Google logo
google/gemini-omni-flash/v1.1/text-to-video

Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint generates video with synchronized native audio from a text prompt, grounded in Gemini's real-world knowledge and physics understanding, with cinematic camera control expressed in natural language.
Inference
Commercial use
Partner

Input

Result

Idle

What would you like to do next?

Billing is calculated per second of output video, by resolution. For 360p, your request will cost $0.03 per second; for 720p, $0.10 per second; for 1080p, $0.15 per second; and for 4K, $0.30 per second. A 10-second 1080p clip costs $1.50, while the same clip at 360p costs $0.30.

Logs