whatmodel.sh

· find the best video models you can run

142 models · scores combine 55 benchmarks · updated 2026-10-11 02:20 UTChow it works · find a leaderboard · benchmark your machine

task[all tasks][text to video][image to video][video editing]

Filter by your hardware and budget

+ more

Detect your exact chip or graphics card:

curl -G whatmodel.sh/video --data-urlencode "mac=$(sysctl -n hw.memsize machdep.cpu.brand_string)"Mac

curl -G whatmodel.sh/video --data-urlencode "ram=$(awk '/MemT/{print $2}' /proc/meminfo)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>/dev/null)"Linux

curl.exe -G whatmodel.sh/video --data-urlencode "ram=$((gcim Win32_ComputerSystem).TotalPhysicalMemory)" --data-urlencode "nv=$(nvidia-smi --query-gpu=name,memory.total --format=csv,noheader 2>$null)"Windows

$ terminal

ram[8][16][24][32][48][64][96][128][192][256]GB

gpu[apple silicon][graphics card][unified memory][none]

price[local][$0.02][$0.05][$0.1][$0.25][any]max per sec

detecting your OS…

Score vs API price

  80 ┤ · · · · · · · · · · · Wan 2.2 I2V Flash · · · Wan 3.0 ◆◆· · · · ·◇· · · · · · · · · · · · ◇ · · · · · ·
     │   ·                  ◆──────────◇──────────────◆◇─────◇   ◇    ∘ ◇     ◇     ·            ◇        ◇
  60 ┤ · ◆──────◆─Wan 2.6 Flash· · ◇◇·◇◇◇· · · · ·◇· ·∘· · · ◇ · ◇ ◇ · · · · · · · · · · · · · ◇ · · · · · · ·
     │   ∘                     ∘       ·     ◇      ∘ ∘◇     ·     ∘                ·     ∘    ◇
  40 ┤ · · · · · · · · · · · · ◇ · · · ◇ · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · · ·
     └───┬─────────────────────────────┬─────────────────────┬──────────────────────┬─────────────────────────
       $0.02                         $0.05                 $0.1                   $0.2

