Gemini Omni 1.2 Flash API
gemini-omni-1.2-flashGemini Omni 1.2 Flash is Google's Omni video model released on 5 November 2026, and on APIMODELS it costs $0.045 per output second at 720p and $0.052 at 1080p — 36% and 50% below Google's $0.07 and $0.104. Per Google, 1.2 extends clips to 15 seconds (1.1 stopped at 10), keeps faces, garments and brand colors closer to your reference images, drifts and morphs less across a shot, holds the camera steadier with fewer jump cuts, and delivers more natural speech with clearer lip-sync; Google also says fast sports action, rapid script changes and complex physics are still hard. One model id covers three input modes chosen by the fields you send: a prompt alone is text-to-video; images (up to 3) is reference-to-video for a character, a product or a style; first_frame_url, optionally with last_frame_url, anchors the opening (and closing) frame. Duration is any whole number of seconds from 3 to 15 — 3 to 10 when both frames are set — output is 720p or 1080p in 16:9 or 9:16, and every clip comes with synced audio. Reference images cannot be combined with a first frame, and video input (editing an existing clip), saved voices or characters, 4K and 360p are not available on this model here; Gemini Omni 1.1 Flash still covers those. Success is not 100%: upstream safety filters can reject a prompt or an image and the model can be temporarily unavailable. If the primary upstream channel is unavailable, the request switches automatically to a second channel at the same price, and failed requests are never charged.
Generate Video
Leave empty for text-to-video, or add up to 3 reference images (a character, a product, a style). Reference images cannot be combined with a first frame.
Result
Generated video will appear here
Provide URLs and click Generate
Below the Official Price
720p $0.045/s and 1080p $0.052/s against Google's $0.07 / $0.104 per second; an 8-second 720p clip is $0.36
Up to 15 Seconds
Any whole number of seconds from 3 to 15 (1.1 stopped at 10); 3 to 10 when both a first and a last frame are set
Closer to Your References
Per Google: faces, garments and brand colors stay closer to the reference images, with less drift and morphing across a shot
Clearer Speech, Steadier Camera
Per Google: more natural dialogue with clearer lip-sync, and camera moves with fewer jump cuts
Three Input Modes
Prompt only, up to 3 reference images, or a first frame with an optional last frame — one model id, 720p or 1080p, 16:9 or 9:16
Limits to Know
No video input, saved voices/characters, 4K or 360p here; a first frame cannot be combined with reference images; success is not 100%, failed requests are not charged
About Gemini Omni 1.2 Flash
Gemini Omni 1.2 Flash is a Video Generation API provided by Google. Gemini Omni 1.2 Flash is Google's Omni video model released on 5 November 2026, and on APIMODELS it costs $0.045 per output second at 720p and $0.052 at 1080p — 36% and 50% below Google's $0.07 and $0.104. Per Google, 1.2 extends clips to 15 seconds (1.1 stopped at 10), keeps faces, garments and brand colors closer to your reference images, drifts and morphs less across a shot, holds the camera steadier with fewer jump cuts, and delivers more natural speech with clearer lip-sync; Google also says fast sports action, rapid script changes and complex physics are still hard. One model id covers three input modes chosen by the fields you send: a prompt alone is text-to-video; images (up to 3) is reference-to-video for a character, a product or a style; first_frame_url, optionally with last_frame_url, anchors the opening (and closing) frame. Duration is any whole number of seconds from 3 to 15 — 3 to 10 when both frames are set — output is 720p or 1080p in 16:9 or 9:16, and every clip comes with synced audio. Reference images cannot be combined with a first frame, and video input (editing an existing clip), saved voices or characters, 4K and 360p are not available on this model here; Gemini Omni 1.1 Flash still covers those. Success is not 100%: upstream safety filters can reject a prompt or an image and the model can be temporarily unavailable. If the primary upstream channel is unavailable, the request switches automatically to a second channel at the same price, and failed requests are never charged. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: 720p · per second: $0.045, 1080p · per second: $0.052, 720p · 8s: $0.36, 1080p · 8s: $0.416, 720p · 15s: $0.675, 1080p · 15s: $0.78, Official Google rate · 720p per second: $0.07, Official Google rate · 1080p per second: $0.104.
Key Features
- Below the Official Price -- 720p $0.045/s and 1080p $0.052/s against Google's $0.07 / $0.104 per second; an 8-second 720p clip is $0.36
- Up to 15 Seconds -- Any whole number of seconds from 3 to 15 (1.1 stopped at 10); 3 to 10 when both a first and a last frame are set
- Closer to Your References -- Per Google: faces, garments and brand colors stay closer to the reference images, with less drift and morphing across a shot
- Clearer Speech, Steadier Camera -- Per Google: more natural dialogue with clearer lip-sync, and camera moves with fewer jump cuts
- Three Input Modes -- Prompt only, up to 3 reference images, or a first frame with an optional last frame — one model id, 720p or 1080p, 16:9 or 9:16
- Limits to Know -- No video input, saved voices/characters, 4K or 360p here; a first frame cannot be combined with reference images; success is not 100%, failed requests are not charged
Use Cases
Marketing Videos
Quickly generate brand promotion videos for ad campaigns and social media marketing.
