateVideo requestBody: required: true content: application/json: schema: type: object required: - prompt properties: prompt: type: string minLength: 1 maxLength: 4000 description: >- Text description of the video to generate. Cannot be empty or whitespace-only. model: type: string enum: - seedance-2 - kling-video - google-veo-2 - veo-3.1 - veo-3.1-fast - google-veo-3-fast default: seedance-2 description: >- Video model to use. **$5.00/video:** `veo-3.1` (Google best quality). **$3.00/video:** `seedance-2` (longest clips, 5–15s), `kling-video` (motion quality, 5–10s), `google-veo-2` (fastest, ~40s), `veo-3.1-fast` (speed-optimized, 4/6/8s), `google-veo-3-fast` (budget Veo, 4/6/8s). duration: type: integer minimum: 4 maximum: 15 default: 8 description: >- Video length in seconds. Seedance 2: 5–15. Kling: 5–10. Veo 2: 5–8. Veo 3.1 / Veo 3.1 Fast: 4, 6, or 8. aspect_ratio: type: string enum: - '16:9' - '9:16' default: '16:9' description: >- Aspect ratio. `16:9` for landscape, `9:16` for portrait. Supported by Veo and Kling models. Ignored for Seedance 2. image_url: type: string format: uri description: >- Public URL of a reference image for image-to-video generation. Must be an HTTP or HTTPS URL. Omit for text-to-video. examples: seedance: summary: Seedance 2 (default) value: prompt: A golden retriever running in a sunny park model: seedance-2 duration: 10 kling: summary: Kling Video value: prompt: >- A samurai draws a katana in a field of golden grass, cherry blossoms swirl in the wind model: kling-video duration: 5 aspect_ratio: '16:9' veo2: summary: Google Veo 2 value: prompt: >- Underwater camera glides through a bioluminescent coral reef at night model: google-veo-2 duration: 5 aspect_ratio: '16:9' veo31: summary: Google Veo 3.1 value: prompt: >- A drone shot soaring over a misty mountain range at golden hour, cinematic lighting model: veo-3.1 duration: 8 aspect_ratio: '16:9' veo31fast: summary: Veo 3.1 Fast value: prompt: >- A person walking through a neon-lit Tokyo alley at night, rain reflections model: veo-3.1-fast duration: 6 aspect_ratio: '9:16' veo-3-fast: summary: Google Veo 3 Fast value: prompt: >- A cat watching birds from a sunny window ledge, gentle breeze model: google-veo-3-fast duration: 4 aspect_ratio: '16:9' responses: '200': description: Video generation job accepted. content: application/json: schema: type: object properties: request_id: type: string description: >- Unique job identifier. Use this to poll the status endpoint. model: type: string enum: - seedance-2 - kling-video - google-veo-2 - veo-3.1 - veo-3.1-fast - google-veo-3-fast description: The model used for this generation. message: type: string example: >- Poll GET /api/v1/video/status?request_id=... for completion. cost: type: object properties: this_request: type: string example: $3.00 per_video: type: string example: $3.00 balance: type: string example: $39.00 description: Remaining credit balance after this charge. metadata: type: object properties: latency_ms: type: integer description: Request latency in milliseconds. '400': description: >- Validation error (missing/invalid prompt, invalid duration, invalid model, or invalid image_url). content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication failed. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '402': description: Insufficient credits. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '502': description: Upstream video generation failed. You were not charged. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: ErrorResponse: type: object description: >- OpenAI-compatible error. The top-level `message`, `code`, and `request_id` mirror fields inside `error` for convenience. properties: error: type: object properties: message: type: string description: Human-readable error description. type: type: string description: >- Error category: invalid_request_error, authentication_error, rate_limit_error, insufficient_quota, or api_error. code: type: string description: Machine-readable error code. param: type: string nullable: true description: The request parameter that caused the error, if any. message: type: string description: Same as error.message. code: type: string description: Same as error.code. request_id: type: string description: Unique request ID, useful when contacting support. securitySchemes: bearerAuth: type: http scheme: bearer description: API key starting with nj_sk_ ````