Wan 3.0
Alibaba
It's the one people like most in blind votes between videos.
You'll find it inAPI only (for developers)
Developers only
Choose AI / Video
The best AI for creating videos
Video generators, ranked by people's blind votes. Some are open source.
Our picks
Three ways to get it right: the best one regardless of price, the best value and the best one without paying.
Gemini Omni Flash 1.1
Google
It scores 88 versus 100 for the most powerful one.
You'll find it inGemini (Google AI Plus plan)
Google AI Plus: €4.99/mo≈ $5.59/mo
Video generation from Google AI Plus.
MiniMax H3
MiniMax
It's open source: you download it and use it without paying and without usage limits. It scores 95 versus 100 for the most powerful one.
You'll find it inDownload it (open source) · How to use it
Free (open source)
Needs a computer with about 25.0 GB of video memory (VRAM).
The top 10
One model per row (its best version). The variants (max, high, medium…) are in «For the data nerds», at the end.
- 1Wan 3.0Alibaba · You'll find it in: API only (for developers)Score 100/100Developers only
- 2Utopai XUtopai · You'll find it in: API only (for developers)Score 98/100Developers only
- 3
Dreamina Seedance 2.5ByteDance · You'll find it in: API only (for developers)Score 96/100Developers only - 4MiniMax H3MiniMax · You'll find it in: Download it (open source) · How to use itScore 95/100Free (open source)
- 5MiniMax H3 MaxMiniMax · You'll find it in: API only (for developers)Score 93/100Developers only
- 6
FLUX 3Black Forest Labs · You'll find it in: API only (for developers)Score 92/100Developers only - 7Dreamina Seedance 2.0ByteDance · You'll find it in: API only (for developers)Score 89/100Developers only
- 8Score 88/100Google AI Plus: €4.99/mo≈ $5.59/mo
- 9SkyReels V4Skywork AI · You'll find it in: API only (for developers)Score 77/100Developers only
- 10Agnes-Video-2.5Sapiens AI · You'll find it in: API only (for developers)Score 72/100Developers only
Data zone
For the data nerds
Quality vs price chart, full table with filters and all the variants of each model (max, high, medium…). Click ▸ on a row to see sources, memory and notes.
Sources publish API prices in dollars. With the €/$ button at the top you choose the currency; in euros they are converted at €1 = $1.1206 (ECB reference rate of October 9, 2026).
Quality (Elo) vs price per second
Up = better · left = cheaper · the dashed line is the efficient frontier.
ClosedOpen weightsEfficient frontier
Swipe to see the whole chart
No price or no Elo: Vidu Q4 Preview, Runway Gen-4.5, Utopai X, MAGI-2 Preview (0912), HunyuanVideo 1.5, CogVideoX1.5-5B, CogVideoX-3, Wan 2.2 A14B, Kling O1 Pro (January), Pika 2.5, P-Video, Kandinsky 6.0 Video Pro, Kandinsky 6.0 Video Lite.
Full table
40 models and variants · click ▸ on a row to see sources, memory and notes
| Model | EloAA (audio) ⇅ | €/sUSD/s1080p ⇅ | WeightsWeights⇅ | MaturityMad.⇅ | |||||
|---|---|---|---|---|---|---|---|---|---|
| Wan 3.0 Alibaba | 1156 #1 | €0.18/s$0.20/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Featured: on the efficient frontier (nothing gives more performance for less money) Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · 51 days · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-08-19; data from 2026-10-09) Arena AA T2V v2.0: with audio #1 (Elo 1156) · no audio #1 (Elo 1127) Score: #1 in the arena (with audio). Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Utopai X Utopai | 1149 #2 | n/d | ClosedClosed | NewNew 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: NewNew Released 9 days ago · 1 leaderboard (AA T2V v2.0) · Adoption: No usage data (1 ranking) (leaderboards: AA T2V v2.0; released: 2026-09-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #2 (Elo 1149) · no audio: not listed Score: #2 in the arena, no API. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Dreamina Seedance 2.5 ByteDance | 1143 #3 | €0.51/s$0.57/s | ClosedClosed | ProvenProven 3 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 3 leaderboards · 70 days · Adoption: No usage data (3 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V; released: 2026-07-31; data from 2026-10-09) Arena AA T2V v2.0: with audio #3 (Elo 1143) · no audio #4 (Elo 1104) Score: AA text-to-video arena with audio: #3 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-11 | |||||||||
| MiniMax H3 (768p) MiniMax | 1137 #4 | €0.071/s$0.080/s | OpenOpen | ProvenProven ⬇ 3.6M/mo HF · 4 rankingsWidely usedWidely used | |||||
Featured: ★ Best open · on the efficient frontier (nothing gives more performance for less money) Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 3.6 M HF downloads/mo · 4 leaderboards · 71 days · Adoption: Widely used (⬇ 3.6M/mo HF · 4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-07-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #4 (Elo 1137) · no audio #3 (Elo 1116) Score: Best open weights and very cheap. Memory: disk 66.3 GB (BF16 (transformer)) · Min. VRAM 25.0 GB approx. · fits on: 1× 32 GB (approx.)
