Early-bird pricing (ends Dec 25), locked in while you stay subscribed: Go $10/mo (normally $20), Plus with Opus 5.5 just $30/mo (normally $50)Subscribe →

Gemini Omni 1.2 Flash AI Video Generator and API

Try Gemini Omni 1.2 Flash online or via API. 3–15 second 720p clips from a prompt or up to 3 images. Billed per second. Failed jobs are free.

Run with API
MODEL TYPE
24H Status MonitorSuccess: 100%
Input
0/5000
Ideas:
Prompt0/5000
0/3

Optional. Up to 3 images. Leave empty for text-to-video. Reference video is not supported.

16:9 landscape or 9:16 portrait. 11–15 seconds is portrait only.

3–10s landscape or portrait. 11–15s portrait only.

Output
Gemini Omni 1.2 Flash1 prices
google
SpecificationCreditsPrice (USD)
720p video7per second$0.07per second

Prices follow the model configuration. Reference images are not billed unless the model says so.

What Gemini Omni 1.2 Flash generates

One request returns one 720p MP4 between 3 and 15 seconds long.

Native 720p

1280×720 landscape or 720×1280 portrait. H.264 MP4.

Any length from 3 to 15 seconds

Pick a whole number of seconds. The default is 8.

Text or up to 3 images

Write a prompt alone, or add 1, 2, or 3 stills to guide the look.

Same fields in the playground and the API

What you set on this page is what POST /api/openapi/submit sends.

Gemini Omni 1.2 Flash clips from this playground

Generated through the AIReiter OpenAPI on 18 November 2026.

01

Text only, 8 seconds, 16:9

Prompt: A golden retriever running along a sunny beach, cinematic tracking shot, realistic

Request: no images, 16:9, 8 seconds.

Delivered: H.264 MP4, 1280×720, 8.00 seconds.

Generate a 1.2 clip

Gemini Omni 1.2 Flash API pricing

The live table on this page is the source of truth. Failed jobs are not charged.

Billed per second

The charge follows the length you pick. Longer clips cost more.

Images are free

Text only, 1, 2, or 3 images: the same length costs the same.

Aspect ratio is free

16:9 and 9:16 cost the same.

How to read a quote

Submit returns estimated credits for the length you sent. Query returns credits_used when the job completes.

Text or up to 3 reference images

No mode tabs. One prompt, one optional image field.

Text to video

Leave the image field empty. The prompt drives the whole clip.

1 to 3 stills

Images guide the subject and style. They are references, so the clip does not have to open on your first image.

Length and orientation

3–10 seconds: 16:9 or 9:16. 11–15 seconds: 9:16 only. The playground switches to 9:16 for you.

Video input

Reference video, video extension, and video editing are not available for this model.

Gemini Omni 1.2 Flash API: submit and query

One async contract. The model ID for this page is gemini_omni_1_2_flash.

Model ID

Send gemini_omni_1_2_flash.

Submit

POST /api/openapi/submit with model, params (prompt, aspect_ratio, video_length, image_url), and a unique out_task_id.

Query

POST /api/openapi/query with the same out_task_id. A completed job includes credits_used and the video URL.

What the API rejects

A 4th image. 11–15 seconds with 16:9. Lengths outside 3–15. A reference video (video_url).

Supported Gemini Omni 1.2 Flash Controls

ControlTypeDefaultNotes
01prompttext——
02image_urlimage—Optional. Up to 3 images. Leave empty for text-to-video. Reference video is not supported.
03aspect_ratiostring16:916:9 landscape or 9:16 portrait. 11–15 seconds is portrait only.
04video_lengthstring3s / 4s / 5s / 6s / 7s / 8s / 9s / 10s / 11s / 12s / 13s / 14s / 15s83–10s landscape or portrait. 11–15s portrait only.

Generate with Gemini Omni 1.2 Flash

Open Playground ↑
  1. Write the motion

    Subject first, then camera and light. Skip images for text-to-video.

  2. Add up to 3 images if you have them

    Product shots, a character, or a style frame. Three is the cap.

  3. Pick length and aspect ratio

    3 to 15 seconds. 16:9 or 9:16 up to 10 seconds; 9:16 from 11 seconds.

  4. Submit and poll

    POST /api/openapi/submit returns a quote. Poll POST /api/openapi/query with the same out_task_id.

Use Gemini Omni 1.2 Flash through the AIReiter API

API ↗
01Model IDs

gemini_omni_1_2_flash

02Submit a task

POST to /api/openapi/submit with the model, a unique out_task_id, and parameters.

03Query the result

POST to /api/openapi/query with the same out_task_id until the task completes.

04Store results on your side

Save outputs in your own storage rather than hot-linking them.

Gemini Omni 1.2 Flash FAQ

01Does Gemini Omni 1.2 Flash support 4K or 1080p?

No. Every clip is native 720p: 1280×720 landscape or 720×1280 portrait.

02How much does the Gemini Omni 1.2 Flash API cost?

Billed per second of output, from 3 to 15 seconds. Images and aspect ratio do not change the price. Failed jobs are not charged. The table on this page is current.

03Can I upload a reference video?

No. This model takes a prompt and up to 3 images. For reference video, use Kling v3 Omni.

04Which durations can I request?

Any whole number from 3 to 15 seconds. The default is 8.

05Why are 11–15 second clips portrait only?

The model only renders 11–15 second clips in 9:16. The playground switches to 9:16 for you; the API rejects 16:9 at those lengths.

06Can I set a first and last frame?

No. Your images are references for subject and style. The clip is not forced to start or end on them.

07Which API model ID should I use?

gemini_omni_1_2_flash. Send it to POST /api/openapi/submit and poll POST /api/openapi/query with the same out_task_id.

08Is this Google's official Gemini API?

No. This page runs Gemini Omni 1.2 Flash through the AIReiter API with AIReiter credits. Google's own Gemini docs are on ai.google.dev.

BOARDING

Start building with leading image, video and text models.

One API keyOne billing systemOne usage dashboard