#	model	score↓	where↓	speed↓	RAM↓	get it	sources

#	model	score↓	where↓	RAM↓	get it	sources
1	Gemini Omni 1.1 Flash Google	81±2	api $0.10/sec		ai.google.dev ↗	+1
2	Wan 3.0 Prime Alibaba	80±7*	api $0.14/sec		www.alibabacloud.com ↗
3	Gemini Omni Flash Google	80±2	api $0.10/sec		ai.google.dev ↗
4	Wan 3.0 Alibaba	79±2	api $0.10/sec		www.alibabacloud.com ↗
5	Dreamina Seedance 2.0 ByteDance Seed	79±1	api $0.30/sec		fal.ai ↗	+3
6	MiniMax H3 MiniMax	78±1	api $0.13/sec +local	~40GB	fal.ai ↗	+2
7	Dreamina Seedance 2.5 ByteDance	77±1	api $0.30/sec		docs.dev.runwayml.com ↗
8	FLUX 3 Video Black Forest Labs	77±2	api $0.17/sec		docs.bfl.ai ↗
9	HappyHorse 1.1 Alibaba	76±3	api $0.14/sec		www.alibabacloud.com ↗
10	MiniMax H3 Max MiniMax	76±4*	api $0.080/sec		platform.minimax.io ↗
11	Muse Video Meta	76±2*	comparison only
12	Grok Imagine Video 1.5 xAI	75±2	api $0.080/sec		docs.x.ai ↗
13	HiDream-O1-Video 1.0 HiDream	75±3*	comparison only
14	Wan 2.2 I2V Flash Alibaba	75±4*	api $0.036/sec		www.alibabacloud.com ↗
15	HappyHorse 1.0 Alibaba-ATH	73±2	api $0.14/sec		replicate.com ↗
16	Wan 2.2 I2V Plus Alibaba	71±5*	api $0.10/sec		www.alibabacloud.com ↗
17	Grok Imagine Video xAI	69±2	api $0.050/sec		docs.x.ai ↗
18	Kling 3.0 Pro Kuaishou	69±2	api $0.11/sec		fal.ai ↗
19	Veo 3.1 Google	69±1	api $0.40/sec		ai.google.dev ↗	+11
20	Sora 2 Pro OpenAI	68±2*	comparison only
21	Veo 3.1 Fast Google	68±1	api $0.10/sec		ai.google.dev ↗	+1
22	Kling 3.0 Kuaishou (Kling AI)	68±4	api $0.084/sec		kling.ai ↗
23	Wan 2.7 Alibaba	68±2	api $0.10/sec		www.alibabacloud.com ↗
24	Vidu Q3 Pro ShengShu (Vidu)	65±2	api $0.10/sec		platform.vidu.com ↗
25	Veo 3 Fast Google	65±2	comparison only
26	Runway Aleph 2.0 Runway	65±7*	api $0.28/sec		docs.dev.runwayml.com ↗
27	Sora 2 OpenAI	65±2	comparison only			+5
28	Wan 2.6 Alibaba	65±1	api $0.10/sec		www.alibabacloud.com ↗
29	Wan2.1-VACE-14B Alibaba	65±7*	comparison only
30	Veo 3 Google	64±2	comparison only
31	Kling O3 Pro Kuaishou (Kling AI)	64±4*	api $0.11/sec		fal.ai ↗
32	Seedance 1.0 Pro Fast ByteDance	62±11*	api $0.049/sec		fal.ai ↗
33	Wan 2.5 Preview Alibaba	61±2	api $0.10/sec		www.alibabacloud.com ↗
34	Kling 2.6 Pro Kuaishou (Kling AI)	59±2	api $0.070/sec		fal.ai ↗
35	PixVerse V5.6 PixVerse	59±2	api $0.045/sec		docs.platform.pixverse.ai ↗
36	Runway Gen-4.5 Runway	58±2	api $0.12/sec		docs.dev.runwayml.com ↗
37	Wan 2.1 I2V Plus Alibaba	58±5*	api price unknown		www.alibabacloud.com ↗
38	Cosmos3-Super NVIDIA	58±4*†	local	~160GB	how to run ›
39	Seedance 1.5 Pro ByteDance Seed	58±2	api $0.052/sec		fal.ai ↗
40	Kling 2.5 Turbo Pro Kuaishou	57±2	api $0.070/sec		fal.ai ↗
41	Runway Aleph Runway	56±5*	comparison only
42	Wan 2.2 I2V A14B Alibaba	56±2	api $0.080/sec +local	~31GB	fal.ai ↗	+2
43	Seedance 1.0 Pro ByteDance Seed	56±2	api $0.052/sec		docs.byteplus.com ↗
44	Kling O1 Pro Kuaishou (Kling AI)	56±2*	api $0.11/sec		replicate.com ↗
45	Wan 2.6 Flash Alibaba	55±7*	api $0.025/sec		www.alibabacloud.com ↗
46	P-Video Pruna	55±2	api $0.020/sec		replicate.com ↗
47	Vidu Q2 Turbo ShengShu (Vidu)	55±3*	api $0.050/sec		fal.ai ↗
48	Hailuo 2.3 MiniMax	55±2	api $0.047/sec		platform.minimax.io ↗