Requirement: Model card: inference example with --num-gpus 4; no official VRAM figure. source Official repo (diffusers): several pipelines (FL2VA, Ref2VA) with a 32B encoder; the pruned/quantized variants are from Comfy-Org and unsloth. No official VRAM figure; the official example uses --num-gpus 4. License: MiniMax H3 Community License Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| MiniMax H3 Max MiniMax | 1130 #5 | €0.071/s$0.080/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · 44 days · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-08-26; data from 2026-10-09) Arena AA T2V v2.0: with audio #5 (Elo 1130) · no audio #2 (Elo 1117) Score: AA text-to-video arena with audio: #5 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| FLUX 3 Black Forest Labs | 1128 #6 | €0.26/s$0.29/s | ClosedClosed | ProvenProven 3 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 3 leaderboards · 78 days · Adoption: No usage data (3 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V; released: 2026-07-23; data from 2026-10-09) Arena AA T2V v2.0: with audio #6 (Elo 1128) · no audio #5 (Elo 1092) Score: AA text-to-video arena with audio: #6 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Dreamina Seedance 2.0 ByteDance | 1116 #7 | €0.33/s$0.37/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-03 · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-03-18; data from 2026-10-09) Arena AA T2V v2.0: with audio #7 (Elo 1116) · no audio #7 (Elo 1080) Score: AA text-to-video arena with audio: #7 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Gemini Omni Flash 1.1 Google | 1113 #8 | €0.14/s$0.15/s | ClosedClosed | ProvenProven 3 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 3 leaderboards · 42 days · Adoption: No usage data (3 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V; released: 2026-08-28; data from 2026-10-09) Arena AA T2V v2.0: with audio #8 (Elo 1113) · no audio #8 (Elo 1070) Score: AA text-to-video arena with audio: #8 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| SkyReels V4 Skywork AI | 1074 #9 | €0.31/s$0.35/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-03 · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-03-18; data from 2026-10-09) Arena AA T2V v2.0: with audio #9 (Elo 1074) · no audio #6 (Elo 1085) Score: AA text-to-video arena with audio: #9 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Agnes-Video-2.5 Sapiens AI | 1057 #10 | €0.036/s$0.040/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Featured: on the efficient frontier (nothing gives more performance for less money) Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · 48 days · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-08-22; data from 2026-10-09) Arena AA T2V v2.0: with audio #10 (Elo 1057) · no audio #9 (Elo 1050) Score: AA text-to-video arena with audio: #10 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
 Grok Imagine Video 1.5xAI | 1045 #11 | €0.071/s$0.080/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-05 · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-05-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #11 (Elo 1045) · no audio #12 (Elo 1036) Score: Official API price ≈ €0.071$0.08/s (docs.x.ai). Elo still from the AA arena. Source: docs.x.ai/developers/models/grok-imagine-video-1.5 · 2026-10-09 | |||||||||
