Video · Alibaba

Wan 3.0

Alibaba's August 2026 model, up to 30 s per clip with sound. Pick it for long shots at a mid-range price.

Anonymized Moderate cost
Latest versionWan 3.0August 24, 2026
Artificial Analysis Image to Video Arena1,164 Elo#3 of 22 on Artificial Analysis Image to Video Arena
Price$0.117 per second of video$0.585 a 5 s clip
Key specClips up to 30 s, with sound

What sets it apart

Wan 3.0 is Alibaba's closed-weights flagship: up to 30 s at 1080p, and the prompt can include text, images, video, audio and even PDFs or slide decks. It tops the Artificial Analysis text-to-video arena at the time of reading.

  • Up to 30 s at 1080p
  • Takes PDFs and slide decks as input
  • Closed weights, unlike Wan 2.2

Recommended for: one long continuous shot.

Strengths and limits

Where it shines

  • Up to 30 s in one clip
  • Sound generated with the picture
  • Text, image and reference modes at every level

Think twice when

  • Standard and Prime stop at 1080p; 4K needs Pro or Prime Pro
  • Long clips add up: the price is per second
  • 2 to 30 s, native sound
  • Up to 1080p (Pro levels up to 4K)

Use cases

Slide deck to explainer

Turn the attached quarterly results slides into a 30 second explainer video with a calm English voice-over and simple animated charts.

Documents as input are a Wan 3.0 first among these models.

Long continuous shot

A single 30 second tracking shot through a flower market at dawn, vendors arranging bouquets, soft chatter and birdsong.

30 s in one clip keeps motion and layout consistent.

Consistent character ad

Using my two reference images of the runner, show her tying her shoes, then sprinting across a bridge. Same outfit throughout, upbeat drums.

Reference mode keeps characters and props stable.

Against its rivals

  • Seedance 2.5Seedance 2.5 offers 30 s too, with a larger reference budget.#2 of 18 on Artificial Analysis Text to Video Arena with audio (1,142 Elo)
  • MiniMax H3 (Hailuo)MiniMax H3 has open weights but tops out at 15 s.#1 of 22 on Artificial Analysis Image to Video Arena (1,195 Elo)
  • Kling O3 (Omni)Kling O3 is stronger on voice binding for recurring characters.#14 of 22 on Artificial Analysis Image to Video Arena (1,044 Elo)
Compare side by side ↗

Version history

Each version, dated, with what it changed over the one before.

  1. Wan 2.7Earlier, not in Sub Rosa
    • Added first and last frame generation, video-to-video editing and subject referencing.
    Source : mindstudio.ai
  2. Wan 3.0Latest
    • Clip length doubles from 15 s to 30 s, up to 1080p.
    • Takes up to 10 images, 5 videos and 5 audio clips, plus PDFs and slides.
    • Weights are closed, a break from the open Wan 2.2.
    Source : datanorth.ai

Benchmarks

How to read these scores: what a benchmark tells you.

Artificial Analysis Image to Video Arena: #3 of 22 models measured in the catalog. The same blind duel, starting from one image: which clip brings it to life better. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Image to Video ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. MiniMax H3 MaxMiniMax H3 (Hailuo)1,195
  2. 2. MiniMax H3MiniMax H3 (Hailuo)1,181
  3. 3. Wan 3.0Wan 3.01,164
  4. 4. HappyHorse 1.1HappyHorse1,104
  5. 5. Grok Imagine 1.5Grok Imagine video1,098
  6. 6. HappyHorse 1.0HappyHorse1,083
  7. 7. Veo 3.1 Full QualityVeo 3 and 3.11,082
  8. 8. Wan 2.7Wan 2.x1,077
  9. 9. Grok ImagineGrok Imagine video1,072
  10. 10. Veo 3.1 FastVeo 3 and 3.11,066
See the numbers
ModelElo
1. MiniMax H3 Max1,195
2. MiniMax H31,181
3. Wan 3.01,164
4. HappyHorse 1.11,104
5. Grok Imagine 1.51,098
6. HappyHorse 1.01,083
7. Veo 3.1 Full Quality1,082
8. Wan 2.71,077
9. Grok Imagine1,072
10. Veo 3.1 Fast1,066

Artificial Analysis Text to Video Arena with audio: #1 of 18 models measured in the catalog. The duel for clips with sound: picture, voices, effects and how well they match. An Elo rating: higher is preferred more often. Only models that make their own sound take part.

