Seedance 2.5 is live — 30-second cinematic video with native audio & real-person references

Gemini Omni 1.1 — Draft in 360p, Deliver in 4K

Gemini Omni 1.1 is Google's newest video model. Type a prompt, drop in a still, or hand it three references and get a 4 to 10 second clip. Iterate cheaply at 360p, then render the keeper at 1080p or 4K from the same request.

Text-to-videoFirst-frame image-to-videoThree-image fusionReference-to-video360p drafts4K output
Highlights
4–10 s · 360p drafts to 4K · first-frame or reference images · video reference
Best for
Storyboards, product shots, character clips
Input
Text, 1 or 3 images, or a source clip
Output
Video (mp4)
Input

≤ 2000 chars · required

Default 720p · 360p and 720p share a price

16:9 or 9:16 · default 16:9

Default 6 · ignored in reference-to-video mode

wire field: content_filter (boolean) · default true · API only

Estimated cost~$0.462462 credits
Result

Try one of these prompts

See what it generates

Unedited output from this model. Every clip plays exactly as the API returned it.

What is Gemini Omni 1.1?

Gemini Omni 1.1 is the point release of Google's Gemini Omni video model, announced on August 27, 2026. On reAPI it is one async endpoint with four modes: text-to-video, image-to-video from a first frame or a reference, three-image fusion, and reference-to-video from a clip of up to 30 seconds. Clips run 4 to 10 seconds in 16:9 or 9:16. The headline change over Gemini Omni 1.0 is the 360p draft tier, which Google says renders up to 60% faster than 720p, so you can test five prompts for the price of one final. Every job is billed flat per generation.

What you can build with this model

Real-world workflows and production use cases you can build and ship with this model.

Animate a product still with Gemini Omni 1.1

Upload one photo, set the image role to frame, and describe the move. Gemini Omni 1.1 keeps your first frame pixel-exact and animates from there — a cat hopping onto the counter, a bottle turning in the light. Ship it at 1080p or 4K when the take is right.

Animate an image

Build a scene from three references

Send a location, a character and a prop as three images. Gemini Omni 1.1 fuses them into one shot with consistent lighting and geometry, so a costume, a street and a bicycle become a single tracking take — no compositing, no masks, one Gemini Omni 1.1 call.

Draft at 360p, deliver at 4K

Iterate on framing and motion at 360p, where Gemini Omni 1.1 renders fastest and cheapest. Once the take works, resend the same request at 4K for macro detail, glossy product surfaces and hero shots that survive a big screen.

Pricing

Credit-based — 1 credit = $0.001 USD. Pay only for completed generations.

First test cost
$0.347347 credits

One sample at the cheapest tier (1 generation).

Testing budget guide
Add credits
$10
≈ 28 tests
$50
≈ 144 tests
$100
≈ 288 tests
ModelCategoryPrice
360p draft4 seconds
$0.347
347 credits · 1 generation
6 seconds
$0.462
462 credits · 1 generation
8 seconds
$0.578
578 credits · 1 generation
10 seconds
$0.693
693 credits · 1 generation
720p4 seconds
$0.347
347 credits · 1 generation
6 seconds
$0.462
462 credits · 1 generation
8 seconds
$0.578
578 credits · 1 generation
10 seconds
$0.693
693 credits · 1 generation
1080p4 seconds
$0.347
347 credits · 1 generation
6 seconds
$0.462
462 credits · 1 generation
8 seconds
$0.578
578 credits · 1 generation
10 seconds
$0.693
693 credits · 1 generation
4K4 seconds
$0.809
809 credits · 1 generation
6 seconds
$0.924
924 credits · 1 generation
8 seconds
$1.04
1040 credits · 1 generation
10 seconds
$1.155
1155 credits · 1 generation
Reference 360pper generation
$0.924
924 credits · 1 generation
Reference 720pper generation
$0.924
924 credits · 1 generation
Reference 1080pper generation
$0.924
924 credits · 1 generation
Reference 4Kper generation
$1.386
1386 credits · 1 generation

Why reAPI

Cheap drafts, expensive finals — same request

Gemini Omni 1.1 prices 360p the same as 720p and keeps the request shape identical across tiers. Explore at draft resolution, change one field, and render the final. Failed jobs refund automatically.

You decide what an image means

One image can be a locked first frame or a loose reference — Gemini Omni 1.1 lets you pick with a single field. Three images become subject and scene references for Gemini Omni 1.1. Two images is the only count it refuses.

Drop-in upgrade from Gemini Omni

Same endpoint, same fields, same task polling as gemini-omni. Change the model id to gemini-omni-1-1 and you get the 360p tier, the image role control and the newer model — nothing else in your Gemini Omni 1.1 integration moves.

Gemini Omni 1.1 vs Gemini Omni 1.0

What changes when you move the model field from gemini-omni to gemini-omni-1-1 on reAPI — same endpoint, same request shape.

Capability
Gemini Omni 1.1 on reAPI
Gemini Omni 1.0 on reAPI
Resolutions
360p, 720p, 1080p, 4K
720p, 1080p, 4K
Draft tier
360p drafts, priced like 720p, up to 60% faster to render
None — every take renders at delivery resolution
Image control
Pick per request: one image as a locked first frame, or 1 / 3 images as references
One image always animates as the first frame; three images fuse
Content filter
Switchable per request via content_filter
Not exposed
Price per generation
Lower at every resolution and duration tier
Previous Gemini Omni rates — see its pricing table
Clip length & video reference
4–10 seconds; one source clip of up to 30 seconds
Same: 4–10 seconds, one source clip of up to 30 seconds

Both models run on the same reAPI endpoint and task polling; switching is a one-line change in the model field. Rates for each are on their own pricing tables.

Ship Gemini Omni 1.1 in three steps

  1. step 01

    Create an API key

    Sign up and grab a key from the dashboard. Signup credits cover your first Gemini Omni 1.1 drafts — no card required.

    Open
  2. step 02

    Submit a video task

    POST to /api/v1/videos/generations with model = gemini-omni-1-1. Gemini Omni 1.1 returns a task ID immediately so your worker can move on.

    Open
  3. step 03

    Poll the result

    GET /api/v1/tasks/:id until status is completed. Download the Gemini Omni 1.1 mp4 and ship it.

    Open
docs/api/gemini-omni-1-1

API reference

Drop-in code and the full parameter table.

curl -X POST https://reapi.ai/api/v1/videos/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-omni-1-1",
    "prompt": "A ginger cat hops onto a sunlit kitchen counter, slow dolly-in",
    "duration": 6,
    "resolution": "1080p",
    "aspect_ratio": "16:9"
  }'

Parameter validation failed

Rejected synchronously with the failing field named. Check enum values, ranges, and URL fields — nothing is charged.

Authentication or balance issue

401 means a missing or invalid Bearer key; 402 means the reserve exceeds your balance. Manage keys and credits in the console.

Content or material rejected

Reference material and outputs pass automated moderation. Rejected tasks fail with a clear error and a full refund.

Task failed or timed out

A task that reaches a failed state is never charged — the reserve refunds automatically. Keep the task id and retry when ready.

Frequently asked questions

Common questions about this model.

Gemini Omni 1.1 is Google's August 2026 update to the Gemini Omni video model. On reAPI it generates 4 to 10 second clips from text, from a single image used as a first frame or a reference, from three reference images, or from a source video of up to 30 seconds — at 360p, 720p, 1080p or 4K.

start building

Ready to ship?

Try it in the playground or grab an API key to integrate now.