| HappyHorse-1.1 Alibaba (ATH) | 1042 #12 | €0.16/s$0.18/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · 109 days · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-06-22; data from 2026-10-09) Arena AA T2V v2.0: with audio #12 (Elo 1042) · no audio #10 (Elo 1043) Score: AA text-to-video arena with audio: #12 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Wan 2.7 Alibaba | 1030 #13 | €0.13/s$0.15/s | ClosedClosed | ProvenProven 5 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 5 leaderboards · 119 days · Adoption: No usage data (5 rankings) (leaderboards: AA Text-to-Image, AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-06-12; data from 2026-10-09) Arena AA T2V v2.0: with audio #13 (Elo 1030) · no audio #13 (Elo 1027) Score: AA text-to-video arena with audio: #13 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| HappyHorse-1.0 Alibaba (ATH) | 1023 #14 | €0.21/s$0.24/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-04 · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-04-07; data from 2026-10-09) Arena AA T2V v2.0: with audio #14 (Elo 1023) · no audio #11 (Elo 1038) Score: AA text-to-video arena with audio: #14 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
 Kling 3.0 Omni 1080p (Pro)Kuaishou | 1015 #15 | €0.12/s$0.14/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-02 · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-02-04; data from 2026-10-09) Arena AA T2V v2.0: with audio #15 (Elo 1015) · no audio #16 (Elo 990) Score: AA text-to-video arena with audio: #15 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Kling 3.0 1080p (Pro) Kuaishou | 1000 #16 | €0.15/s$0.17/s | ClosedClosed | ProvenProven 3 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 3 leaderboards · from 2026-02 · Adoption: No usage data (3 rankings) (leaderboards: AA T2V v2.0, LMArena I2V, AA I2V v1.0; released: 2026-02-04; data from 2026-10-09) Arena AA T2V v2.0: with audio #16 (Elo 1000) · no audio #14 (Elo 1000) Score: AA text-to-video arena with audio: #16 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Grok Imagine Video 1.5 Lite xAI | 993 #17 | €0.12/s$0.14/s | ClosedClosed | NewNew 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: NewNew Only 1 leaderboard (AA T2V v2.0) · 44 days · Adoption: No usage data (1 ranking) (leaderboards: AA T2V v2.0; released: 2026-08-26; data from 2026-10-09) Arena AA T2V v2.0: with audio #17 (Elo 993) · no audio #17 (Elo 985) Score: AA text-to-video arena with audio: #17 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| PixVerse V6 PixVerse | 985 #18 | €0.10/s$0.12/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-03 · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-03-23; data from 2026-10-09) Arena AA T2V v2.0: with audio #18 (Elo 985) · no audio #15 (Elo 997) Score: AA text-to-video arena with audio: #18 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Veo 3.1 Google | 962 #19 | €0.36/s$0.40/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-01 · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-01-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #19 (Elo 962) · no audio #18 (Elo 968) Score: AA text-to-video arena with audio: #19 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Veo 3.1 Fast Google | 961 #20 | €0.11/s$0.12/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-01 · Adoption: No usage data (4 rankings) (leaderboards: AA T2V v2.0, LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2026-01-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #20 (Elo 961) · no audio #19 (Elo 964) Score: AA text-to-video arena with audio: #20 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| MAGI-2 Preview (0912) Sand.ai | 960 #21 | n/d | ClosedClosed | NewNew 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: NewNew Released 27 days ago · 1 leaderboard (AA T2V v2.0) · Adoption: No usage data (1 ranking) (leaderboards: AA T2V v2.0; released: 2026-09-12; data from 2026-10-09) Arena AA T2V v2.0: with audio #21 (Elo 960) · no audio #20 (Elo 959) Score: AA text-to-video arena with audio: #21 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Veo 3.1 Lite Google | 948 #22 | €0.071/s$0.080/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-03 · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-03-31; data from 2026-10-09) Arena AA T2V v2.0: with audio #22 (Elo 948) · no audio #21 (Elo 955) Score: AA text-to-video arena with audio: #22 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
