GoogleVideo model
Gemini Omni 1.1 Flash
In text to video, Gemini Omni 1.1 Flash is in place 1 of 23, with image to video in place 2. A 5 s clip costs about $0.51.
1,488Arena ratinglevel with MiniMax H3
1,516Arena ratinglevel with FLUX.3 Video
$0.51$0.10 per secondlower is better
10slongest single cliphigher is better
33out of 100same as last month
Summary
At $0.10 per second of video it is fairly cheap; a typical video model costs $0.12.
New in Gemini Omni 1.1 Flash are the stable Omni video API and the documented succession to Gemini Omni Flash. Text, images, and videos up to 10 seconds feed generation, editing, or extension. Output ranges from 3 to 10 seconds, 360p through 4K, at 24 frames per second.
The context window is 1,048,576 tokens. Google lists access on the paid API tier with no free tier, while the predecessor’s preview identifier is discontinued.
Gemini Omni 1.1 Flash benchmarks
Image to video arena
How people rate generated videos in blind comparisons, Elo points · higher is better
20 of 21 models
as of September 22, 2026 · Source: LMArena
Text to video arena
How people rate generated videos in blind comparisons, Elo points · higher is better
20 of 23 models
as of September 22, 2026 · Source: LMArena
Show all 46 individual results from 15 sources
Page 1 of 4
Published benchmarks
LMArena Text to Video
Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.
higher is betterAs of November 5, 2026Scale: 0 Elo - 1,516 Elo
Methodology and context
- Metric
- elo-rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 23
- Sample
- 1,784
LMArena Image to Video
Elo ratings summarize pairwise comparisons within this leaderboard. They are not percentages. The scale does not express absolute quality or linear gaps between models.
higher is betterAs of November 5, 2026Scale: 0 Elo - 1,495 Elo
Methodology and context
- Metric
- elo-rating
- Scale
- No upper bound is documented. The chart spans the recorded values and zero.
- Participants
- 21
- Sample
- 3,734
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
AA Video Arena Elo (Show measurement, test conditions, and source)
- Source value
- 1132
- Score
- 1132
- Metric
- pairwise human-preference Elo
- Unit
- elo
- Benchmark version
- AA-Video-T2V v2.1
- Category
- text-to-video
- Direction
- Higher is better
- Sample
- 6302
- Confidence interval
- 15
- Lower confidence bound
- 1117
- Upper confidence bound
- 1147
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis AA-Video-T2V v2.1
- Status
- superseded
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Text-to-video with audio; exact source row Gemini Omni Flash 1.1.
- Context
- The published comparison includes audio; it is not a silent-video-only score.
AA Video Arena Elo (Show measurement, test conditions, and source)
- Source value
- 1134
- Score
- 1134
- Metric
- pairwise human-preference Elo
- Unit
- elo
- Benchmark version
- AA-Video-I2V v1.1
- Category
- image-to-video
- Direction
- Higher is better
- Sample
- 3176
- Confidence interval
- 17
- Lower confidence bound
- 1117
- Upper confidence bound
- 1151
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis AA-Video-I2V v1.1
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Independent evaluation. Image-to-video with audio; exact source row Gemini Omni Flash 1.1.
- Context
- The published comparison includes audio; it is not a silent-video-only score.
Physics-IQ Verified leaderboard score (Show measurement, test conditions, and source)
- Source value
- 35.34
- Score
- 35.34
- Metric
- Physics-IQ Verified physical-understanding score on a 0-100 point scale
- Unit
- points
- Benchmark version
- Physics-IQ Verified leaderboard
- Category
- image-to-video
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- Physics-IQ Verified GitHub leaderboard
- Status
- active
- Retrieved at
- 2026-10-16
- Methodology
- Official benchmark leaderboard. Image-to-video (I2V); unmarked entry uses the model-specific best-practice prompt template. The leaderboard row does not disclose output resolution, duration, or a per-model sample count.
- Context
- This measures physical understanding on a 0-100 point scale, not general video quality. The benchmark paper does not evaluate this newer model, so no generation controls are imported from it. The leaderboard displays ± notation; no confidence interval or row-specific run count is inferred.
