> ## 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. # Muse Video > Muse Video, Meta's video model. Generates one **10-second 720p** clip from a prompt alone, or guided by up to 9 reference images in `image_urls`. Reference images steer the subject, style and scene; they are not used as an exact first frame, so this is not image-to-video. **Audio** — every video comes with native sound. It is always on and cannot be turned off. **Pricing** — 1.56 tokens ($0.0312) per video, flat. Reference images are not charged. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. The delivered clip is about 10 seconds; read the exact length from the file. **Not accepted by this model** (rejected before any tokens are charged): `duration` other than 10, `resolution` other than 720p, turning sound off (`generate_audio: false`), `negative_prompt`, `seed`, first / last frames (`image_url` / `image_end_url`), and reference videos or audio. ## OpenAPI ````yaml api-reference/video-generations/openapi-muse-video.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Muse Video description: >- Video generation with Muse Video. Same endpoint as the other video models; the model is selected by model. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: Muse Video description: >- Muse Video, Meta's video model. Generates one **10-second 720p** clip from a prompt alone, or guided by up to 9 reference images in `image_urls`. Reference images steer the subject, style and scene; they are not used as an exact first frame, so this is not image-to-video. **Audio** — every video comes with native sound. It is always on and cannot be turned off. **Pricing** — 1.56 tokens ($0.0312) per video, flat. Reference images are not charged. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. The delivered clip is about 10 seconds; read the exact length from the file. **Not accepted by this model** (rejected before any tokens are charged): `duration` other than 10, `resolution` other than 720p, turning sound off (`generate_audio: false`), `negative_prompt`, `seed`, first / last frames (`image_url` / `image_end_url`), and reference videos or audio. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object description: |- Muse Video text-to-video and reference-image video. **Pricing** — 1.56 tokens ($0.0312) per 10-second 720p video. properties: model: type: string enum: - muse-video description: Model name. Must be `muse-video` on this page. prompt: type: string maxLength: 4000 description: >- Text prompt describing the scene, motion, camera and sound. Required, also when reference images are given. Chinese and English are supported. image_urls: type: array maxItems: 9 items: type: string format: uri description: >- Optional reference image URLs, up to 9, in the order you refer to them in the prompt. JPG, PNG or WebP, publicly reachable, up to 30MB each. Large images are downscaled automatically. ratio: type: string enum: - auto - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' - '3:2' - '2:3' default: auto description: >- Aspect ratio. `auto` means 16:9 for text-to-video, and follows the reference images when `image_urls` is given. `aspect_ratio` is accepted as an alias. duration: type: integer enum: - 10 default: 10 description: Fixed at 10 seconds. Optional. resolution: type: string enum: - 720p default: 720p description: Fixed at 720p. Optional. 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 example: model: muse-video prompt: >- The fox from the reference image slowly raises its head as wind moves its fur, gentle camera push-in, soft forest ambience image_urls: - https://your-cdn.com/fox.png ratio: '16:9' 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: 5.82 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: 5.82 '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 examples: '1': summary: Unauthorized value: code: 401 msg: Unauthorized headers: {} deprecated: false security: [] ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.