 LTX-2.5 FastLightricks | 946 #23 | €0.12/s$0.13/s | OpenOpen | ProvenProven ⬇ 1.7M/mo HF · 2 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 1.7 M HF downloads/mo · 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · 59 days · Adoption: Widely used (⬇ 1.7M/mo HF · 2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-08-11; data from 2026-10-09) Arena AA T2V v2.0: with audio #23 (Elo 946) · no audio #22 (Elo 937) Score: Same weights repo as LTX-2.5 Pro (AA links to Lightricks/LTX-2.5); in the API it's the fast mode. Memory: disk 42.0 GB (BF16 (transformer)) · Min. VRAM 32.0 GB official · fits on: 1× 32 GB (official min.) · 80 GB recommended
Requirement: LTX docs: NVIDIA GPU with 32 GB+ of VRAM, 32 GB of RAM; recommended A100 80 GB or H100. source Plus Gemma 4 12B encoder (26.3 GB BF16 · 15.4 GB int8). Low VRAM: --quantization fp8-cast --offload cpu (model card). License: LTX-2.x Community Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| LTX-2.5 Pro Lightricks | 943 #24 | €0.15/s$0.17/s | OpenOpen | ProvenProven ⬇ 1.7M/mo HF · 2 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 1.7 M HF downloads/mo · 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · 59 days · Adoption: Widely used (⬇ 1.7M/mo HF · 2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-08-11; data from 2026-10-09) Arena AA T2V v2.0: with audio #24 (Elo 943) · no audio #23 (Elo 933) Score: Free license under $10M in revenue; gated repo. Memory: disk 42.0 GB (BF16 (transformer)) · Min. VRAM 32.0 GB official · fits on: 1× 32 GB (official min.) · 80 GB recommended
Requirement: LTX docs: NVIDIA GPU with 32 GB+ of VRAM, 32 GB of RAM; recommended A100 80 GB or H100. source Plus Gemma 4 12B encoder (26.3 GB BF16 · 15.4 GB int8). Low VRAM: --quantization fp8-cast --offload cpu (model card). License: LTX-2.x Community Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Vidu Q3 Pro Shengshu (Vidu) | 941 #25 | €0.11/s$0.12/s | ClosedClosed | ProvenProven 3 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 3 leaderboards · from 2026-01 · Adoption: No usage data (3 rankings) (leaderboards: AA T2V v2.0, LMArena I2V, AA I2V v1.0; released: 2026-01-30; data from 2026-10-09) Arena AA T2V v2.0: with audio #25 (Elo 941) · no audio #26 (Elo 910) Score: AA text-to-video arena with audio: #25 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| Vidu Q3 Turbo Shengshu (Vidu) | 911 #26 | €0.058/s$0.065/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-02 · Adoption: No usage data (2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-02-09; data from 2026-10-09) Arena AA T2V v2.0: with audio #26 (Elo 911) · no audio #25 (Elo 912) Score: AA text-to-video arena with audio: #26 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| LTX-2.3 Pro Lightricks | 892 #27 | €0.071/s$0.080/s | OpenOpen | ProvenProven ⬇ 971k/mo HF · 2 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 971k HF downloads/mo · 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-03 · Adoption: Widely used (⬇ 971k/mo HF · 2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-03-05; data from 2026-10-09) Arena AA T2V v2.0: with audio #27 (Elo 892) · no audio #29 (Elo 856) Score: Fits in 16–24 GB with FP8/offload. Memory: disk 46.1 GB (BF16 (transformer)) · Min. VRAM 16.0 GB community · fits on: 1× 16 GB tight (FP8 + offload) · 24 GB comfortable
