Veo 3
Available google-deepmind/veo-3 · by Google DeepMind · Diffusion transformer (DiT)
Pricing — 1 offering(s)
Google DeepMind (Gemini API)
Standard
- $0.40 / second Current 2026-06-13 → present
Fast 720p
- $0.10 / second Current 2026-06-13 → present
Fast 4K
- $0.30 / second Current 2026-06-13 → present
Showing the active price and any recorded history. Full pricing history is available via the paid API — see API docs.
Capability profile
Prompt adherence strong
temporal consistency strong
motion quality strong
native audio strong
camera control moderate
Resolution ceiling strong
Inference speed moderate
clip duration ceiling moderate
Benchmarks
| Benchmark | Score | Config | Source |
|---|---|---|---|
| vbench | 87.2 | Approximate; verify against current leaderboard as scores may be updated. | leaderboard ↗ |
Operator guidance
First choice when native audio is required — no other major commercial API model matches Veo 3's audio quality as of mid-2026. Standard tier ($0.40/s) for premium output; Fast tier ($0.10–0.30/s) for cost-sensitive or latency-sensitive workflows. Choose Veo 2 if audio is not needed and cost matters more.
Use cases
- High-production video advertising with synchronized audio
- Cinematic pre-visualisation
- Social content requiring audio-visual sync
- 4K content production (via Fast 4K tier)
Limitations
- Standard tier ($0.40/s) is expensive for long clips
- Max 8 seconds per clip
- No explicit camera control API
- Free tier quota is limited; production use requires paid API plan