Google · Text to video
Veo 3.1
Veo 3.1 is suited to cinematic realism, detailed scene direction and native sound that follows the action. Use it for story-driven B-roll, realistic product scenes or character moments where camera movement, ambience and dialogue contribute to the same shot. Describe the visual action and audio intention together, and use the selected route’s supported image guidance to anchor composition or subject appearance.
Generation mode
Text to video
Credit cost
30–255 credits
Observed generation time
Not enough public data
Release date
Dec 1, 2025
Current credit pricing
| Duration | Configuration | Credits |
|---|---|---|
| 0 seconds | veo3_1080p | 255 |
| 0 seconds | veo3_720p | 250 |
| 0 seconds | veo3_fast_1080p | 65 |
| 0 seconds | veo3_fast_4k | 180 |
| 0 seconds | veo3_fast_720p | 60 |
| 0 seconds | veo3_lite_1080p | 35 |
| 0 seconds | veo3_lite_4k | 150 |
| 0 seconds | veo3_lite_720p | 30 |
Availability and credit rows come from Flowctory's active production catalog. Observed time is shown only after at least five completed generations and is not a controlled benchmark. Model availability, limits, and costs can change.
Use model