AA Video Arena Elo (Show measurement, test conditions, and source)
- Source value
- 1132
- Score
- 1132
- Metric
- pairwise human-preference Elo
- Unit
- elo
- Benchmark version
- AA-Video-I2V v1.1, snapshot 2026-10-17
- Category
- image-to-video
- Direction
- Higher is better
- Sample
- 3368
- Confidence interval
- 17
- Lower confidence bound
- 1115
- Upper confidence bound
- 1149
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis AA-Video-I2V v1.1
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Image-to-video with audio; exact source row "Gemini Omni Flash 1.1"; output resolution not reported.
- Context
- Point-in-time Elo snapshot from AA-Video-I2V v1.1; the displayed sample count is the model row's appearances, not a prompt count. Output resolution is not reported.
AA-Video-Editing Elo, with audio (Show measurement, test conditions, and source)
- Source value
- 1149
- Score
- 1149
- Metric
- Elo from pairwise human preference votes
- Unit
- elo
- Benchmark version
- AA-Video-Editing v1.1, with audio; page snapshot 2026-10-17
- Category
- video-editing
- Direction
- Higher is better
- Sample
- 6778
- Confidence interval
- 11
- Lower confidence bound
- 1138
- Upper confidence bound
- 1160
- Source type
- official-leaderboard
- Evaluator
- Artificial Analysis AA-Video-Editing v1.1
- Status
- superseded
- Retrieved at
- 2026-10-17
- Methodology
- Official benchmark leaderboard. Exact board label Gemini Omni Flash 1.1. AA-Video-Editing ranks video models editing an input video from a text instruction, with audio kept, by Elo from pairwise human preference votes. The source reports 6,778 samples and the displayed 95% interval. Some prompts were declined by copyright and safety filters; the row reflects the remaining prompts. The board does not give a per-model serving revision or test resolution.
- Context
- This is an editing benchmark, not text-to-video or image-to-video generation. AA does not publish the per-model serving revision or test resolution. The reported score excludes prompts declined by the model's copyright and safety filters.
Rapidata Physics Benchmark overall pairwise Elo (Show measurement, test conditions, and source)
- Source value
- 1346
- Score
- 1346
- Metric
- equal-weight mean of two Bradley–Terry/Elo human-preference leaderboard scores
- Unit
- elo
- Benchmark version
- Rapidata Physics Benchmark, README source commit 5f99e9587b9d04017e8d3effe682af2385f78061
- Category
- video
- Direction
- Higher is better
- Confidence interval
- 27
- Source type
- independent-evaluator
- Evaluator
- Rapidata, image-to-video-physics-human-feedback-benchmark dataset README
- Status
- superseded
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. One participant named by the dataset per model. On 65 Physics-IQ scenes, each model receives a switch-frame image and a human-written scene description and generates four approximately five-second image-to-video clips per scene. Human raters compare same-scene clips and answer which looks more realistic, either blind or with the real continuation visible. The overall row equally averages the two leaderboard fits. The README names no exact provider API route, serving revision, quantization, or output resolution. Dataset row: Gemini Omni 1.1 Flash. Leaderboard condition: overall.
- Context
- The README explicitly defines ± as a 95% confidence interval; its half-width is stored. No sampleCount is assigned: 65 scenes, approximately 260 generated clips per model, 21,125 pairwise rows in the pinned README, and 282,698 total votes describe the study or corpus, not the effective denominator of a model-specific Bradley–Terry fit. Current Hugging Face viewer metadata reports 22,625 rows, which conflicts with the pinned README; the discrepancy is unresolved and neither count is used as N. Overall, with-reference, and blind are projections of the same study and overlapping vote pool, not independent studies. Exact serving revision and resolution are not published.
Rapidata Physics Benchmark with-reference pairwise Elo (Show measurement, test conditions, and source)
- Source value
- 1366
- Score
- 1366
- Metric
- Bradley–Terry/Elo human-preference score, with-reference leaderboard
- Unit
- elo
- Benchmark version
- Rapidata Physics Benchmark, README source commit 5f99e9587b9d04017e8d3effe682af2385f78061
- Category
- video
- Direction
- Higher is better
- Confidence interval
- 39
- Source type
- independent-evaluator
- Evaluator
- Rapidata, image-to-video-physics-human-feedback-benchmark dataset README
- Status
- superseded
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. One participant named by the dataset per model. On 65 Physics-IQ scenes, each model receives a switch-frame image and a human-written scene description and generates four approximately five-second image-to-video clips per scene. Human raters compare same-scene clips and answer which looks more realistic, either blind or with the real continuation visible. The overall row equally averages the two leaderboard fits. The README names no exact provider API route, serving revision, quantization, or output resolution. Dataset row: Gemini Omni 1.1 Flash. Leaderboard condition: with-reference.
