← All models

Gemini Omni 1.1 Flash

Published Publisher Googlegemini-omni-1.1-flash

Gemini Omni 1.1 Flash

Release date: August 27, 2026. Google introduced it as a production-ready multimodal model for controllable video generation and editing through the Gemini API. (blog.google)

Capabilities and uses

  • The model family accepts text, images, audio and video and produces high-resolution video with audio. Availability of particular input types can vary by platform and version. (deepmind.google)
  • Scene extension uses up to 10 seconds of prior video context and extends footage in 10-second increments, up to 40 seconds in total. First- and last-frame controls enable transitions between specified keyframes. (blog.google)
  • Google announced 360p drafts for faster iteration and 4K upscaling for final output. These features are intended for generative-video workflows, creative tools, storyboarding and media-editing software. (blog.google)

Limitations and availability

The model card identifies persistent challenges with consistency across edits, complex motion and accurate rendering of text. Google also restricts the capability to change people's speech during video editing. (deepmind.google)

The separately identified Google Cloud preview, gemini-omni-1.1-flash-preview, is deprecated. Its documentation lists different platform-specific capabilities: audio input and video upscaling are not supported, while text- and image-to-video generation, video editing and extension are supported. Those preview-specific limits should not be assumed to apply to every deployment of the model. (docs.cloud.google.com)

Google states that, effective December 3, 2026, Gemini API requests to gemini-omni-1.1-flash will automatically route to Gemini Omni 1.2 Flash and be billed at the latter model's rates. (aistudio.google.com)

Pricing

Gemini API Standard paid tier, USD; checked November 16, 2026:

  • Input: USD $1.50 per 1 million text, image or video tokens. An audio-input rate was not verified on the current pricing page.
  • Output: USD $9.00 per 1 million text tokens and USD $17.50 per 1 million video tokens; output pricing includes thinking tokens.
  • Free tier: Not available for these input and output categories.
  • Video billing is based on output tokens. Google specifies 5,792 tokens per second of 720p video, equivalent to approximately USD $0.10 per second at the listed 1.1 Standard rate. This effective per-second figure is specific to 720p and does not replace input charges. (aistudio.google.com)

These are Gemini API prices, not a quotation for the separate Google Cloud preview. The December 3 routing change and 1.2 rates described above are distinct from the 1.1 rates listed here. (aistudio.google.com)

Official sources