Veo 3.1 vs Sora 2
Preferred for text to video: Veo 3.1 · Newest: Veo 3.1 · Widest inputs: Veo 3.1. Quality scores are blind human-preference votes; specs and prices come from each lab’s listings.
Where they differ
Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.
- Preferred for text to videoVeo 3.1Veo 3.1 1,364 (#12) · Sora 2 1,343 (#17) — blind human votes
- NewestVeo 3.1Veo 3.1 Oct 15, 2025 · Sora 2 Oct 6, 2025
- Widest inputsVeo 3.1Veo 3.1: Text prompts, Reference images, Video · Sora 2: Text prompts, Reference images
- Native audioVeo 3.1Generates an audio track with the video: Veo 3.1 yes · Sora 2 no
- Image to videoBoth animate imagesStarts from an uploaded image: Veo 3.1 yes · Sora 2 yes
- Self-hostingNo open weightsBoth are available only through APIs and apps
- Most API hostsVeo 3.1Veo 3.1: 3 · Sora 2: 1
Every spec in one table
Dashes mean the data is not published.
| Specification |  Veo 3.1Google |  Sora 2OpenAI |
|---|---|---|
| Quality (blind human votes) | ||
| Text to video arenaElo-style score · higher is better | 1,364 ±14#12 of 48 · 13,741 votes (best) | 1,343 ±6#17 of 48 · 71,947 votes |
| Image to video arenaElo-style score · higher is better | 1,398 ±10#13 of 48 · 25,116 votes | — |
| Price | ||
| Starting price | $0.20/s 720p–1080p | — |
| Top price | $0.60/s 4K, with audio | — |
| 10-second clip | $2.00at the starting rate | — |
| How it is billed | Per second | — |
| Output | ||
| Produces | Video with sound | Video |
| Resolutions | 720p · 1080p · 4K | — |
| Highest resolution | 4K | — |
| Clip length | 4, 6 or 8 s | — |
| Longest clip | 8 s | — |
| Sound | Optional | — |
| Frame control | First and last frame | — |
| Aspect ratios | 16:9 · 9:16 | — |
| Inputs | ||
| Text prompts | Yes | Yes |
| Start image (image to video) | Yes | Yes |
| Video input | Yes | No |
| Audio input | No | No |
| Access | ||
| Weights | Proprietary | Proprietary |
| API hosts | 3 (best) | 1 |
| Released | Oct 15, 2025 | Oct 6, 2025 |
Which should you choose?
Which is better, Veo 3.1 or Sora 2?
For text to video, voters prefer Veo 3.1 (Veo 3.1 1,364 (#12) · Sora 2 1,343 (#17)). Arena scores come from blind, side-by-side human votes on the same prompts; when the gap is inside both models’ error margins we call it a tie. Test your own prompts before you commit.
Which is cheaper?
Veo 3.1 costs from $0.20/s (720p–1080p), up to $0.60/s (4K, with audio). A 10-second clip at the lowest rate: Veo 3.1 $2.00. Sora 2 has no published per-second price. Prices are list rates and change often; check the lab before budgeting.
How long can the videos be, and at what resolution?
Veo 3.1: 4, 6 or 8 s, 720p / 1080p / 4K; Sora 2: length not published.
What is the difference between Veo 3.1 and Sora 2?
Veo 3.1 is a video model from Google (Oct 15, 2025), taking text prompts, reference images and video and producing video with sound. Sora 2 is a video model from OpenAI (Oct 6, 2025), taking text prompts and reference images and producing video.
Which is newer?
Veo 3.1 Oct 15, 2025; Sora 2 Oct 6, 2025.
Which generates video with sound?
Generates an audio track with the video: Veo 3.1 yes; Sora 2 no.
Can I run any of these on my own hardware?
No open weights. Both are available only through APIs and apps.
Related comparisons
- Veo 3.1 vs Kling v2.6Kling AI · Dec 3, 2025
- Veo 3.1 vs Seedance v1.0 Pro FastByteDance Seed · Oct 24, 2025
- Veo 3.1 vs Wan v2.6Alibaba (Qwen) · Dec 16, 2025
- Sora 2 vs Wan v2.5 PreviewAlibaba (Qwen) · Sep 24, 2025
- Sora 2 vs Kling v2.6Kling AI · Dec 3, 2025
- Sora 2 vs Seedance v1.0 Pro FastByteDance Seed · Oct 24, 2025