Requirement: Community guide: minimum 16 GB with FP8 distilled + sequential offload; 24 GB BF16 distilled with offload; 48 GB+ BF16 without offload. source Plus Gemma 3 12B encoder (24.4 GB BF16 · 13.2 GB FP8 community). 48 GB+ for BF16 without offload (community guide). License: LTX-2 Community Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-08 | |||||||||
| LTX-2.3 Fast Lightricks | 855 #28 | €0.054/s$0.060/s | OpenOpen | ProvenProven ⬇ 971k/mo HF · 2 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 971k HF downloads/mo · 2 leaderboards (AA T2V v2.0, AA I2V v1.0) · from 2026-03 · Adoption: Widely used (⬇ 971k/mo HF · 2 rankings) (leaderboards: AA T2V v2.0, AA I2V v1.0; released: 2026-03-05; data from 2026-10-09) Arena AA T2V v2.0: with audio #28 (Elo 855) · no audio #28 (Elo 857) Score: Same weights repo as LTX-2.3 Pro (AA links to Lightricks/LTX-2.3); in the API it's the fast mode. Memory: disk 46.1 GB (BF16 (transformer)) · Min. VRAM 16.0 GB community · fits on: 1× 16 GB tight (FP8 + offload) · 24 GB comfortable
Requirement: Community guide: minimum 16 GB with FP8 distilled + sequential offload; 24 GB BF16 distilled with offload; 48 GB+ BF16 without offload. source Plus Gemma 3 12B encoder (24.4 GB BF16 · 13.2 GB FP8 community). 48 GB+ for BF16 without offload (community guide). License: LTX-2 Community Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Boreal Creatify | 838 #29 | €0.040/s$0.045/s | ClosedClosed | NewNew 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: NewNew Released 24 days ago · 1 leaderboard (AA T2V v2.0) · Adoption: No usage data (1 ranking) (leaderboards: AA T2V v2.0; released: 2026-09-15; data from 2026-10-09) Arena AA T2V v2.0: with audio #29 (Elo 838) · no audio #31 (Elo 841) Score: AA text-to-video arena with audio: #29 of 29. Source: artificialanalysis.ai/video/leaderboard/text-to-video?audio-output=tru · 2026-10-09 | |||||||||
| Vidu Q4 Preview Shengshu (Vidu) | n/d | €0.11/s$0.12/s | ClosedClosed | NewNew 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: NewNew Released 2 days ago · 1 leaderboard (AA I2V v1.0) · Adoption: No usage data (1 ranking) (leaderboards: AA I2V v1.0; released: 2026-10-07; data from 2026-10-09) Score: New (Oct 7). 540p ≈ €0.040$0.045/s · 4K ≈ €0.35$0.39/s. -30% until Nov 30. Not in the arena yet. Source: platform.vidu.com/docs/pricing · 2026-10-08 | |||||||||
 Runway Gen-4.5Runway | AA T2V no audio 920 (#24/32) | €0.11/s$0.12/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (LMArena T2V, AA T2V v2.0 (no audio)) · from 2025-12 · Adoption: No usage data (2 rankings) (leaderboards: LMArena T2V, AA T2V v2.0 (no audio); released: 2025-12-01; data from 2026-10-09) Arena AA T2V v2.0: with audio: not listed · no audio #24 (Elo 920) Score: Only in the no-audio arena (#24 of 32); price without audio. Source: docs.dev.runwayml.com/guides/pricing · 2026-10-08 | |||||||||
| HunyuanVideo 1.5 Tencent | LMArena T2V 1169 (n.º 38/48) | self-host | OpenOpen | ProvenProven ⬇ 684k/mo HF · 3 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 684k HF downloads/mo · 3 leaderboards · from 2025-11 · Adoption: Widely used (⬇ 684k/mo HF · 3 rankings) (leaderboards: LMArena T2V, LMArena I2V, AA I2V v1.0; released: 2025-11-20; data from 2026-10-09) Score: License NOT valid in the EU/UK/South Korea. Memory: disk 33.3 GB (FP32 (transformer, per variant)) · Min. VRAM 14.0 GB official (offload) · fits on: Official min. 14 GB (with offload) · Wan2GP from 6 GB
