video model comparison
Gemini Omni 1.2 Flash vs Gemini Omni Flash 1.1
Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1 are video models, from Google. Gemini Omni Flash 1.1 is now listed as a legacy model. Gemini Omni 1.2 Flash is 30% cheaper per video second at 720p than Gemini Omni Flash 1.1, $0.07 vs $0.10. On Arena Text-to-Video, Gemini Omni 1.2 Flash scores 1541 Elo and Gemini Omni Flash 1.1 1514 Elo (Arena, measured November 5, 2026). Both accept 131,072 tokens of context.
- Higher Arena Text-to-Video
- Gemini Omni 1.2 Flash1541 Elo against 1514 Elo
- Lower price per video second at 720p
- Gemini Omni 1.2 Flash$0.07 against $0.10
- Newer release
- Gemini Omni 1.2 FlashNov 2026 against Aug 2026
Data verified November 6, 2026 · Dataset 2026-11-06
Side by side
Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | Gemini Omni 1.2 Flash | Gemini Omni Flash 1.1 |
|---|---|---|
| Price | ||
| Price per video second at 720p | $0.07 (better) | $0.10 |
| Independent benchmarks | ||
| Arena Text-to-Video | 1541 Elo (#1 of 6) (better) | 1514 Elo |
| Arena Image-to-Video | 1502 Elo (#1 of 5) (better) | 1486 Elo |
| Artificial Analysis Video Arena (image to video) | Not measured | 1046 Elo |
| Artificial Analysis Video Arena (text to video) | Not measured | 1129 Elo |
| Specs | ||
| Provider | ||
| Release date | November 5, 2026 | August 27, 2026 |
| Access | API only | API only |
| Context window | 131,072 tokens | 131,072 tokens |
| Max output | 65,536 tokens | 65,536 tokens |
| Input | text, image, video | text, image, video |
| Output | video, audio, text | video, audio |
Scores:Arena · 2026-11-06Artificial Analysis · 2026-11-03Artificial Analysis · 2026-11-03
Charts
Against every current video model
Where Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1 land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Gemini Omni Flash 1.1 is no longer a current model, so it is not ranked. On Arena Text-to-Video, Gemini Omni 1.2 Flash ranks #1 of 6 current models. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text-to-Video
Gemini Omni 1.2 Flash:#1of 6
1,541 Elo · ahead of 100%
Gemini Omni Flash 1.1:Not rankedno longer current
1,514 Elo · ahead of 83%
Arena Image-to-Video
Gemini Omni 1.2 Flash:#1of 5
1,502 Elo · ahead of 100%
Gemini Omni Flash 1.1:Not rankedno longer current
1,486 Elo · ahead of 60%
Artificial Analysis Video Arena (image to video)
Gemini Omni 1.2 Flash: Not scored
Gemini Omni Flash 1.1:Not rankedno longer current
1,046 Elo · ahead of 33%
Artificial Analysis Video Arena (text to video)
Gemini Omni 1.2 Flash: Not scored
Gemini Omni Flash 1.1:Not rankedno longer current
1,129 Elo · ahead of 67%
Price and context
Price per video second
Gemini Omni 1.2 Flash:#4of 8
$0.07 · cheaper than 57%
Gemini Omni Flash 1.1:Not rankedno longer current
$0.10 · cheaper than 25%
Quality against price
Gemini Omni 1.2 Flash scores 1,541 at $0.07; Gemini Omni Flash 1.1 scores 1,514 at $0.1 (price per video second). The line joins the current models no other beats on both price and Arena Text-to-Video score; hover any point to name it.
Quality against price: the data
| Model | Provider | Price per video second | Arena Text-to-Video (Elo) |
|---|---|---|---|
| Gemini Omni 1.2 Flash | $0.070 | 1,541 | |
| Gemini Omni Flash 1.1 | $0.10 | 1,514 | |
| Grok Imagine Video 1.5 | xAI | $0.080 | 1,486 |
| Dreamina Seedance 2.5 | ByteDance Seed | $0.23 | 1,480 |
| Veo 3.1 Preview | $0.40 | 1,363 | |
| grok-imagine-video | xAI | $0.050 | 1,341 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
At each provider's listed rates.
