Gemini Omni Flash is Google's fast video model in the Gemini API. Google announced Gemini Omni 1.2 Flash on November 5, 2026. It is generally available through the Gemini API and Gemini for business, with Google Cloud also listed as a production path.
Status
Google says Gemini Omni 1.2 Flash is generally available. The earlier gemini-omni-flash-preview is shut down; teams using an earlier model ID should check the current Gemini API model documentation before migrating.
Key features
- Video generation: create video from text and image prompts, with native audio.
- Conversational editing: refine and edit generated videos with natural-language instructions through the Interactions API.
- Extension and interpolation: extend video, upscale resolution and use advanced keyframe interpolation.
- Output range: generate and edit clips natively up to 15 seconds, up from 10 seconds in Omni 1.1.
- Inputs: text, images and video up to 10 seconds for editing and extension, with a 1,048,576-token context window.
Pricing
Google's November 5 announcement says Omni 1.2 Flash costs $0.07 per second for 720p video, a 30% reduction from Omni 1.1. Google also recommends drafting at 360p or 720p, refining with follow-up edits, and upscaling selected results to 1080p or 4K. Check the pricing documentation before budgeting because API terms can change.
Use cases
- Short product, social and concept videos from a text prompt.
- Iterating on a clip by chatting with the model instead of regenerating it.
- Extending or upscaling an existing 10-second clip.
Getting started
- Use a Gemini API key and select Gemini Omni 1.2 Flash from the current model documentation.
- Start with a short prompt at 720p to keep cost down, then upscale a version you like.
- Use the Interactions API to request edits in plain language.
FAQ
Is Gemini Omni 1.2 Flash generally available?
Yes. Google announced general availability for the Gemini API and Gemini for business on November 5, 2026.
How long can a generated clip be?
Up to 15 seconds. Google says this is up from 10 seconds in Omni 1.1.
How much does it cost?
Google lists $0.07 per second for 720p video in its November 5, 2026 announcement, 30% lower than Omni 1.1. Confirm current pricing before deploying.
Is it a text model?
No. Its output is video, so for text work choose a model such as Gemini 3.5 Flash.
Alternatives
- Veo 3: Google's earlier video generation model.
- Gemini 3.5 Flash-Lite: a low-cost Gemini model for text output.
- Seedance 2.5: another video generation model.
Conclusion
Gemini Omni 1.2 Flash brings 15-second generation, conversational editing and native audio to Google's video workflow at a lower announced 720p price. Read Google's model documentation for current model IDs and limits, and see more models in the models category.
Sources
- Websitehttps://ai.google.dev/gemini-api/docs/models
- Social Mediahttps://x.com/GoogleAI
Comments
No comments yet. Be the first to comment!