Requirement: Model card: «Minimum GPU Memory: 14 GB (with model offloading enabled)». Wan2GP (community): from 6 GB. source The official repo stores each transformer in FP32 (33.3 GB) and has 11 variants (480p/720p, T2V/I2V, distilled, SR 1080p). Distilled 480p I2V step: ~75 s per video on an RTX 4090 (model card). Not in the AA T2V v2.0 arena (with audio). AA I2V v1.0 (no audio): Elo 1134, #66 of 83 (LTX-2.3 Pro: 1158, #61). LMArena: T2V 1169 (#38/48), I2V 1198 (#40/48). No VBench for 1.5 (the original 13B HunyuanVideo: 83.2%). API on fal: $0.075/s at 480p. License: Tencent Hunyuan Community (excludes EU, UK and South Korea; >100M MAU requires a license) Source: lmarena.ai/leaderboard/text-to-video · 2026-10-09 | |||||||||
 CogVideoX1.5-5BZhipu (Z.ai) | VBench 82.0 % | self-host | OpenOpen | NewNew ⬇ 2.5k/mo HF · 1 rankingModerately usedModerately used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: NewNew Only 1 leaderboard (VBench) · 3k HF downloads/mo · from 2024-11 · Adoption: Moderately used (⬇ 2.5k/mo HF · 1 ranking) (leaderboards: VBench; released: 2024-11-02; data from 2026-10-09) Score: Old (Nov 2024); not in the AA arena or LMArena. Memory: disk 11.1 GB (BF16 (transformer)) · Min. VRAM 10.0 GB official (offload) · fits on: Official min. 10 GB (diffusers BF16 optimized) · INT8 from 7 GB
Requirement: Model card: diffusers BF16 «from 10GB*» and INT8 (torchao) «from 7GB*» with optimizations; SAT BF16 76 GB; multi-GPU BF16 24 GB. 5 s in ~550 s on an H100. source Not in any AA or LMArena arena. VBench T2V: 82.0% (Wan2.2-A14B: 82.6%, LTX-2: 79.4%). 1360×768, 5–10 s at 16 fps, English-only prompts. Successor CogVideoX-3 API only (no weights). License: CogVideoX License (commercial use: free registration; >1M visits/month, separate license) Source: huggingface.co/spaces/Vchitect/VBench_Leaderboard · 2026-10-09 | |||||||||
| CogVideoX-3 Zhipu (Z.ai) | n/d | n/d | ClosedClosed | Barely testedBarely t. 0 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: Barely testedBarely t. No independent benchmark · from 2025-07 · Adoption: No usage data (0 rankings) (released: 2025-07-15; data from 2026-10-09) Score: API only: $0.20/video (5–10 s, up to 4K); no arena. Closed (no weights). Released on Jul 15, 2025 (Z.ai release notes). Text/image/first-last frame to video, up to 4K and 60 fps, optional audio. Not on AA, LMArena or VBench. Source: docs.z.ai/guides/overview/pricing · 2026-10-09 | |||||||||
| Wan 2.2 A14B Alibaba | LMArena T2V 1132 (n.º 42/48) | self-host | OpenOpen | ProvenProven ⬇ 297k/mo HF · 4 rankingsWidely usedWidely used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: ProvenProven 297k HF downloads/mo · 4 leaderboards · from 2025-07 · Adoption: Widely used (⬇ 297k/mo HF · 4 rankings) (leaderboards: LMArena T2V, LMArena I2V, AA I2V v1.0, VBench; released: 2025-07-28; data from 2026-10-09) Score: Last Wan with open weights (Wan 2.5+ API only). Memory: disk 114 GB (FP32 (2 experts × 57.15 GB)) · Min. VRAM 80.0 GB official · fits on: 1× 80 GB (official, with offload) · less with FP8/GGUF in ComfyUI
Requirement: Model card: the 1-GPU command (720p, --offload_model --convert_model_dtype) «can run on a GPU with at least 80GB VRAM». source Only one expert (14B) works at each step; ComfyUI loads one at a time, so with FP8 (14.3 GB per expert) or GGUF Q4 (9.65 GB) VRAM drops a lot (no official figure). Not in AA T2V v2.0. AA I2V v1.0 (no audio): 1107, #69 of 83. LMArena: T2V 1132 (#42), I2V 1170 (#43). VBench T2V 82.6% (84.2% with an optimized prompt). Smaller sibling TI2V-5B (720p, fits in 24 GB). License: Apache 2.0 Source: lmarena.ai/leaderboard/text-to-video · 2026-10-09 | |||||||||
| Kling O1 Pro (January) KlingAI | AA T2V no audio 900 (#27/32) | €0.100/s$0.11/s | ClosedClosed | ProvenProven 1 rankingNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven Veteran · 1 leaderboard (AA T2V v2.0 (no audio)) · from 2026-01 · Adoption: No usage data (1 ranking) (leaderboards: AA T2V v2.0 (no audio); released: 2026-01-13; data from 2026-10-09) Arena AA T2V v2.0: with audio: not listed · no audio #27 (Elo 900) Score: Only in the no-audio arena (#27 of 32); price without audio. Source: artificialanalysis.ai/video/leaderboard/text-to-video · 2026-10-09 | |||||||||