Social Media Content
Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.
Product Demos
Generate product feature demonstrations and tutorials to improve user conversion.
Educational Content
Produce course explanations, knowledge explainers, and training videos at an affordable price.
Why APIMODELS
- Unified API -- One API key to access all models, no need to register on multiple platforms
- Transparent Pricing -- Pay-as-you-go with per-call pricing published on every model page, ideal for indie developers and startups
- Instant Access -- Start using immediately after signup, supports Stripe and Alipay payments
- Full Documentation -- Detailed API docs with code examples in cURL, Python, and Node.js
Frequently Asked Questions
How much does Gemini Omni 1.2 Flash cost?
Gemini Omni 1.2 Flash is available through APIMODELS at: 720p · per second: $0.045, 1080p · per second: $0.052, 720p · 8s: $0.36, 1080p · 8s: $0.416, 720p · 15s: $0.675, 1080p · 15s: $0.78, Official Google rate · 720p per second: $0.07, Official Google rate · 1080p per second: $0.104. Billing is pay-as-you-go — you only pay for what you generate.
How to use Gemini Omni 1.2 Flash API?
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
What is the difference between APIMODELS and the official Google API?
APIMODELS offers the same Gemini Omni 1.2 Flash model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
How much does Gemini Omni 1.2 Flash cost on APIMODELS?
It is billed per requested second: $0.045/s at 720p and $0.052/s at 1080p, against Google's official $0.07 and $0.104 (36% and 50% below). An 8-second 720p clip is $0.36, a 15-second 720p clip $0.675 and a 15-second 1080p clip $0.78. Only delivered videos are charged — failures and safety rejections cost nothing.
What is new in Gemini Omni 1.2 Flash compared with 1.1?
Per Google's 5 November 2026 announcement: clips up to 15 seconds instead of 10, a 30% lower official price, faces, garments and brand colors that stay closer to your reference images, less drift and morphing across a shot, steadier camera moves with fewer jump cuts, and more natural speech with clearer lip-sync. Google also says fast sports action, rapid script changes and complex physics are still hard. These are Google's claims, not our own benchmark.
How do I call it, and what inputs does it accept?
POST https://api.apimodels.app/v1/video/generations with model "gemini-omni-1.2-flash", then poll the same endpoint with task_id (or pass callback_url). A prompt alone is text-to-video; images (up to 3, URL or base64) is reference-to-video; first_frame_url, optionally with last_frame_url, anchors the opening and closing frame. duration is any whole number of seconds from 3 to 15 (3 to 10 with both frames), resolution is 720p or 1080p, aspect_ratio is 16:9 or 9:16. Every clip comes with synced audio.
What are the limitations on APIMODELS?
Video input (editing an existing clip), saved voices or characters (audio_ids / character_ids), seed, 4K and 360p are not available on this model here, and a first frame cannot be combined with reference images; those requests return a 400 at creation and are not charged. Success is not 100%: upstream safety filters can reject a prompt or an image, and the model can be temporarily unavailable. If the primary upstream channel is unavailable, the request switches automatically to a second channel at the same price; failed requests are never charged.
Gemini Omni 1.2 Flash or 1.1 Flash — which should I use?
Use 1.2 for new work: it costs 36% less per second here ($0.045 vs $0.07 at 720p), runs up to 15 seconds and, per Google, follows references more closely. Stay on Gemini Omni 1.1 Flash when you need 4K, video editing from a source clip, more than 3 reference images, or saved voices and characters. Both take the same request fields, so switching is a change to the model string. Google has announced that its own API will route gemini-omni-1.1-flash to 1.2 from 3 December 2026.
How does Gemini Omni 1.2 Flash compare to other Video Generation models?
On APIMODELS, Gemini Omni 1.2 Flash runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Text-to-Video, Up to 3 Reference Images, First + Last Frame, 720p / 1080p, 3–15s, Synced Audio, and you can weigh it on price and capability against other Video Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Video Generation option with live pricing at apimodels.app/models.
What can Gemini Omni 1.2 Flash do?
Gemini Omni 1.2 Flash supports: Text-to-Video, Up to 3 Reference Images, First + Last Frame, 720p / 1080p, 3–15s, Synced Audio. See the APIMODELS docs for full parameters and call examples.
Can I access the Gemini Omni 1.2 Flash API from anywhere (incl. China)?
Yes. APIMODELS exposes Gemini Omni 1.2 Flash through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
What payment methods are supported?
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.