Google DeepMind
Build with Gemini
Try Gemini
Published 5 November 2026

Gemini Omni 1.2 Flash

Learn more
View PDF version

Model Cards are intended to provide essential information on Gemini models, including known limitations, mitigation approaches, and safety performance. Model cards may be updated from time to time; for example, to include updated evaluations as the model is improved or revised. See the Google DeepMind site for a comprehensive list of model cards.

Published: November, 2026

Model Information

Description

Gemini Omni 1.2 Flash is our next step towards models that can create and edit anything from any input—starting with video. It combines Gemini’s intelligence with our generative media models, representing a leap forward in world understanding, multimodality, and editing. Gemini Omni 1.2 Flash enables high-quality video creation and a more natural way to edit videos through conversation.

Model dependencies

Gemini Omni 1.2 Flash is based on Gemini Omni Flash.

Inputs

Text strings (e.g., a question, a prompt), images, audio, and video files.

Outputs

High-quality, high-resolution video with audio.

Architecture

Gemini Omni 1.2 Flash is based on Gemini Omni Flash. For more information about the model architecture for Gemini Omni 1.2 Flash, see the Gemini Omni Flash model card.

Model Data

Training Dataset

Gemini Omni 1.2 Flash is based on Gemini Omni Flash. For more information about the training dataset for Gemini Omni 1.2 Flash, see the Gemini Omni Flash model card.

Training Data Processing

Gemini Omni 1.2 Flash is based on Gemini Omni Flash. For more information about the training data processing for Gemini Omni 1.2 Flash, see the Gemini Omni Flash model card.

Implementation and Sustainability

Hardware

Gemini Omni 1.2 Flash is based on Gemini Omni Flash. For more information about the hardware for Gemini Omni 1.2 Flash and our continued commitment to operate sustainably, see the Gemini Omni Flash model card.

Software

Gemini Omni 1.2 Flash is based on Gemini Omni Flash. For more information about the software for Gemini Omni 1.2 Flash, see the Gemini Omni Flash model card.

Distribution

Gemini Omni 1.2 Flash is distributed in the following channels; respective documentation shared in line:

Our models are available to downstream providers via an application program interface (API) and subject to relevant terms of use. There is no required hardware or software to use the model. For AI Studio and Gemini API, see the Gemini API Additional Terms of Service. For more information, see Gemini Model API instructions and Gemini API quickstart.

Intended Usage and Limitations

Benefit and Intended Usage

Gemini Omni 1.2 Flash can be used to generate high-quality, high-resolution videos from any input in a wide range of visual styles. The model is able to faithfully follow simple and complex instructions, simulate real-world physics, and edit videos through conversation.

Known Limitations

For more information about the known limitations for Gemini Omni 1.2, see the Gemini Omni Flash model card

Acceptable Usage

For more information about the acceptable usage for Gemini Omni 1.2, see the Gemini Omni Flash model card

Ethics and Content Safety

Evaluation Approach

For more information about the evaluation approach for Gemini Omni 1.2, see the Gemini Omni Flash model card

Safety Policies

For more information about the safety policies for Gemini Omni 1.2, see the Gemini Omni Flash model card

Frontier Safety Assessment

Gemini Omni 1.2 Flash is part of the Gemini 3 series of models. To assess Gemini Omni 1.2 Flash for frontier safety, we rely on our evaluations of Gemini 3.1 Pro and Gemini 3.7 Flash as outlined in our Frontier Safety Framework. We found that Gemini 3.1 Pro and Gemini 3.7 Flash did not reach any Tracked or Critical Capability Levels (T/CCLs). Our assessments have shown that Gemini Omni 1.2 Flash does not have meaningful new capabilities or material increases in performance compared to Gemini 3.1 Pro or Gemini 3.7 Flash, therefore based on these results, we are confident that Gemini Omni 1.2 Flash is also unlikely to reach any T/CCLs.

For more information on our Frontier Safety Assessment, read the Gemini 3.1 Pro Model Card and Gemini 3.7 Flash Model Card.

Risks and Mitigations

Similar to our safety approach to our other Gemini models, we built safety at the core of Gemini Omni 1.2 Flash:

  • Pre-training mitigations: We used diverse synthetic captioning to improve the model’s ability to accurately represent a wide variety of concepts.
  • Post-training mitigations: To maintain high information integrity and prevent unwanted outputs, we deployed advanced production filters.

Additionally, SynthID watermarks enable users to verify AI-generated content.

As part of editing videos, Gemini Omni 1.2 Flash is capable of changing people's speech. For now, we are restricting this capability and working to better understand how to safely and responsibly bring it to our users.model card

Latest model cards