- Context
- The README explicitly defines ± as a 95% confidence interval; its half-width is stored. No sampleCount is assigned: 65 scenes, approximately 260 generated clips per model, 21,125 pairwise rows in the pinned README, and 282,698 total votes describe the study or corpus, not the effective denominator of a model-specific Bradley–Terry fit. Current Hugging Face viewer metadata reports 22,625 rows, which conflicts with the pinned README; the discrepancy is unresolved and neither count is used as N. Overall, with-reference, and blind are projections of the same study and overlapping vote pool, not independent studies. Exact serving revision and resolution are not published.
Rapidata Physics Benchmark blind pairwise Elo (Show measurement, test conditions, and source)
- Source value
- 1325
- Score
- 1325
- Metric
- Bradley–Terry/Elo human-preference score, blind leaderboard
- Unit
- elo
- Benchmark version
- Rapidata Physics Benchmark, README source commit 5f99e9587b9d04017e8d3effe682af2385f78061
- Category
- video
- Direction
- Higher is better
- Confidence interval
- 38
- Source type
- independent-evaluator
- Evaluator
- Rapidata, image-to-video-physics-human-feedback-benchmark dataset README
- Status
- superseded
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. One participant named by the dataset per model. On 65 Physics-IQ scenes, each model receives a switch-frame image and a human-written scene description and generates four approximately five-second image-to-video clips per scene. Human raters compare same-scene clips and answer which looks more realistic, either blind or with the real continuation visible. The overall row equally averages the two leaderboard fits. The README names no exact provider API route, serving revision, quantization, or output resolution. Dataset row: Gemini Omni 1.1 Flash. Leaderboard condition: blind.
- Context
- The README explicitly defines ± as a 95% confidence interval; its half-width is stored. No sampleCount is assigned: 65 scenes, approximately 260 generated clips per model, 21,125 pairwise rows in the pinned README, and 282,698 total votes describe the study or corpus, not the effective denominator of a model-specific Bradley–Terry fit. Current Hugging Face viewer metadata reports 22,625 rows, which conflicts with the pinned README; the discrepancy is unresolved and neither count is used as N. Overall, with-reference, and blind are projections of the same study and overlapping vote pool, not independent studies. Exact serving revision and resolution are not published.
Megaton V-Benchmark C01 Prompt Adherence (Show measurement, test conditions, and source)
- Source value
- 88.6
- Score
- 88.6
- Metric
- Category score on Megaton's 0-100 scale
- Unit
- points
- Benchmark version
- V-Benchmark v2.3.0; report publication 1.6.0
- Category
- video-generation:prompt-adherence
- Direction
- Higher is better
- Sample
- 36
- Source type
- independent-evaluator
- Evaluator
- Megaton, Gemini Omni 1.1 Flash V-Benchmark v2 report
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Named model: Gemini Omni 1.1 Flash; the report says generated via Google and evaluated August 28, 2026. Megaton V-Benchmark v2.3.0, report publication 1.6.0 dated October 2, 2026. Text-to-video methodology specifies 480p and 5 seconds; any closest-supported deviation is said to be noted, but this public report does not state a model-specific exception. Category C01 Prompt Adherence (20% publication weight); 36 videos were rated for this category. The report does not identify an exact Google API model ID or serving revision.
- Context
- The public report gives the number of videos rated for this category but does not expose prompt-level data or a category-specific confidence interval. The methodology's ±2 value is an empirical comparison for the combined index and is expressly not a universal statistical confidence interval; it is not transferred to this category. The exact evaluated Google API model ID and serving revision are not public.
