Gemini Omni 1.1 Flash: Google's GA Video Model, Pricing and the December Switch to 1.2

What Gemini Omni 1.1 Flash is

Gemini Omni 1.1 Flash is Google's fast video generation and editing model, released on the Gemini API on 27 August 2026 as the generally available version of Gemini Omni Flash, under the identifier gemini-omni-1.1-flash. It followed the public preview, gemini-omni-flash-preview, which Google released on 30 June 2026 and shut down on 22 October 2026. Gemini Omni 1.2 Flash has since succeeded both. Google describes the model as conversational: a video is generated from text or images and then refined through follow-up requests in natural language using the Interactions API. On LMArena's text-to-video leaderboard Gemini Omni 1.1 Flash has 1513 Elo (rank 2).

What the GA release added

Google's changelog entry for the release lists three new capabilities. Video extension generates a continuation at the end of an existing clip, either with the extend task or directly from a prompt. Interpolation takes a first and a last frame, up to two images through the image_to_video task, and generates the transition between them. Resolution control adds a resolution parameter to video_config with 360p, 720p (the default), 1080p and 4K outputs; Google states that 1080p and 4K are produced by upscaling.

Inputs, outputs and limits

Google's model page lists text, image and video as input, with video of up to 10 seconds accepted for editing and extension, and video as output. Each clip runs from 3 to 10 seconds at 24 frames per second, in any of the four resolutions above. The input token limit is 131,072 tokens and the output token limit is 65,536 tokens. Gemini Omni 1.2 Flash, released on 5 November 2026, raised the clip length to 15 seconds; Google's announcement of 1.2 gives 10 seconds as the Omni 1.1 limit.

Pricing

The model is billed on the Gemini API's paid tier only; Google lists no free tier for it. Input costs $1.50 per million tokens for text, image or video. Output costs $9.00 per million tokens for text and $17.50 per million tokens for video. Google bills video at 5,792 output tokens per second of 720p video, which it states works out to about $0.10 per second under Standard pricing, so a 10-second 720p clip comes to roughly $1; Google’s pricing page gives the per-second figure for 720p only. Google gives the price of Omni 1.2 Flash as 30% lower, at about $0.07 per second of 720p video.

The switch to Gemini Omni 1.2 Flash

Google's deprecations page gives 3 December 2026 as the shutdown date for gemini-omni-1.1-flash and names gemini-omni-1.2-flash as the replacement. From that date, requests sent to gemini-omni-1.1-flash are routed automatically to gemini-omni-1.2-flash and billed at Omni 1.2 Flash rates, so code that keeps the old identifier carries on working but at the newer model's output and price. Until then both identifiers are listed as stable on Google's model page. The preview identifier, gemini-omni-flash-preview, was shut down on 22 October 2026, also with gemini-omni-1.2-flash as the named replacement.

Official Resources