Veo 3.1
The strongest general-purpose video model available through a stable API: 4K output, native audio, strong prompt adherence, and controls for character and style consistency, plus extension and seamless transitions for sequences longer than one clip. Google lists a retirement date of November 2026 or later, so track the successor.
Pricing checked against provider documentation on . How we verify
veo-3.1-generate-001 Price
$0.40
/ video sec
Context
—
not token-based
Max output
—
varies
Pricing caveat: 720p/1080p with audio included. Video-only routes run about $0.20/sec and 4K is priced separately. Clips are 4, 6, or 8 seconds; maximum 4 outputs per request.
Where Veo 3.1 fits
- Client-facing and broadcast-adjacent work
- 4K deliverables
- Character and style consistency across shots
- Longer sequences via extension
Specifications
- API model ID
- veo-3.1-generate-001
- Provider
- Model family
- Veo 3.1
- Released
- November 2025
- Knowledge cutoff
- —
- Context window
- —
- Max output
- —
- Native reasoning
- No
- Relative latency
- high
- Input modalities
- text, image
- Output modalities
- video, audio
- Open weights
- No
- Cached input
- —
- Batch discount
- —
Frequently asked
How much does Veo 3.1 cost?
Veo 3.1 is billed at $0.40 / video sec.
What is Veo 3.1's context window?
Context limits for Veo 3.1 depend on the input format rather than a token count.
Is Veo 3.1 a reasoning model?
No. Veo 3.1 answers directly without a native thinking phase, which keeps latency and cost predictable.
What is Veo 3.1 best for?
Best all-round generated video. The strongest general-purpose video model available through a stable API: 4K output, native audio, strong prompt adherence, and controls for character and style consistency, plus extension and seamless transitions for sequences longer than one clip. Google lists a retirement date of November 2026 or later, so track the successor.