10M input and 2M output tokens
The same price
- Gemini Omni 1.2 Flash
- $33
- Gemini Omni Flash 1.1
- $33
One minute of video at 720p
Gemini Omni Flash 1.1 costs 1.4× as much
- Gemini Omni 1.2 Flash
- $4.20
- Gemini Omni Flash 1.1
- $6
| Workload or rate | Gemini Omni 1.2 Flash | Gemini Omni Flash 1.1 |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $33 | $33 |
| One minute of video at 720p | $4.20 (better) | $6 |
| Other listed rates | ||
| 1M output tokens, video | $12 (better) | $17.50 |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
Gemini Omni 1.2 Flash
Where it leads
- Lower price per video second at 720p, $0.07 vs $0.10
- Higher Arena Text-to-Video score, 1541 Elo vs 1514 Elo
- Higher Arena Image-to-Video score, 1502 Elo vs 1486 Elo
- Also outputs text
Best for
- Short clips with sound and consistent characters that need conversational edits
Watch out for
- Arena's ratings rest on 2,745 votes or fewer per board so far, far fewer than older video models
- 1080p and 4K come from upsampling, and first-and-last-frame interpolation is limited to 3 to 10 seconds
- Paid tier only: there is no free-tier access in the Gemini API
Gemini Omni Flash 1.1
Where it leads
No measured lead over Gemini Omni 1.2 Flash in this data.
Best for
- Short clips with sound that need conversational edits
Watch out for
- Google now calls it its previous-generation video model: from December 3, 2026, requests to gemini-omni-1.1-flash are routed to Gemini Omni 1.2 Flash and billed at its rates
- Each clip is 3 to 10 seconds; extensions add 10 seconds at a time up to 40 seconds
- Editing uploaded videos is not available in every region, and voice editing is not supported
From benchmark to production
Building on Gemini Omni 1.2 Flash or Gemini Omni Flash 1.1?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
Gemini Omni 1.2 Flash vs Gemini Omni Flash 1.1 FAQ
Which is cheaper, Gemini Omni 1.2 Flash or Gemini Omni Flash 1.1?
Gemini Omni 1.2 Flash is 30% cheaper per video second at 720p than Gemini Omni Flash 1.1, $0.07 vs $0.10.
How much would one minute of video at 720p cost with Gemini Omni 1.2 Flash or Gemini Omni Flash 1.1?
One minute of video at 720p comes to $4.20 with Gemini Omni 1.2 Flash and $6 with Gemini Omni Flash 1.1 at their listed rates.
Which scores higher on independent benchmarks, Gemini Omni 1.2 Flash or Gemini Omni Flash 1.1?
Gemini Omni 1.2 Flash leads on Arena Text-to-Video, 1541 Elo to 1514 Elo; Gemini Omni 1.2 Flash leads on Arena Image-to-Video, 1502 Elo to 1486 Elo. Scores are independent evaluations, not either vendor's launch figures.
Which has the larger context window, Gemini Omni 1.2 Flash or Gemini Omni Flash 1.1?
Both accept 131,072 tokens of context. Both return up to 65,536 tokens per response.
How do Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1 differ in features?
Gemini Omni 1.2 Flash produces video, audio and text; Gemini Omni Flash 1.1 produces video and audio.
Further reading
More on Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1
Related comparisons
- Dreamina Seedance 2.5 vs Gemini Omni 1.2 Flash
- Dreamina Seedance 2.5 vs Gemini Omni Flash 1.1
- Gemini Omni 1.2 Flash vs grok-imagine-video
- Gemini Omni Flash 1.1 vs Grok Imagine Video 1.5
- Gemini Omni 1.2 Flash vs Grok Imagine Video 1.5
- Gemini Omni Flash 1.1 vs grok-imagine-video
- Gemini Omni 1.2 Flash vs Veo 3.1 Preview
- Gemini Omni Flash 1.1 vs Grok Imagine Video 1.5 Lite
- Gemini Omni 1.2 Flash vs Gen-4.5
- Gemini Omni Flash 1.1 vs Veo 3.1 Preview
- Gemini Omni 1.2 Flash vs Grok Imagine Video 1.5 Lite
- Gemini Omni Flash 1.1 vs Gen-4.5
Production evaluation
Choosing between Gemini Omni 1.2 Flash and Gemini Omni Flash 1.1?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty