Tuesday, 10 November 2026 | Updating Daily AI insight, written for builders

Gemini Omni 1.2 Flash

Gemini Omni 1.2 Flash — Specifications

Compiled by Mustafa Ihsan from the vendor’s published documentation · Last updated

Developer Google
Type Video generation
Modality Text, Image, Video, Audio -> Video with audio, Text
Parameters Undisclosed
Context window 131K
Max output 65K
License Proprietary
Open weights No
Released 2026-11
Price from $0.023 per second
API providers Gemini API (paid tier), Google Cloud (Gemini Enterprise Agent Platform); Flow, Google Vids, Gemini app (consumer apps)

Official page →

What is Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash (gemini-omni-1.2-flash) is Google’s video generation and editing model, generally available since 5 November 2026 on the paid tier of the Gemini API and on Google Cloud. Google says it makes clips of 3 to 15 seconds with native audio, up from 10 seconds in Omni 1.1, and lets you edit a clip over several conversational turns. It takes text, images, video and audio as input, returns video with sound and text, and can extend a clip to 30 seconds in total.

Google bills it per token, which it puts at about $0.07 per second of 720p video. On the Gemini API price list, input costs $1.50 per million tokens, text output $9.00 and video output $12.00, a 30% cut from Omni 1.1’s video rate. At 5,792 tokens per second of 720p video, a 10-second clip costs about $0.70 and a 15-second clip about $1.04. Google gives $0.023 per second at 360p, and $0.104 at 1080p and $0.209 at 4K, both upsampled. Google lists no free tier and only a standard rate. From 3 December 2026, calls to gemini-omni-1.1-flash route to 1.2 at 1.2 prices.

Omni 1.2 Flash is the replacement Google names for the Veo 3.1 previews it shut down in the Gemini API on 22 October 2026. Consumers meet it in Flow, in Google Vids and, as it rolls out to Google AI Ultra subscribers, in the Gemini app. On 5 December 2026 Flow retires Omni Flash 1.1, Veo 3.1 Fast and Veo 3.1 Quality, leaving Omni Flash 1.2 and Veo 3.1 Lite. Compare per-second prices in our AI video cost index and AI video generation pricing guide.

Gemini Omni 1.2 Flash pricing

TierResolution Price / second
Gemini API / Google Cloud 360p $0.02
Gemini API / Google Cloud 720p $0.07
Gemini API / Google Cloud (upsampled) 1080p $0.10
Gemini API / Google Cloud (upsampled) 4K $0.21

What a clip costs

LengthGemini API / Google Cloud Gemini API / Google Cloud (upsampled)
10 seconds $0.23 $2.09
30 seconds $0.69 $6.27
60 seconds $1.38 $12.54

One successful generation. A usable shot commonly takes three to ten attempts, so multiply by your real retry rate before budgeting.

How Gemini Omni 1.2 Flash compares

ModelCheapest tiervs Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash $0.02 this model
MiniMax H3 (Hailuo 3.0) $0.03 1.1x the price
Wan 3.0 $0.05 2.2x the price
Wan 2.5 $0.05 2.2x the price
Veo 3.1 $0.05 2.2x the price
Kling 2.5 Turbo Pro $0.07 3x the price
Kling 4.0 $0.09 4.1x the price
Sora 2 $0.10 4.3x the price
Seedance 2.5 $0.10 4.5x the price
Sora 2 Pro $0.30 13x the price

Frequently asked questions

How much does Gemini Omni 1.2 Flash cost?

Gemini Omni 1.2 Flash costs between $0.02 and $0.21 per second of output, depending on tier. The cheapest is Gemini API / Google Cloud at $0.02 and the most expensive is Gemini API / Google Cloud (upsampled) at $0.21.

How much is a 30-second video with Gemini Omni 1.2 Flash?

A 30-second clip costs $0.69 on the cheapest tier and $6.27 on the most expensive, for one successful generation. A usable shot commonly takes three to ten attempts, so multiply by your real retry rate before budgeting.

Is Gemini Omni 1.2 Flash the cheapest option?

Yes. Gemini Omni 1.2 Flash is the cheapest in our database at $0.02 per second. The next cheapest is MiniMax H3 (Hailuo 3.0) at $0.03.

Full per-second table for every provider in the AI video generation pricing guide. Prices are the provider published list rates and change without notice.

Scroll to Top