> ## 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. # Gemini Omni 1.2 Flash > Gemini Omni 1.2 Flash, Google's multimodal video model. Text-to-video, image-to-video from a first frame, first & last frame interpolation, and generation guided by up to **10 reference images**. Clips run **3-15 seconds** at 24fps. **Audio** — every generated video comes with a native audio track (dialogue, music or sound effects, described in the prompt). It is always on: the model has no switch for it, so turning `sound` / `generate_audio` off is rejected. **Pricing** — per second of generated video, in tokens (USD at $0.02/token). Text-to-video, image-to-video and reference images cost the same; frames and reference images are not charged: | resolution | tokens/s | USD/s | |---|---|---| | 360p | 1.3 | $0.026 | | 720p | 3.9 | $0.078 | | 1080p | 5.876 | $0.11752 | | 4k | 11.752 | $0.23504 | Example: a 10-second video at 720p costs 39 tokens. 1080p and 4k are upscaled by the model. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. **Not accepted by this model** (rejected before any tokens are charged): turning audio off, `negative_prompt` (describe what to avoid in `prompt`), `seed`, middle `keyframes`, combining first / last frames with `image_urls`, and video input (editing or extending a video is not available yet). ## OpenAPI ````yaml api-reference/video-generations/openapi-gemini-omni-1-2-flash.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Gemini Omni 1.2 Flash description: >- Video generation with Gemini Omni 1.2 Flash. 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: Gemini Omni 1.2 Flash description: >- Gemini Omni 1.2 Flash, Google's multimodal video model. Text-to-video, image-to-video from a first frame, first & last frame interpolation, and generation guided by up to **10 reference images**. Clips run **3-15 seconds** at 24fps. **Audio** — every generated video comes with a native audio track (dialogue, music or sound effects, described in the prompt). It is always on: the model has no switch for it, so turning `sound` / `generate_audio` off is rejected. **Pricing** — per second of generated video, in tokens (USD at $0.02/token). Text-to-video, image-to-video and reference images cost the same; frames and reference images are not charged: | resolution | tokens/s | USD/s | |---|---|---| | 360p | 1.3 | $0.026 | | 720p | 3.9 | $0.078 | | 1080p | 5.876 | $0.11752 | | 4k | 11.752 | $0.23504 | Example: a 10-second video at 720p costs 39 tokens. 1080p and 4k are upscaled by the model. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the generated video. **Not accepted by this model** (rejected before any tokens are charged): turning audio off, `negative_prompt` (describe what to avoid in `prompt`), `seed`, middle `keyframes`, combining first / last frames with `image_urls`, and video input (editing or extending a video is not available yet). parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object description: >- Gemini Omni 1.2 Flash text-to-video, image-to-video (first frame, optional last frame) and reference-image video. **Pricing** — per second of generated video: - 360p — 1.3 tokens ($0.026) - 720p — 3.9 tokens ($0.078) - 1080p — 5.876 tokens ($0.11752) - 4k — 11.752 tokens ($0.23504) properties: model: type: string enum: - gemini-omni-1-2-flash description: Model name. Must be `gemini-omni-1-2-flash` on this page. prompt: type: string maxLength: 3000 description: >- Text prompt describing the scene, motion, camera and sound. Required (also when images are provided), up to 3000 characters. With `image_urls`, describe how the references should be used. image_url: type: string format: uri description: >- Optional first-frame image URL. If provided, the video starts from this image. Cannot be combined with `image_urls`. image_end_url: type: string format: uri description: >- Optional last-frame image URL; the model interpolates from the first frame to this one. Requires `image_url`. With a last frame, `duration` can be at most 10. image_urls: type: array maxItems: 10 items: type: string format: uri description: >- Optional reference image URLs (1-10), e.g. characters, products or style. They guide the video but are not used as exact frames. Order is kept. Cannot be combined with `image_url` / `image_end_url`. duration: type: integer minimum: 3 maximum: 15 default: 10 description: >- Video duration in seconds, any integer from 3 to 15. At most 10 when `image_end_url` is provided. resolution: type: string enum: - 360p - 720p - 1080p - 4k default: 720p description: >- Output resolution. 1080p and 4k are upscaled; `2160p` is accepted as 4k. `quality` is accepted as a compatible alias. ratio: type: string enum: - '16:9' - '9:16' default: '16:9' description: >- Aspect ratio. `aspect_ratio` is accepted as a compatible alias. 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: gemini-omni-1-2-flash prompt: >- The sun rises over a quiet harbor, fishing boats drift out to sea, gulls call and waves lap against the pier image_url: https://your-cdn.com/harbor-dawn.jpg image_end_url: https://your-cdn.com/harbor-morning.jpg duration: 8 resolution: 1080p 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.