Megaton V-Benchmark C02 Scene Consistency (Show measurement, test conditions, and source)
- Source value
- 88.56
- Score
- 88.56
- Metric
- Category score on Megaton's 0-100 scale
- Unit
- points
- Benchmark version
- V-Benchmark v2.3.0; report publication 1.6.0
- Category
- video-generation:scene-consistency
- Direction
- Higher is better
- Sample
- 36
- Source type
- independent-evaluator
- Evaluator
- Megaton, Gemini Omni 1.1 Flash V-Benchmark v2 report
- Status
- active
- Retrieved at
- 2026-10-17
- Methodology
- Independent evaluation. Named model: Gemini Omni 1.1 Flash; the report says generated via Google and evaluated August 28, 2026. Megaton V-Benchmark v2.3.0, report publication 1.6.0 dated October 2, 2026. Text-to-video methodology specifies 480p and 5 seconds; any closest-supported deviation is said to be noted, but this public report does not state a model-specific exception. Category C02 Scene Consistency (10% publication weight); 36 videos were rated for this category. The report does not identify an exact Google API model ID or serving revision.
- Context
- The public report gives the number of videos rated for this category but does not expose prompt-level data or a category-specific confidence interval. The methodology's ±2 value is an empirical comparison for the combined index and is expressly not a universal statistical confidence interval; it is not transferred to this category. The exact evaluated Google API model ID and serving revision are not public.
Recorded measurement details
LMArena Text to Video: LMArena Text to Video (Show measurement, test conditions, and source)
- Source value
- 1516
- Score
- 1516
- Metric
- elo-rating
- Unit
- Elo
- Task
- lmarena-text-to-video
- Task label
- LMArena Text to Video
- Direction
- Higher is better
- Source rank
- 1
- Sample
- 1784
- Lower confidence bound
- 1501
- Upper confidence bound
- 1531
- Retrieved at
- 2026-11-05
LMArena Image to Video: LMArena Image to Video (Show measurement, test conditions, and source)
- Source value
- 1488
- Score
- 1488
- Metric
- elo-rating
- Unit
- Elo
- Task
- lmarena-image-to-video
- Task label
- LMArena Image to Video
- Direction
- Higher is better
- Source rank
- 2
- Sample
- 3734
- Lower confidence bound
- 1477
- Upper confidence bound
- 1499
- Retrieved at
- 2026-11-05
Page 1 of 4
Video sample from our test
This video exists as a documented run for the exact model version. Playback is muted.
Motion and physical consistency
This sample tests Anatomy, object consistency, camera tracking, rain, and reflections.
Prompt and settings
Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.
Generated through Gemini API with model gemini-omni-1.1-flash. Archived settings were 16:9, one request, first output, prompt motion-and-physics, duration not controllable (prompt asks for five seconds), native audio (no switch), interaction v1_ChdDUFBtYXFYRUctS192ZElQMzk2MjZRaxIXQ1BQbWFxWEVHLUtfdmRJUDM5NjI2UWs, request {"model":"gemini-omni-1.1-flash","input":"Generate exactly one continuous five-second 16:9 cinematic video. A fictional bicycle courier in a mustard-yellow raincoat rides a red city bicycle from left to right across a rain-wet Hamburg street at blue hour for the entire clip. The camera tracks her smoothly at waist height. Both hands remain visible on the handlebars, the bicycle geometry stays physically correct, and a transparent umbrella fixed to the bicycle moves naturally in the wind. Wet-street reflections and raindrops follow realistic physics. No cuts, no slow motion, no text, no logos, no subtitles, and no audio.","response_format":{"type":"video","aspect_ratio":"16:9","resolution":"720p","delivery":"uri"},"store":true,"background":false,"stream":false}, configured price ceiling $1.06, usage {"total_tokens":29437,"total_input_tokens":118,"input_tokens_by_modality":[{"modality":"text","tokens":118}],"total_cached_tokens":0,"total_output_tokens":28960,"output_tokens_by_modality":[{"modality":"video","tokens":28960}],"total_tool_use_tokens":0,"total_thought_tokens":359,"initial_input_tokens":29396}.
Popularity compared
How often the model is searched for, used and mentioned, compared with every model of its category.
