Skip to content
AI Model Radar

Gemini Omni 1.1 Flash

gemini-omni-1.1-flash
Google · chat · api
GA Alert me on changes
Context
131.1K
Max output
65.5K
Input $/1M
$1.50
Output $/1M
$17.50
Modalities
text
Released
02 Sept 2026
Download image Share on X Share on LinkedIn
AI summary
● machine-written

Google releases Gemini Omni 1.1 Flash for video generation and editing

Gemini Omni 1.1 Flash is Google's multimodal model that generates and edits short videos (3–10 seconds) with native audio, accepting text, images, and video input. It supports conversational editing through the Interactions API and offers multiple output resolutions with SynthID watermarking. Available on the paid Gemini API tier with input at $1.50/1M tokens and video output at $17.50/1M tokens.

What's new
  • Generates video with native audio at 24 FPS in 360p, 720p, or upscaled 1080p/4K
  • Conversational editing through Interactions API for iterative refinement
  • Supports image-to-video animation and frame interpolation workflows
  • SynthID watermarking included for provenance verification
  • Context window of 131K tokens with 66K max output
Best for
Short marketing and social media video generation (3–10 seconds)Conversational video editing and refinement workflowsImage animation and product visualizationVideo transitions, extensions, and frame interpolation
Sources

Source: https://ai.google.dev/gemini-api/docs/models/gemini-omni-1.1-flash