> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Vidu Q4 Preview (Reference to Video) > Vidu Q4 Preview **reference-image to video**. Supply 1-15 reference images via `image_urls` and refer to them in the prompt as `@1`, `@2`, … in array order; the model keeps those subjects consistent across the video. Optionally add up to 3 reference audio clips via `ref_audios` to guide voices and dialogue. Output includes a native audio track and goes up to 4K. This model only accepts `image_urls`. For first-frame image-to-video use [`viduq4_preview`](/api-reference/video-generations/viduq4-preview) — passing `image_url` or `image_end_url` here returns an error. **Pricing** — per second of generated video, in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | |---|---|---| | 540p | 2.925 | $0.0585 | | 720p | 6.175 | $0.1235 | | 1080p | 7.8 | $0.156 | | 2K | 12.35 | $0.247 | | 4K | 25.35 | $0.507 | The price is the same for both Vidu Q4 Preview models and does not depend on the number of reference images or audio clips, or on `generate_audio`. Example: an 8s 720p video costs 49.4 tokens (= $0.988). Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. ## OpenAPI ````yaml api-reference/video-generations/openapi-viduq4-preview-reference.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Vidu Q4 Preview Reference description: Reference-image to video with Vidu Q4 Preview. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: Vidu Q4 Preview (Reference to Video) description: >- Vidu Q4 Preview **reference-image to video**. Supply 1-15 reference images via `image_urls` and refer to them in the prompt as `@1`, `@2`, … in array order; the model keeps those subjects consistent across the video. Optionally add up to 3 reference audio clips via `ref_audios` to guide voices and dialogue. Output includes a native audio track and goes up to 4K. This model only accepts `image_urls`. For first-frame image-to-video use [`viduq4_preview`](/api-reference/video-generations/viduq4-preview) — passing `image_url` or `image_end_url` here returns an error. **Pricing** — per second of generated video, in tokens (USD at $0.02/token): | resolution | tokens/s | USD/s | |---|---|---| | 540p | 2.925 | $0.0585 | | 720p | 6.175 | $0.1235 | | 1080p | 7.8 | $0.156 | | 2K | 12.35 | $0.247 | | 4K | 25.35 | $0.507 | The price is the same for both Vidu Q4 Preview models and does not depend on the number of reference images or audio clips, or on `generate_audio`. Example: an 8s 720p video costs 49.4 tokens (= $0.988). Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - viduq4_preview_reference description: Model name. Must be `viduq4_preview_reference`. prompt: type: string description: >- Text prompt describing the video (required). Refer to reference images as `@1`, `@2`, … in the order of `image_urls`. image_urls: type: array items: type: string format: uri minItems: 1 maxItems: 15 description: >- Reference image URLs (required, 1-15 images). png / jpeg / jpg / webp, max 50MB each. ref_audios: type: array items: type: string format: uri maxItems: 3 description: >- Optional reference audio URLs (up to 3), e.g. a voice sample or a line of dialogue. Each clip must be an mp3 of 3-12 seconds. duration: type: integer minimum: 3 maximum: 16 default: 5 description: Video duration in seconds (3-16). Defaults to 5. resolution: type: string enum: - 540p - 720p - 1080p - 2K - 4K default: 720p description: >- Output resolution. Case-insensitive (`2k` and `2K` are both accepted). ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' default: '16:9' description: >- Aspect ratio of the output video. `aspect_ratio` is accepted as a compatible alias. generate_audio: type: boolean default: true description: >- Whether the output contains a native audio track (dialogue and sound effects). Defaults to `true`. Turning it off does not change the price. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - prompt - image_urls example: model: viduq4_preview_reference prompt: >- The barista from @1 stands in front of the cafe in @2 and greets the camera image_urls: - https://your-cdn.com/barista.jpg - https://your-cdn.com/cafe.jpg ref_audios: - https://your-cdn.com/greeting.mp3 duration: 8 resolution: 720p ratio: '9:16' responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string cost: type: number description: >- Tokens deducted for this request. This is the amount actually charged, so it already reflects any discount active on your account and can be lower than the listed price. Tokens are deducted when the task is accepted, and refunded automatically if the generation ends in failure. example: 30.88 required: - img_uuid - cost required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 cost: 30.88 '2': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.