Popularity index
0 to 100, higher is more popular
20 of 98 models
As of November 2026 · Source: gradually.ai popularity index
Over time
Weekly values from October 18, 2026 to November 5, 2026
Gemini Omni 1.1 FlashVidu Q3 ProVeo 3.1 FastWan 2.7Dreamina Seedance 2.0 720p
Gemini Omni 1.1 Flash compared
Compare with another model
Predecessor and successor
The most popular comparisons
- 1FLUX.3 Video vs. Gemini Omni 1.1 Flash
- 2Dreamina Seedance 2.5 720p vs. Gemini Omni 1.1 Flash
- 3Dreamina Seedance 2.0 720p vs. Gemini Omni 1.1 Flash
- 4MiniMax H3 vs. Gemini Omni 1.1 Flash
- 5Sora 2 Pro vs. Gemini Omni 1.1 Flash
- 6Sora 2 vs. Gemini Omni 1.1 Flash
- 7Veo 3.1 vs. Gemini Omni 1.1 Flash
- 8Veo 3.1 Fast vs. Gemini Omni 1.1 Flash
- 9Grok Imagine Video 1.5 vs. Gemini Omni 1.1 Flash
Show all 47 comparisons
- 10Grok Imagine Video vs. Gemini Omni 1.1 Flash
- 11Wan 2.7 vs. Gemini Omni 1.1 Flash
- 12Wan 2.6 vs. Gemini Omni 1.1 Flash
- 13Runway Gen-4.5 vs. Gemini Omni 1.1 Flash
- 14Kling 3.0 Pro vs. Gemini Omni 1.1 Flash
- 15Kling 2.6 Pro vs. Gemini Omni 1.1 Flash
- 16Vidu Q3 Pro vs. Gemini Omni 1.1 Flash
- 17PixVerse V5.6 vs. Gemini Omni 1.1 Flash
- 18Hailuo 2.3 vs. Gemini Omni 1.1 Flash
- 19LTX-2 19B vs. Gemini Omni 1.1 Flash
- 20Wan 2.2 A14B vs. Gemini Omni 1.1 Flash
- 21HunyuanVideo 1.5 vs. Gemini Omni 1.1 Flash
- 22Pika 2.2 vs. Gemini Omni 1.1 Flash
- 23Gemini Omni 1.1 Flash vs. Muse Video
- 24Gemini Omni 1.1 Flash vs. Wan 3.0
- 25Gemini Omni 1.1 Flash vs. Wan 3.0 Prime
- 26Gemini Omni 1.1 Flash vs. HappyHorse 1.0
- 27Gemini Omni 1.1 Flash vs. HappyHorse 1.1
- 28Gemini Omni 1.1 Flash vs. PixVerse V6
- 29Gemini Omni 1.1 Flash vs. PixVerse C1
- 30Gemini Omni 1.1 Flash vs. Seedance 2.0 Fast
- 31Gemini Omni 1.1 Flash vs. Seedance 2.0 Mini
- 32Gemini Omni 1.1 Flash vs. Vidu Q3 Turbo
- 33Gemini Omni 1.1 Flash vs. Vidu Q2
- 34Gemini Omni 1.1 Flash vs. Vidu Q1
- 35Gemini Omni 1.1 Flash vs. Kling 4.0
- 36Gemini Omni 1.1 Flash vs. Kling 3.0 Standard API
- 37Gemini Omni 1.1 Flash vs. Kling Video O1
- 38Gemini Omni 1.1 Flash vs. Hailuo 2.3 Fast
- 39Gemini Omni 1.1 Flash vs. Wan 2.5 Preview
- 40Gemini Omni 1.1 Flash vs. Wan 2.6 I2V Flash
- 41Gemini Omni 1.1 Flash vs. Wan 2.2 TI2V 5B
- 42Gemini Omni 1.1 Flash vs. Wan 2.2 I2V A14B
- 43Gemini Omni 1.1 Flash vs. HunyuanVideo 1.0 T2V
- 44Gemini Omni 1.1 Flash vs. HunyuanVideo I2V 1.0
- 45Gemini Omni 1.1 Flash vs. Ray 3.2
- 46Gemini Omni 1.1 Flash vs. Grok Imagine Video 1.5 Lite
- 47Gemini Omni 1.1 Flash vs. LTX-2.5
All specifications
Input and output
- Context window
- 1,048,576 tokens
- no source
Watermarking and provenance
AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.
- AI watermarking
- Subject to limitations. Google describes an invisible SynthID watermark for videos in Gemini Apps. Marking may depend on the product used.
- Source 1: AI watermarkingSource 2: AI watermarking
- Visible watermark
- In Gemini Apps, a visible mark may appear depending on the setting, country and plan.