| Pika 2.5 Pika Art | AA T2V no audio 850 (#30/32) | €0.080/s$0.090/s | ClosedClosed | ProvenProven 2 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 2 leaderboards (AA I2V v1.0, AA T2V v2.0 (no audio)) · from 2025-11 · Adoption: No usage data (2 rankings) (leaderboards: AA I2V v1.0, AA T2V v2.0 (no audio); released: 2025-11-22; data from 2026-10-09) Arena AA T2V v2.0: with audio: not listed · no audio #30 (Elo 850) Score: Only in the no-audio arena (#30 of 32); price without audio. Source: artificialanalysis.ai/video/leaderboard/text-to-video · 2026-10-09 | |||||||||
| P-Video Pruna AI | AA T2V no audio 820 (#32/32) | €0.036/s$0.040/s | ClosedClosed | ProvenProven 4 rankingsNo usage dataNo data | |||||
Weights: ClosedClosed Maturity: ProvenProven 4 leaderboards · from 2026-02 · Adoption: No usage data (4 rankings) (leaderboards: LMArena T2V, LMArena I2V, AA I2V v1.0, AA T2V v2.0 (no audio); released: 2026-02-26; data from 2026-10-09) Arena AA T2V v2.0: with audio: not listed · no audio #32 (Elo 820) Score: Only in the no-audio arena (#32 of 32); price without audio. Source: artificialanalysis.ai/video/leaderboard/text-to-video · 2026-10-09 | |||||||||
| Kandinsky 6.0 Video Pro Kandinsky Lab | No AA Elo yet (new) | self-host | OpenOpen | NewNew ⚠ little use · New on HFLittle usedLittle used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: NewNew By default: new open · ~270 HF downloads/mo · no AA arena yet · Adoption: Little used (⚠ little use · New on HF) Score: Open MIT · 29B · audio sync; vendor: beats open LTX-2.5 in visual/voice quality. Memory: disk 90.0 GB (BF16) · Min. VRAM 79.0 GB approx. · fits on: Large GPU / multi-GPU or offload (transformer ~70 GB BF16)
Requirement: Gearbrain: Pro 29B; block offloading lets you run it on a home PC at the cost of speed. source HF total: transformer 69.73 + text_encoder 16.58 + rest ~3.7 GB. Vendor (side-by-side): better than open LTX 2.5 in visuals and speech; in image animation it beats Veo 3.1 Fast (closed) according to Kandinsky. Only open MiniMax H3 is ahead. No public API price. License: MIT Source: huggingface.co/kandinskylab/Kandinsky-6.0-Pro-5s-Diffusers · 2026-10-10 | |||||||||
| Kandinsky 6.0 Video Lite Kandinsky Lab | No AA Elo yet (new) | self-host | OpenOpen | NewNew ⚠ little use · New on HFLittle usedLittle used | |||||
Weights: OpenOpen 🤗 Hugging Face Maturity: NewNew By default: new open · ~200 HF downloads/mo · no AA arena yet · Adoption: Little used (⚠ little use · New on HF) Score: Open MIT · 3B · 5 s clips with audio sync; fits on a consumer GPU. Memory: disk 27.7 GB (BF16) · Min. VRAM 16.0 GB community · fits on: 1× 16–32 GB (official presets Lite; offload)
Requirement: Gearbrain/Kandinsky: Lite adapted to consumer RTX cards with 16, 24 and 32 GB presets; block offloading lets you run it at home. source HF total: transformer 7.48 + text_encoder 16.58 + audio_vae 1.71 + vae 0.99 + clip 0.49 + vocoder 0.49 GB. T2AV + TI2AV, 44 kHz, lip-sync. Text encoder Qwen2.5-VL (~16.6 GB) shared. Presets 16/24/32 GB (Gearbrain). Distill 10-step available. License: MIT Source: huggingface.co/kandinskylab/Kandinsky-6.0-Lite-5s-Diffusers · 2026-10-10 | |||||||||
Vidu Q4 Preview: price by resolution
List price (credits at ≈ €0.0045$0.005). Without the -30% promo. source
| Resolution | €US$ per second |
|---|---|
| 540p | €0.040$0.045 |
| 720p | €0.085$0.095 |
| 1080p | €0.11$0.12 |
| 2K | €0.17$0.19 |
| 4K | €0.35$0.39 |