Gemini Omni 1.2 Flash Release
Google released Gemini Omni 1.2 Flash on Nov 5, 2026, generally available in the Gemini API, Google Cloud, Flow and Google Vids. It makes and edits video clips of 3 to 15 seconds with sound, at about $0.07 a second for 720p, 30% below Omni 1.1, with no free tier.
Google released Gemini Omni 1.2 Flash on Nov 5, 2026, generally available that day in the Gemini API and on Google Cloud. It makes and edits video clips with sound of 3 to 15 seconds, up from 10 seconds on Omni 1.1, and Google cut the price by 30% to about $0.07 a second of 720p video, so a 15-second clip costs about $1.04. There is no free tier in the API. In Google's own apps it is in Flow, in Google Vids at no extra cost, and rolling out in the Gemini app to Google AI Ultra subscribers only.
What changed from Omni 1.1
From Google's announcement and the Gemini API changelog of Nov 5, 2026:
- Longer clips, set by the second. Any length from 3 to 15 seconds, drafted at 360p or 720p and upscaled to 1080p or 4K, at 24 frames a second.
- Editing in conversation on the whole clip. Swap a product or background, change the lighting, weather or aspect ratio, turn after turn, on all 15 seconds.
- More kinds of reference. Character, product and style images (up to six held consistent), motion clips up to three seconds, and audio cues; first and last frame interpolation from 3 to 10 seconds; each extension adds 3 to 10 seconds, up to 30 in all.
- Speech. More natural dialogue, clearer lip-sync and several speakers in one clip.
- Higher limits. Paid-tier rate limits doubled.
Google itself names what it is still fixing: fast sports action, quick changes of script and complex physics. Every clip carries a SynthID watermark.
What it costs
| Price | |
|---|---|
| 360p video | $0.023 a second |
| 720p video | about $0.07 a second (5,792 tokens a second at $12 per million output tokens) |
| 1080p, upscaled | $0.104 a second |
| 4K, upscaled | $0.209 a second |
| Input (text, image, video) | $1.50 per million tokens |
| Free tier | None |
Source: Gemini API pricing, read Nov 8, 2026. Omni 1.1 Flash's video output was $17.50 per million tokens; 1.2's is $12.
In Google's apps, Omni comes out of each plan's Flow credits rather than a per-second bill: AI Plus $4.99 a month with 200 credits, AI Pro $19.99 with 1,000 and AI Ultra from $99.99 with 10,000 (US prices, read Nov 8, 2026). Google Vids makes 15-second clips at no extra cost for anyone with a Google account or Workspace subscription.
Limits
The model page lists gemini-omni-1.2-flash as stable, with 131,072 input tokens and 65,536 output tokens; editing takes clips of up to 15 seconds, and extension looks back over the last 10. Rate limits by tier, read Nov 8, 2026:
| Requests a minute | Requests a day | |
|---|---|---|
| Free tier | Not supported | Not supported |
| Tier 1 | 8 | 40 |
| Tier 2 | 16 | 200 |
| Tier 3 | 40 | 2,000 |
Developers still calling gemini-omni-1.1-flash are moved to 1.2 on Dec 3, 2026. Google states no country limits for the API.
Where it ranks
Gemini Omni 1.2 Flash was first on Arena's text-to-video leaderboard when Vi.ki read it on Nov 6, 2026, above Google's own Veo 3.1 in 14th place (Veo). Best AI Video Generator compares it with Kling, Runway, Seedance and the rest.
What we think
We think Omni 1.2 Flash reaches Google AI Pro subscribers in the Gemini app before Mar 1, 2027. Today only Ultra has it in the app, but Pro already gets Omni through its 1,000 Flow credits, and Google Vids gives 15-second clips to anyone with a Google account, so keeping it from Pro's Gemini app is the odd one out.
Confidence: Likely. Check by: Mar 2027.
We expect the next Omni to pass 30 seconds per clip. Google went from 10 to 15 seconds between 1.1 and 1.2 and already lets a clip be extended to 30 seconds in steps, and Kling makes single shots of up to 30 seconds.
Confidence: Possible. Check by: Jun 2027.
Sources
- Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips, Google, Nov 5, 2026
- Gemini API changelog, Google, Nov 5, 2026
- Gemini Omni Flash model page, pricing and rate limits, Google, read Nov 8, 2026
- Google AI subscriptions, Google, read Nov 8, 2026
- Text-to-video leaderboard, Arena, read Nov 6, 2026
See also
-
VeoVeo is Google DeepMind's video model family; the latest, Veo 3.1, makes 4 to 8 second clips with sound at up to 4K. As of Nov 6, 2026 it costs $0.05 to $0.60 a second on Google Cloud, and in Google Flow only the cheap Veo 3.1 Lite stays after Dec 5, 2026, as Google moves its apps to the newer Gemini Omni.
-
Best AI Video GeneratorThe best AI video generator in Nov 2026 on LMArena's votes is Google's Gemini Omni Flash, and on Artificial Analysis's it is Alibaba's Wan 3.0; ByteDance's Seedance and MiniMax's Hailuo models rank near the top of both. OpenAI closed the Sora app in 2026, and Sora 2 and Veo 3.1 now rank 13th and 14th on LMArena.
-
KlingKling is the AI video generator from Kuaishou's Kling AI unit; its newest model, Kling 4.0, launched Oct 15, 2026 and makes clips of up to 30 seconds in one pass. The Kling 3.0 API costs from $0.084 a second, and Kling also runs inside Runway, Luma and Pika, as of Nov 6, 2026.
- Gemini 4 Carbon ReleaseGoogle announced Gemini 4 Carbon on Oct 28, 2026 as its strongest model, priced at $2 and $10 per million input and output tokens for an introductory period, then $4 and $20. As of Nov 8, 2026 only a subset of cyber defenders in Google's Fairwind Program can use it.
-
Genie 4 ReleaseGoogle DeepMind announced Genie 4 on Oct 27, 2026, a world model that generates explorable scenes in real time with their own sound and changes them on a typed prompt mid-run. As of Nov 8, 2026 it is a research preview for trusted testers, with Google AI Ultra and the Gemini API promised as "coming soon".
-
GitHub Copilot Fusion ReleaseAt GitHub Universe on Oct 28, 2026, GitHub made Copilot Fusion generally available, letting Copilot route and combine models at three effort levels instead of a model picker, with model costs 30% off through Nov 30, 2026. The same day GitHub Enterprise began including Copilot, and Copilot Standalone went on sale at $10 a user a month.