Text-to-video · audio evaluated · all categories
95% CI 947.6–981.6 · n=3,985
googleReleased Jan 30, 2026
veo-3.1-fast
Veo 3.1 is the latest text-to-video model from Google that generates high-fidelity, cinematic videos with synchronized audio from a simple text prompt. It excels at creating realistic and imaginative scenes with a deep understanding of natural language and visual dynamics.
Measured performance
All leaderboards ↗Benchmark results
Text-to-video · silent evaluation · all categories
95% CI 942.29–978.29 · n=3,766
Access & cost
1 quotePrices across providers
DeepInfra
Output video second; base configuration
- Rate
- $0.15
Model specifications
- Developer
- Modality
- Video
- Context
- Not reported
- Maximum output
- Not reported
- Weights
- Not reported
- Released
- Jan 30, 2026
- Provider listed
- Oct 16, 2025
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
google/veo-3.1-fast - deepinfra
google/veo-3.1-fast - aa-video
f3c7e331-2b60-4f87-bc9c-363264f211a8
Sources
Updated Oct 18, 2026
More from google
View all ↗googleReleased Aug 28
Gemini Omni Flash 1.1 Text to Video
Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint generates video with synchronized native audio from a text prompt, grounded in Gemini's real-world knowledge and physics…
Price not listed
googleListed Aug 25
Gemini Omni Flash 1.1 Edit
Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint edits video through natural-language instruction, applying the requested change while preserving the parts of the scene you want kept,…
No reported score
No reported score
Price not listed
googleListed Aug 25
Gemini Omni Flash 1.1 Reference to Video
Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint generates video from combined multimodal references, images, videos and text together. Reasoning across all inputs to produce a single…
No reported score
No reported score
Price not listed
googleListed Aug 25
Gemini Omni Flash 1.1 Image to Video
Gemini Omni Flash 1.1 is Google's multimodal video model. This endpoint animates a still image into video with synchronized audio, extending a single frame into coherent motion that reflects the logic of…
No reported score
No reported score
Price not listed