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

# Gemini Omni Flash API

> Gemini Omni Flash API on Venice: text to video, image to video and reference to video, 10s clips, from $0.1378 per second. Pricing, specs and code examples.

> [accordion] Plain-text specification
>
> ## Gemini Omni Flash API
>
> Gemini Omni Flash is a text to video, image to video and reference to video model by Google, available on the Venice API as `gemini-omni-flash-text-to-video`. Requests are anonymized, so the provider never sees your identity.
>
> ### Gemini Omni Flash API pricing
>
> | Model ID | Variant | Privacy | Price |
> | - | - | - | - |
> | `gemini-omni-flash-text-to-video` | Text to video | Anonymized | from \$0.1378 / sec |
> | `gemini-omni-flash-image-to-video` | Image to video | Anonymized | from \$0.1427 / sec |
> | `gemini-omni-flash-reference-to-video` | Reference to video | Anonymized | from \$0.1427 / sec |
>
> ### Gemini Omni Flash specifications
>
> | Spec | Value |
> | - | - |
> | Provider | Google |
> | Released | Jun 30, 2026 |
> | Privacy | Anonymized |
> | Status | Stable |
> | Modes | text to video, image to video and reference to video |
> | Durations | 4s, 6s, 8s, 10s |
> | Aspect ratios | 16:9, 9:16 |
> | Audio | None |
>
> ### How to use the Gemini Omni Flash API
>
> Send requests to `POST https://api.venice.ai/api/v1/video/queue` with `"model": "gemini-omni-flash-text-to-video"` and your API key.
>
> ```bash theme={"system"}
> # 1. Queue the job (returns a queue_id)
> curl https://api.venice.ai/api/v1/video/queue \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{
>     "model": "gemini-omni-flash-text-to-video",
>     "prompt": "Slow aerial drone shot over a misty mountain valley at golden hour",
>     "duration": "4s",
>     "aspect_ratio": "16:9"
>   }'
>
> # 2. Poll until the MP4 is ready
> curl https://api.venice.ai/api/v1/video/retrieve \
>   -H "Authorization: Bearer $VENICE_API_KEY" \
>   -H "Content-Type: application/json" \
>   -d '{ "model": "gemini-omni-flash-text-to-video", "queue_id": "<queue_id>" }' --output video.mp4
> ```
>
> ### Related models
>
> * [Gemini Omni Flash 1.1 API](https://docs.venice.ai/models/gemini-omni-flash-1-1.md): from \$0.0389 / sec
> * [Seedance 2.0 Mini API](https://docs.venice.ai/models/seedance-2-0-mini.md): from \$0.044 / sec
> * [HappyHorse 1.1 API](https://docs.venice.ai/models/happyhorse-1-1.md): from \$0.154 / sec
> * [Kling V3 Turbo Pro API](https://docs.venice.ai/models/kling-v3-turbo-pro.md): from \$0.154 / sec
> * [Kling V3 Turbo Standard API](https://docs.venice.ai/models/kling-v3-turbo-standard.md): from \$0.1233 / sec


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.