Which should you pick?
Kling O3 Standard Reference to Video is the cheaper job: 56-168 credits against 160-320 credits for VEO 3.1 Reference to Video. Those are the credits one complete generation costs, not a headline rate, so they are directly comparable even though the two models bill differently.
At their most expensive settings the gap widens: VEO 3.1 Reference to Video tops out at 320 credits a job versus 168, driven by audio options.
Kling O3 Standard Reference to Video supports more aspect ratios (3: 16:9, 9:16, 1:1), giving it more format flexibility.
What a job costs
VEO 3.1 Reference to Video
160-320 credits
It bills by whether audio is generated, and the price moves with audio options.
- Audio off20 credits
- Audio on40 credits
Kling O3 Standard Reference to Video
56-168 credits
It bills a base charge plus a per-second rate, and the price moves with clip length.
- First 5s56 credits
- Each extra second12 credits
All figures are Versely credits. Your plan's credit allowance is on the pricing page.
Spec comparison
| Spec | VEO 3.1 Reference to Video | Kling O3 Standard Reference to Video |
|---|---|---|
| Provider | Kling | |
| Cost per job | 160-320 credits | 56-168 credits |
| Billing | by whether audio is generated | a base charge plus a per-second rate |
| Max resolution | 4K | — |
| Aspect ratios | 16:9, 9:16 | 16:9, 9:16, 1:1 |
| Durations | 8s | 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s |
| Frame rates | — | — |
| Qualities | 720p, 1080p, 4K | — |
| Requires starting image | Yes | Yes |
| Accepts video input | No | No |
| Reference images | — | — |
| Leaderboard | Unranked | Unranked |
| Released | Oct 15, 2025 | Feb 5, 2026 |
What each one does that the other doesn't
Only VEO 3.1 Reference to Video
cinematic, audio, premium
Only Kling O3 Standard Reference to Video
character consistency
Both list: reference to video, reference to video.
Full VEO 3.1 Reference to Video spec sheet →
Google VEO 3.1 reference-to-video — generate an 8s cinematic clip whose subjects match up to 3 reference images, with native audio.
Full Kling O3 Standard Reference to Video spec sheet →
Kling O3 Standard reference-to-video for character-consistent generation
More comparisons
Frequently asked questions
Which is cheaper, VEO 3.1 Reference to Video or Kling O3 Standard Reference to Video?+
Kling O3 Standard Reference to Video is cheaper per job: 56-168 credits against 160-320 credits for VEO 3.1 Reference to Video.
What can VEO 3.1 Reference to Video do that Kling O3 Standard Reference to Video can't, or vice versa?+
Only VEO 3.1 Reference to Video lists cinematic, audio, premium. Only Kling O3 Standard Reference to Video lists character consistency. Both list reference to video, reference to video.
How do VEO 3.1 Reference to Video and Kling O3 Standard Reference to Video bill?+
VEO 3.1 Reference to Video bills by whether audio is generated, and its price moves with audio options. Kling O3 Standard Reference to Video bills a base charge plus a per-second rate, and its price moves with clip length. Both are charged in Versely credits.
How long a clip can VEO 3.1 Reference to Video and Kling O3 Standard Reference to Video generate?+
VEO 3.1 Reference to Video supports 8s; Kling O3 Standard Reference to Video supports 3s, 4s, 5s, 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s.
Try both inside Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.