Google has released Gemini Omni 1.2 Flash, stretching generated clips to 15 seconds and cutting the 720p price. In a blog.google post dated November 5, 2026, Google said the model "introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following."

Google's Cloud model card lists the release date as November 5, 2026, and marks the launch stage as GA. A Google Cloud blog post covering the same launch is dated November 6, 2026.

#What is new?

  • Longer clips. "You can now generate and edit videos natively up to 15 seconds long, up from 10 seconds with Omni 1.1," Google wrote. "You can also specify duration in one-second increments from 3 to 15 seconds." The Verge reported the same range: "from three to 15 seconds."
  • Edit without a full redo. Google says "you can draft fast at 360p or 720p, fix a detail with a follow-up edit instead of re-generating the entire clip, and then upscale your best creations to 1080p or 4K." The Verge reported: "Google says Omni 1.2 Flash can also make edits to a video without re-generating the entire clip."
  • Conversational editing. "Multi-turn conversational editing works across full 15-second clips," Google says.
  • Speech and camera (Google claims). Google says the model can generate "more fluid, natural-sounding dialogue, clearer lip-sync, and distinct multi-speaker conditioning," and that users can "direct complex, continuous camera movements like sweeping FPV flythroughs to dramatic zoom-outs and orbits with significantly fewer unwanted jump cuts."
  • Limits Google names. "While development is ongoing to further improve things like fast sports action, rapid script changes and complex physics," Google wrote.

The Cloud model card lists resolutions of 360p, 720p, 1080p and 4K, and aspect ratios 16:9 and 9:16. First and last frames are limited to 3 to 10 seconds.

#How much does it cost?

As of November 6, 2026, Google's Gemini API pricing page states an effective price of "approximately $0.07 per second" for 720p on Omni 1.2 Flash, versus "approximately $0.10 per second" for Omni 1.1. blog.google says: "We have dropped the price 30% from Gemini Omni 1.1 making it available at $0.07 per second for 720p video." The Cloud blog, dated November 6, 2026, says "$0.07 per second of 720p video, 30% less than Gemini Omni 1.1 Flash, with similar savings at other resolutions."

That works out to about $0.07 per second at 720p, about 30% less according to Google. The pricing page also lists Standard video output at $12.00 per 1M tokens for Omni 1.2 Flash, versus $17.50 for Omni 1.1.

Effective December 3, 2026, Google's pricing page says: "all API requests to gemini-omni-1.1-flash automatically route to gemini-omni-1.2-flash and are billed at gemini-omni-1.2-flash rates."

#Where is it generally available?

  • Paid Gemini API. The pricing page says Omni 1.2 Flash is "now generally available to developers on the paid tier of the Gemini API." The free tier is listed as not available.
  • Google Cloud. The Cloud blog says: "Today, Gemini Omni 1.2 Flash is generally available on Google Cloud." blog.google's summary box says: "This model is generally available on the Gemini API and Google Cloud for your production needs." Google also says Provisioned Throughput is available and that outputs carry a SynthID watermark.

Rolling out, not GA. blog.google says Omni 1.2 Flash "rolls out across Google’s products and developer platforms," including Google AI Studio, the Google Cloud console, Google Vids ("generate 15-second clips at no additional cost in Google Vids with a Google account or Google Workspace subscription"), the Gemini app ("rolling out to Google AI Ultra subscribers"), Google Ads, and Flow for directing scenes and multi-turn edits. Flow, Vids, Ads and the Gemini app are rolling out, not generally available.

Gemini for business. See the unclear section below. Google's posts disagree on whether business chat access is already GA.

#How does it compare?

For another generative-media launch with published prices, see our story on ChatGPT Images 2.6 and GPT-Image-2.6. For Google's other Gemini institutional work, see Gemini for government services in preview.

Our analysis: The clear product change is length plus price: 15-second clips and a Google-stated 30% cut to about $0.07 per second at 720p. Availability is narrower than a casual reading of "generally available" suggests. Paid API and Google Cloud are GA; the consumer and workspace surfaces Google lists remain in a rollout. Teams should also note the December 3, 2026 routing of Omni 1.1 API traffic onto 1.2 rates.

#What is unclear?

  • Gemini for business. blog.google says the model is "generally available across the Gemini API and Gemini for business." The Google Cloud blog, dated November 6, 2026, says "coming soon to Gemini for business" and that business users will be able to create short videos in chat. We treat business as rolling out, not GA, until Google's posts agree.
  • Audio input. Marketing posts mention audio cues among references, while Google Cloud's model card lists audio as unsupported.
  • Regions. blog.google names no country list. The Cloud model card says only "Global: global."
  • Cloud per-second price. Cloud pricing pages show matching token rates; they do not print a separate per-second figure.