Hayz Labs

Gemini Omni Flash 1.1

GoogleAI modelReleased 27 AugOfficial site for Gemini Omni Flash 1.1 no referral link

Top-rated text to video on arena.ai, from $4.99/month in Google Flow. Skip it if price per clip matters most.

Our callUse itChecked 11 Oct
Score100 across 1 jobVideo, likely 96–100, #1 of 5 we have scored
Cost$4.99 a monthNo free plan
Cheaper optionNothing meaningfully cheaper scores as well

Should you use it?

Pick it if

People who want the highest-rated video model and already pay for, or will pay for, a Google AI plan.

Best for: People on a Google AI plan who want the top-rated video model (Video models Top 20)

Skip it if

You make many clips and want the lowest cost per minute; MiniMax H3 is close on quality for less.

You give up: About twice MiniMax H3's price per minute; its lead rests on few votes

The short version

What this is
Google's video model that makes clips from any mix of text, images, video and voice, and lets you change them by chatting. In the Gemini app, Google Flow and the Gemini API.
Why it matters
It is the highest-rated text to video model in arena.ai's blind tests, and the cheapest way in is a $4.99 Google plan.
  • Scores 100 for video: 1st of 48 on arena.ai text to video, 2nd on image to video.
  • About $0.10 per second of 720p in the API; included in Google AI Plus from $4.99/month.
  • Turn off Keep Activity in the Gemini app if you don't want uploads used for training.

Good at

  • First on arena.ai text to video and second on image to video, out of 48 models s1 s2.
  • Google says it extends scenes in 10 second steps up to 40 seconds and supports first and last frames and video references s8.
  • Google says you edit a clip by chatting, with each instruction building on the last s9.

Weak at

  • Only 7th of 28 distinct models on Artificial Analysis text to video, behind Wan 3.0, Seedance 2.5 and MiniMax H3 s3.
  • Costs about twice MiniMax H3 per minute on Artificial Analysis ($9.12 against $4.80) s3.
  • Its arena.ai text to video lead rests on fewer than 2,000 votes s1.

Our take

Gemini Omni Flash 1.1 is the strongest pick in video on arena.ai's blind tests: first for text to video and second for image to video s1 s2. Artificial Analysis is less sure, placing it 7th for text to video s3, and its arena.ai text to video lead has under 2,000 votes behind it s1. Treat it as one of a handful of top video models rather than a clear winner.

For most people the way in is Google Flow on a Google AI Plus plan at $4.99/month s5. In the API it costs about $0.10 per second of 720p s6. If you make a lot of clips, MiniMax H3 scores close on quality at roughly half the per-minute price on Artificial Analysis s3.

Score

A score from 0 to 100 per job, against everything available today. Overall 100 across 1 job, the average of the job scores.

New to this? What the scores and labels mean
0 to 100
Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
Our verdict
Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
First look
Just released. We say what it is and whether to bother, and give it a score once public results exist.
No score yet
None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
Best buy
Nothing cheaper scores as well for that job.
Best free
The best score for that job that costs nothing, through a free plan or by running on your own computer.
Pay as you go
No monthly plan: you pay for each use, usually through a developer account.
Checked
The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
AI model
The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
Open source
Free to download and run on your own computer, so nothing leaves your machine.
How we score, in full
100Likely 96–100.

Video

Best buy
#1 of 5we have scored

The top score of the 5 we have scored for this job.

From blind votes (Arena) · Arena data, CC BY 4.0

On a scale from 40 to 100, 100 in video, likely 96–100, the best we have scored.

2 sourcesData read 20 Oct

Alternatives

Nothing we have scored beats it for video on score or on price, and we have not scored a free option for it yet.

  • MiniMax H3Video model84Pay as you goMiniMax H3 and H3 Max top the two image to video boards, from about $4.80 a minute; the value pick. Side by side
  • Wan 3.0Video model89Pay as you goFirst on Artificial Analysis text to video; longer clips. Side by side
  • FLUX 3 VideoVideo model93Pay as you goThird on arena.ai text to video, from Black Forest Labs. Side by side
Compare side by side →

Value for money

Where it sits in video: higher is a better score, further left is cheaper to run. Green dots are the best value.

Video: score from 0 to 100 against cost to make one minute of hd (1080p) video (artificial analysis), for 2 scored items, with each Arena score's likely range. The ranking table holds the same data.
100
90
80
70
60
50
40
$0$5$10$20$50
ScoredBest value: nothing cheaper scores as wellLikely range of an Arena scoreThis review
Up: score, 0 to 100. Across: Cost to make one minute of HD (1080p) video (Artificial Analysis) (spaced to spread out the cheaper end)

Evidence

Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.

How we scored this

The video score is our own, built from public data: blind votes on Arena and, where they cover the job, Epoch AI's independent tests. How we combine them is our method and we don't publish it.

Public leaderboardIndependent test

Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.

No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score

Sources 9
  1. s1arena.ai Text to Video leaderboard
  2. s2arena.ai Image to Video leaderboard
  3. s3Artificial Analysis text to video leaderboard
  4. s4Artificial Analysis image to video leaderboard
  5. s5Google AI plans (Gemini subscriptions)
  6. s6Gemini API pricing
  7. s7Gemini Apps Privacy Hub
  8. s8Google blog: Build with Gemini Omni 1.1 Flash
  9. s9Google blog: Gemini Omni

Something here out of date or wrong? Report a mistake and we will check it against the source.

History 2 changes

Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.

  1. New: Video ratedReviewed: video.
  2. Audit: MiniMax H3 alternative reason corrected (H3 Max, not H3, is first on Artificial Analysis image to video). Rating unchanged.
Use it well 4 guides on this site
esc
↑↓ move↵ openesc closeType a product, a job or a question

Keyboard shortcuts

CtrlK
search everything
/
search everything
gr
reviews: all AI, scored
gg
start here
gu
guides
gw
step-by-step workflows
gt
try-it tools
gs
setup
ga
about
[ ]
previous and next entry, or collection
t
theme: auto, light, dark
?
this sheet