Artificial Analysis Text to Video Arena with audioElo rating · Artificial Analysis, October 4, 2026
  1. 1. Wan 3.0Wan 3.01,156
  2. 2. Seedance 2.5Seedance 2.51,142
  3. 3. MiniMax H3MiniMax H3 (Hailuo)1,138
  4. 4. MiniMax H3 MaxMiniMax H3 (Hailuo)1,134
  5. 5. Flux 3FLUX 3 video1,127
  6. 6. Seedance 2.0Seedance 2.0 and 1.51,119
  7. 7. Gemini Omni Flash 1.1Gemini Omni Flash1,113
  8. 8. Grok Imagine 1.5Grok Imagine video1,044
  9. 9. HappyHorse 1.1HappyHorse1,043
  10. 10. Wan 2.7Wan 2.x1,029
See the numbers
ModelElo
1. Wan 3.01,156
2. Seedance 2.51,142
3. MiniMax H31,138
4. MiniMax H3 Max1,134
5. Flux 31,127
6. Seedance 2.01,119
7. Gemini Omni Flash 1.11,113
8. Grok Imagine 1.51,044
9. HappyHorse 1.11,043
10. Wan 2.71,029

Artificial Analysis Text to Video Arena: #1 of 5 models measured in the catalog. People watch two silent clips made from the same description, without knowing the models, and pick the better one. An Elo rating: higher is preferred more often. 100 points apart means the higher-rated model wins about 64% of duels.

Artificial Analysis Text to Video ArenaElo rating · Artificial Analysis, October 4, 2026
  1. 1. Wan 3.0Wan 3.01,129
  2. 2. MiniMax H3MiniMax H3 (Hailuo)1,118
  3. 3. MiniMax H3 MaxMiniMax H3 (Hailuo)1,115
  4. 4. Seedance 2.5Seedance 2.51,102
  5. 5. Flux 3FLUX 3 video1,094
See the numbers
ModelElo
1. Wan 3.01,129
2. MiniMax H31,118
3. MiniMax H3 Max1,115
4. Seedance 2.51,102
5. Flux 31,094

All 12 models in this family

ModelUsePrivacyPrice
Wan 3.0wan-3-0-text-to-videoText to videoAnonymized$0.117 per second of video$0.585 a 5 s clip
Wan 3.0wan-3-0-image-to-videoImage to videoAnonymized$0.117 per second of video$0.585 a 5 s clip
Wan 3.0 Referencewan-3-0-reference-to-videoReferences to videoAnonymized$0.117 per second of video$0.585 a 5 s clip
Wan 3.0 Primewan-3-0-prime-text-to-videoText to videoAnonymized$0.164 per second of video$0.819 a 5 s clip
Wan 3.0 Primewan-3-0-prime-image-to-videoImage to videoAnonymized$0.164 per second of video$0.819 a 5 s clip
Wan 3.0 Prime Referencewan-3-0-prime-reference-to-videoReferences to videoAnonymized$0.164 per second of video$0.819 a 5 s clip
Wan 3.0 Prowan-3-0-pro-text-to-videoText to videoAnonymized$0.106 per second of video$0.531 a 5 s clip
Wan 3.0 Prowan-3-0-pro-image-to-videoImage to videoAnonymized$0.106 per second of video$0.531 a 5 s clip
Wan 3.0 Pro Referencewan-3-0-pro-reference-to-videoReferences to videoAnonymized$0.106 per second of video$0.531 a 5 s clip
Wan 3.0 Prime Prowan-3-0-prime-pro-text-to-videoText to videoAnonymized$0.149 per second of video$0.746 a 5 s clip
Wan 3.0 Prime Prowan-3-0-prime-pro-image-to-videoImage to videoAnonymized$0.149 per second of video$0.746 a 5 s clip
Wan 3.0 Prime Pro Referencewan-3-0-prime-pro-reference-to-videoReferences to videoAnonymized$0.149 per second of video$0.746 a 5 s clip

Specifications

SpecificationWan 3.0
ReleasedAugust 24, 2026
WeightsClosed
Acceptstext, images, video, audio
Producesvideo, audio
Clip length2 to 30 s, with sound
Resolutions1080p, 720p, 480p
Price$0.117 per second of video
PrivacyAnonymized

Prices, context and lengths from the live catalog on October 16, 2026; parameters and licenses from the maker.