google / Video
Veo 3.1 Lite
google/veo-3.1-liteVideo generation from a text prompt or an optional starting image, with model-generated audio.
Best for: Short AI video clips from text or images
Catalog status
Enabled
Research checked
2026-10-06
Benchmark results
Results are source-attributed, not TokenRex measurements. Different tests and thinking variants are not interchangeable.
1 of 1 results
AA-Video-T2V v2.0 (with audio)
Video · Third-party report
Test conditions and source
Freshly fetched overall with-audio v2.0 table, pairwise human preference Elo, 95% interval ±10. Arena revision and vote counts change; not an API availability or latency test.
Tested model: google/veo-3.1-lite
Artificial Analysis · Text-to-Video Arena · Checked 2026-10-06
Model specifications
Duration accepted by TokenRex
4, 6 or 8 seconds
Documented capability
Resolution accepted by TokenRex
720p or 1080p
Documented capability
Input and output modalities
Provider-reported formats; API compatibility is detailed below.
Input
Output
- Exact model ID
- google/veo-3.1-lite
- Model type
- Video
- Duration accepted by TokenRex
- 4, 6 or 8 seconds
- Resolution accepted by TokenRex
- 720p or 1080p
- Default request
- 8 seconds at 720p
- Audio control
- Enabled by default; generate_audio can disable it
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.
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
AvailableText prompt (and optional start image) on POST /v1/videos.
Output through TokenRex
AvailableA job id you check on /v1/videos/{id}; the finished MP4 downloads from /v1/videos/{id}/content.
Function tools
Not exposedVideo endpoint only — it creates videos and does not run tools.
Duration accepted by TokenRex
Limited4, 6 or 8 seconds
Resolution accepted by TokenRex
Limited720p or 1080p
Default request
Limited8 seconds at 720p
Audio control
LimitedEnabled by default; generate_audio can disable it
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.
- Lovable AI: video generation
Vendor-reported
Last checked - Google: Veo video generation
Vendor-reported
Last checked - Artificial Analysis · Text-to-Video Arena
Third-party report
Last checked
Research notes (4)
- 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.
- TokenRex’s endpoint requires 8 seconds for 1080p and 4K; this is its validation rule, not a claim about every upstream interface. Unsupported duration values are normalized to 8 seconds.
- 4K requests are rejected for Veo 3.1 Lite.