- Source: Visible watermark
- Provenance metadata
- Google documents C2PA Content Credentials for content in Gemini Apps, Google Flow and YouTube.
- Source: Provenance metadata
- Labelling reviewed
- Nov 5, 2026
- Source 1: Labelling reviewedSource 2: Labelling reviewedSource 3: Labelling reviewed
Licence and access
API
Further details
- Video capabilities
- Generation, natural-language editing, extension, upscaling, and interpolation
- Source: Video capabilities
Prices
At Google from €4.99 a month (Google AI Plus, with limited credits). Through other providers from €6.83 a month (Poe Basic, with limited points). 27 plans in Germany.
| Plan | Monthly price | Note |
|---|---|---|
| Google AI Plus | €4.99 | developer's own plan, with limited credit |
| Google AI Pro | €21.99 | developer's own plan, with limited credit |
| Google AI Ultra 5x | €99.99 | developer's own plan, with limited credit |
| Google AI Ultra 20x | €219.99 | developer's own plan, with limited credit |
| Lovable Free | free | with limited credit |
| Poe Basic | €6.83 | with limited credit |
| Pika Starter | ≈ €10.60 | with limited credit |
| Lovable Pro | €25 | with limited credit |
| Leonardo.Ai Team Starter | ≈ €25.45 | for teams, per seat |
| Poe Plus | €27.36 | with limited credit |
| Pika Creator | ≈ €37.11 | with limited credit |
| Lovable Business | €50 | with limited credit, for teams |
| Leonardo.Ai Team Growth | ≈ €50.89 | for teams, per seat |
| Mindverse Studio Team | €58.31 | for teams, per seat |
| Leonardo.Ai Ultimate | ≈ €63.61 | |
| Poe Pro | €68.41 | with limited credit |
| Higgsfield Plus | €70.21 | with limited credit |
| Mindverse Studio Pro | €70.21 | per seat |
| Higgsfield Team | €94.01 | with limited credit, for teams, per seat |
| Pika Fancy | ≈ €100.72 | with limited credit |
| Poe Advanced | €136.84 | with limited credit |
| Higgsfield Ultra | €153.51 | with limited credit |
| Higgsfield Scale | €201.11 | with limited credit, for teams, per seat |
| Poe Max | €342.11 | with limited credit |
| Higgsfield Enterprise | n/a | for enterprises |
| Lovable Enterprise | n/a | for enterprises |
| Pika Enterprise | n/a | for enterprises |
Frequently asked questions about Gemini Omni 1.1 Flash
How good is Gemini Omni 1.1 Flash?
Rank 1 of 23 in the text-to-video arena rating. With a start image: rank 2 of 21.
LMArena, as of Sep 22, 2026
How much does a video with Gemini Omni 1.1 Flash cost?
About $0.51 for a 5 s clip, $0.10 per second of video. That is fairly cheap.
How long can a video with Gemini Omni 1.1 Flash be?
Up to 10 seconds in one go. Resolution: 360p to 4K (24 FPS).
According to Google
- Price
- $0.10 per second$0.51 per 5 s clip
- Longest clip
- 10s
- Resolution
- 360p to 4K (24 FPS)
- Audio
- yes, generated natively
- Open weights
- no
Where can I use Gemini Omni 1.1 Flash?
At Google with a subscription from €4.99 a month. Including other providers that makes 27 plans in Germany.
Subscription comparison, prices in Germany incl. VAT
At Google
4 plans, from €4.99 a month (Google AI Plus).
Through other providers
23 plans from 6 providers, from €6.83 a month (Poe Basic), with limited credits.
Sources and data date
Show all 35 sources
Benchmark sources at a glance
Which independent evaluators tested this model. This is coverage, not a quality ranking.
