RELEASE · MODELS · #3158
Google releases Gemini Omni 1.2 Flash — cheaper, faster 15‑second video generation
Google is rolling out Gemini Omni 1.2 Flash across the Gemini API and Gemini for Business, lowering the price 30% from Omni 1.1 to $0.07/second for 720p and adding native 3–15 second video generation (up to 15s), multi‑turn conversational editing, and improved reference-following for stronger visual and audio consistency.
KEY POINTS
- Google is rolling out Gemini Omni 1.2 Flash across the Gemini API and Gemini for Business, lowering the price 30% from Omni 1.1 to $0.07/second for 720p and adding native 3–15 second video generation (up to 15s), multi‑turn conversational editing, and improved reference-following for stronger visual and audio consistency.
- Lower cost, longer clip length, and improved multi‑turn editing and reference consistency make AI video production more practical for ads, product try‑ons, and multi‑speaker scenes.
- Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips
DECISION BRIEF
CONFIDENCE
WHAT CHANGED
Google launched Gemini Omni 1.2 Flash and made it generally available across the Gemini API and Gemini for Business. The release lowers the 720p price by 30% (to $0.07/second), extends native single-generation video length to up to 15 seconds (specifiable in 1s increments from 3–15s), and adds multi‑turn conversational editing plus improved reference‑following for stronger visual and audio consistency.
WHY NOW
The combination of a material price cut (30% at 720p), longer native clip length (up to 15s), multi‑turn editing, and stronger reference following lowers friction for use cases cited in the announcement—e.g., telling complete short stories, product explainers, social ad spots, virtual try‑ons, catalog spins, and branded video ads—by allowing single-generation social-length clips, iterative fixes instead of full re‑generations, and better cross-shot consistency.
WHO IS AFFECTED
Directly affected (explicit in sources): developers and customers using the Gemini API and Gemini for Business; creators and product/marketing teams that convert product or character images into short ads, virtual try‑ons, catalog spins, or branded video assets.
CONFIRMED
All items below are explicit in the supplied excerpts: - Gemini Omni 1.2 Flash is rolling out and is generally available across the Gemini API and Gemini for Business. - Price for 720p video is $0.07 per second (a 30% reduction from Omni 1.1). - Native generation and editing supports clips from 3 to 15 seconds, with one-second increments; previous Omni 1.1 supported up to 10 seconds. - The release includes multi‑turn conversational editing capabilities and enhanced reference following. - Workflow supports drafting at 360p or 720p, making follow-up edits instead of full re-generation, and upscaling selected outputs to 1080p or 4K. - Generation can combine character/product/style images, short motion clips (up to three seconds), and audio cues; Omni 1.2 holds onto those details for greater consistency. - Examples in the excerpts: a 15-second virtual try-on sequence from one model photo plus front-and-back product shots; a poster-building example where Omni 1.2 matches reference details more closely than Omni 1.1.
UNCERTAIN
Missing or unclear in the supplied excerpts (explicitly labeled): - Missing: exact pricing for resolutions other than 720p (e.g., cost for 360p drafts, 1080p/4K upscales) and whether upscales incur separate per‑second charges. - Missing: quantitative performance metrics (latency, throughput, per‑clip generation time) and hardware/compute requirements. - Missing: limits and operational details for multi‑turn conversational editing (maximum turns, state size, retention across edits). - Missing: content policy, safety/guardrail behavior, and moderation requirements for generated videos. - Missing: regional availability, enterprise tiering, and billing/quotas for Gemini for Business customers. - No conflicting evidence present in the supplied excerpts; both sources present the same statements.
WHAT TO WATCH
Concrete observable signals to monitor (based on the announcement content): - Gemini API documentation and changelog entries showing parameters for duration (3–15s), multi‑turn editing APIs, and file/resolution pricing. - Official pricing page updates confirming $0.07/sec and any rates for drafts (360p), 1080p/4K upscales, or enterprise tiers. - Example galleries, demo videos, or case studies demonstrating 15s virtual try‑ons, catalog spins, social ad spots, and the poster example cited. - Developer blog posts or DeepMind/Google follow‑ups with technical details, performance numbers, or guidance on iterative editing workflows. - Product announcements from customers or partners showing production use (e.g., ads or product explainers) built with Omni 1.2 Flash.
WHY IT MATTERS
Lower cost, longer clip length, and improved multi‑turn editing and reference consistency make AI video production more practical for ads, product try‑ons, and multi‑speaker scenes.
EVIDENCE MAP
4Editorial claims linked to specific sources, with support, contradiction and context shown separately.
Gemini Omni 1.2 Flash price is 30% lower than Omni 1.1, listed at $0.07 per second for 720p.
SUPPORTEDChecked 2026-11-05 · 2 supporting
Omni 1.2 Flash supports native video generation and editing up to 15 seconds, with durations selectable in one-second increments from 3 to 15 seconds.
SUPPORTEDChecked 2026-11-05 · 2 supporting
The excerpt says you can generate and edit videos natively up to 15 seconds and specify duration from 3 to 15 seconds in one-second increments.
SUPPORTS Google DeepMindMEDIA · 2026-11-05The DeepMind excerpt repeats that native generation and editing are available up to 15 seconds and durations can be specified from 3 to 15 seconds.
Omni 1.2 Flash introduces multi-turn conversational editing capabilities.
SUPPORTEDChecked 2026-11-05 · 2 supporting
Omni 1.2 Flash has enhanced reference-following that improves visual and audio consistency (e.g., faces, garments, packaging typography, brand colors) across frames.
SUPPORTEDChecked 2026-11-05 · 2 supporting
The excerpt states Omni 1.2 Flash 'holds onto those details' and lists faces, garments, packaging typography, and brand colors as staying consistent across camera angles and frames.
SUPPORTS Google DeepMindMEDIA · 2026-11-05The DeepMind excerpt repeats that Omni 1.2 Flash maintains stronger character, object, and scene consistency with less visual drift or morphing.
SOURCES & TIMELINE
3Gemini Omni 1.2 Flash brings 15-second clips, stronger consistency, and faster, more cost-effective generation. Today, we’re rolling out Gemini Omni 1.2 Flash, and making it generally available across the Gemini API and Gemini for business . Gemini Omni 1.2 Flash introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following. We have dropped the price 30%…
Gemini Omni 1.2 Flash brings 15-second clips, stronger consistency, and faster, more cost-effective generation. Today, we’re rolling out Gemini Omni 1.2 Flash, and making it generally available across the Gemini API and Gemini for business . Gemini Omni 1.2 Flash introduces native 15-second video creation, multi-turn conversational editing capabilities, and enhanced reference following. We have dropped the price 30%…
Google Vids , our video creation and editing tool, now runs on Google's newest video generation model: Omni 1.2 Flash . Starting today, anyone with a Google account or Google Workspace subscription can generate up to three 15-second videos per month in Vids at no cost. With Omni 1.2 in Google Vids, you can now bring your ideas to life in so many more ways: Create your product promos in one go. Produce professional,…
Google Deepmind is making its Gemini Omni 1.2 Flash video-generation model generally available. The updated model creates clips up to 15 seconds long, supports conversational editing, and costs 30 percent less than its predecessor. Google says Gemini Omni 1.2 Flash is rolling out through the Gemini API , Google AI Studio , the Google Cloud Console, Flow, Google Vids, the Gemini app for Google AI Ultra subscribers, a…