Compare model

google / Video

GoogleGemini Omni 1.1 Flash

google/gemini-omni-1.1-flash

Video generation from a text prompt or an optional starting image, with model-generated audio.

Best for: Short AI video clips from text or images

ShareLinkedInX

Catalog status

Enabled

Research checked

2026-10-06

Benchmark results

1 reported results

Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.

1 of 1 results

Artificial Analysis AA-Video-T2V v2.0 Leaderboard (with audio)

Media · Third-party report

Test conditions and source

Listed on AA leaderboard as 'Gemini Omni Flash 1.1', matching the catalog's gemini-omni-1.1-flash (model code gemini-omni-1.1-flash); Elo 1113 on the v2.0 board — note AA has separate v1 (text-to-video) and v2.0 boards showing different scores (1238 on an older/alt table) for the same family; this entry uses the AA-Video-T2V v2.0 board figure, the most current as of check date. Published source text: AA-Video-T2V v2.0 leaderboard lists 'Gemini Omni Flash 1.1 | Elo 1113±9 (95% interval 1104-1122) | 8,493 samples | Aug 2026'.

Tested model: google/gemini-omni-1.1-flash

Artificial Analysis — AA-Video-T2V v2.0 Leaderboard · Checked 2026-10-06

1113Elo

Model specifications

Duration accepted by TokenRex

3–10 seconds (whole seconds)

Documented capability

Resolution accepted by TokenRex

360p, 720p, 1080p or 4K

Documented capability

Input and output modalities

Provider-reported formats; API compatibility is detailed below.

Input

Text
Image

Output

Video with audio
Exact model ID
google/gemini-omni-1.1-flash
Model type
Video
Duration accepted by TokenRex
3–10 seconds (whole seconds)
Resolution accepted by TokenRex
360p, 720p, 1080p or 4K
Default request
8 seconds at 720p
Audio control
Model-generated audio

Exact token limits are not published in the reviewed sources, so no estimated limits are shown.

Versions and thinking levels

One enabled version is currently listed for this model.

Gemini Omni 1.1 FlashSelected$0.10 per second

Features and tool support

TokenRex’s exposed interface, not every feature advertised by the provider. “Available” describes the implemented interface, not a successful test of every input or tool.

Input through TokenRex

Available

Text prompt (and optional start image) on POST /v1/videos.

Output through TokenRex

Available

A job id you check on /v1/videos/{id}; the finished MP4 downloads from /v1/videos/{id}/content.

Function tools

Not exposed

Video endpoint only — it creates videos and does not run tools.

Duration accepted by TokenRex

Limited

3–10 seconds (whole seconds)

Resolution accepted by TokenRex

Limited

360p, 720p, 1080p or 4K

Default request

Limited

8 seconds at 720p

Audio control

Limited

Model-generated audio

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (3)
  • These durations and resolutions are accepted by the TokenRex endpoint; they are not fresh generation measurements.
  • TokenRex does not expose provider video extension, reference-image arrays or first/last-frame controls.
  • Duration is rounded and clamped to 3–10 seconds. The Omni request does not forward generate_audio, seed or negative_prompt; do not assume Veo-specific controls apply.