| Evaluator | Test series | Composite indices | Recorded active measurements |
|---|---|---|---|
| Artificial Analysis | 0 | 0 | 5 |
| LMArena | 0 | 0 | 2 |
Without vendor claims and historical or disputed results; those stay labelled in the single values. 7 measurements are not yet assigned to a test series.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 16, 2026. 26 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | wiro-video-models-exact-row Note The inspected Wiro leaderboard has no exact model-version route. Nearby variants were not transferred. |
| Not found in the inspected sources | arena-video-edit-exact-row Note The inspected Video Edit table has no exact model-version row. T2V and I2V values were not reused. |
| Not found in the inspected sources | vabench-exact-model-row Note VABench has no exact model row. Sora 2 was not transferred to Sora 2 Pro or other models. |
| Unresolved | vbench-current-public-leaderboard Note The current VBench leaderboard is embedded in a dynamic Hugging Face iframe and was not retrievable; current scores remain unresolved. |
| Not found in the inspected sources | vidbenchmark-exact-row Note No exact model id is present in the 2026-08-04 dataset; similarly named variants were not transferred. |
| Not published | AA output resolution Note The AA-Video leaderboard row does not publish the tested output resolution. |
| Not published | servingRevision Original wording The dataset identifies the participant name but not provider API route, served checkpoint revision, quantization, or resolution. |
| Unresolved | datasetRowCount Original wording The pinned README states 21,125 matchup rows, while current Hugging Face viewer metadata reports 22,625. Neither aggregate is used as sampleCount or leaderboard N. |
| Unresolved | per-model-sample-count Original wording The returned row text contains an ambiguous count under headings that include both Responses and Matches. Per-model N is not copied. Aggregate votes and pairwise-match totals are not substituted. |
| Not published | provider-serving-revision Original wording The page names a model label but does not state an exact provider serving revision or checkpoint. |
| Unresolved | benchmark-update-date Original wording The page header says updated 2026-09-03 while the footer says last updated 2026-10-18. |
| Additional source | Google (retrieved September 26, 2026) · Google Gemini Omni Flash model documentation · Editorial description reviewed October 2, 2026 |
| Additional source | Video pricing (retrieved September 26, 2026) · Google Gemini API pricing · Editorial description reviewed October 2, 2026 |
| Additional source | Lifecycle data · Google Gemini API release notes · Editorial description reviewed October 2, 2026 |
| Additional source | LMArena (retrieved November 5, 2026)12 |
| Additional source | Artificial Analysis AA-Video-T2V v2.1 (retrieved October 16, 2026; October 17, 2026; October 28, 2026) |
| Additional source | Artificial Analysis AA-Video-I2V v1.1 (retrieved October 16, 2026; October 17, 2026; October 28, 2026) |
| Additional source | Physics-IQ Verified GitHub leaderboard (retrieved October 16, 2026) |
| Additional source | Artificial Analysis AA-Video-Editing v1.1 (retrieved October 17, 2026; October 28, 2026) |
| Additional source | Rapidata, image-to-video-physics-human-feedback-benchmark dataset README (retrieved October 17, 2026) |
| Additional source | Megaton, Gemini Omni 1.1 Flash V-Benchmark v2 report (retrieved October 17, 2026) |
| Additional source | Rapidata (retrieved October 18, 2026; October 28, 2026) |
| Additional source | Arena Video Image-to-Video (retrieved September 21, 2026; October 16, 2026; October 28, 2026) |
| Additional source | Arena Video Text-to-Video (retrieved September 21, 2026; October 16, 2026; October 28, 2026) |
| Additional source | Definition AI Video Leaderboard (retrieved October 21, 2026; October 28, 2026) |
| Additional source | Rapidata I2V Physics benchmark (retrieved October 22, 2026; October 28, 2026) |
| Additional source | Rapidata I2V Realism benchmark (retrieved October 22, 2026; October 28, 2026) |
| Additional source | Rapidata Relative Camera Movement (retrieved October 28, 2026) |
| Additional source | Model metadata (retrieved October 16, 2026)1234 |
| Additional source | Model metadata (retrieved October 17, 2026) |
| Additional source | Model metadata (retrieved October 18, 2026) |
| Additional source | Model metadata (retrieved October 28, 2026) |
| Additional source | Gemini Omni video generation (retrieved November 5, 2026) |
| Additional source | Google DeepMind Gemini Omni (retrieved November 5, 2026) |
| Additional source | Gemini Apps watermark settings (retrieved November 5, 2026) |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Ollama: cumulative downloads for the popularity index |
| Additional source | Replicate: cumulative runs for the popularity index |
| Additional source | Google Trending Now: limited feed selection for Germany and the US |
| Additional source | Creative Commons Attribution 4.0 |
| Additional source | Google Gemini API model deprecations and lifecycle table (2026-09-19) |