49	Ray 3 Luma AI	55±2	comparison only
50	Vidu Q3 Shengshu	54±12*	comparison only
51	Kling 2.1 Standard Kuaishou (Kling AI)	54±3*	api $0.050/sec		replicate.com ↗
52	Hailuo 02 MiniMax	54±2	api $0.047/sec		platform.minimax.io ↗
53	LTX-2.5 Lightricks	53±6*	api $0.12/sec +local	~14GB	docs.ltx.io ↗
54	Vidu Q2 Pro ShengShu (Vidu)	53±3*	comparison only
55	HunyuanVideo 1.5 (I2V) Tencent	53±2	api $0.075/sec +local	~66GB	fal.ai ↗	+2
56	Kling 2.1 Master Kuaishou (Kling AI)	53±2*	api $0.28/sec		replicate.com ↗
57	Kandinsky 5.0 Pro Sber	52±2*	api $0.040/sec +local	~76GB	fal.ai ↗
58	HY-OmniWeaving Tencent	52±4	comparison only
59	HunyuanVideo 1.5 Tencent	52±2	api $0.075/sec +local	~20GB	fal.ai ↗
60	Cosmos3-Nano NVIDIA	52±3	local	~42GB	how to run ›
61	PixVerse 5.5 PixVerse	52±10*	api $0.060/sec		docs.platform.pixverse.ai ↗
62	Kling 1.6 (Pro mode) Kuaishou (Kling AI)	52±4*	comparison only
63	LongCat-Video Meituan	51±2	api $0.040/sec +local	~100GB	fal.ai ↗
64	Kandinsky 6.0 Video Lite Sber	51±7*†	local	~34GB	how to run ›
65	Seaweed-7B ByteDance Seed	50±6*†	comparison only
66	Luma Dream Machine 1.6 Luma AI	50±7*	comparison only
67	Wan 2.2 A14B Alibaba	50±2	api $0.080/sec +local	~31GB	fal.ai ↗
68	Runway Gen-4 Runway	50±4*	comparison only
69	Veo 2 Google	50±2	comparison only
70	LTX-2 Lightricks	49±2	local	~120GB	how to run ›
71	Open-Sora Plan v1.3 (T2V) Peking University (PKU-YuanGroup)	49±7*	local	~24GB	how to run ›
72	Cosmos-1.0-Diffusion-7B-Video2World NVIDIA	49±5*†	comparison only
73	Seedance 1.0 Lite ByteDance Seed	48±2	comparison only
74	Cosmos-Predict2.5-2B NVIDIA	48±2	comparison only
75	Cosmos-Predict2-14B-Video2World NVIDIA	48±8*	comparison only
76	MAGI-1 24B Sand AI	48±4*	comparison only
77	Kandinsky 6.0 Video Pro Sber	48±7*†	local	~109GB	how to run ›
78	Wan2.1-I2V-14B-720P Alibaba	48±4*	comparison only
79	Cosmos-Predict2-2B-Video2World NVIDIA	48±8*	comparison only
80	Wan 2.1 14B Alibaba	47±2	api $0.24/sec +local	~20GB	replicate.com ↗
81	Wan 2.2 TI2V 5B Alibaba	47±2	api price unknown +local	~6.5GB	fal.ai ↗	+3
82	Kandinsky 5.0 T2V Lite Sber	47±2*	local	~29GB	how to run ›
83	LTX-2 19B Distilled Lightricks	47±8*	api $0.020/sec +local	~41GB	replicate.com ↗
84	Cosmos-Predict2.5-14B NVIDIA	47±3	comparison only
85	CogVideoX-5B-I2V Zhipu AI (THUDM)	46±4	local	~13GB	how to run ›
86	Cosmos-1.0-Diffusion-7B-Text2World NVIDIA	46±3	local	~30GB	how to run ›
87	Hailuo 01 (MiniMax video-01 / I2V-01) MiniMax	46±4*	api $0.083/sec		fal.ai ↗
88	Kling 1.6 (Standard mode) Kuaishou (Kling AI)	45±5*	comparison only
89	Step-Video-T2V StepFun	45±7*	comparison only
90	HunyuanVideo-I2V Tencent	45±4	local	~57GB	how to run ›
91	CogVideoX-5B Zhipu AI (THUDM)	44±2	api price unknown +local	~13GB	fal.ai ↗
92	Step-Video-TI2V StepFun	44±7*	comparison only
93	Wan 2.1 I2V Turbo Alibaba	43±7*	api price unknown		www.alibabacloud.com ↗
94	Ray 2 Luma AI	43±2	comparison only
95	Open-Sora 2.0 HPC-AI Tech	42±5*	local	~55GB	how to run ›
96	Pyramid Flow (SD3) Peking University / Kuaishou	42±3*	local	~8GB	how to run ›
97	Luma Dream Machine 1.0 Luma AI	42±7*	comparison only
98	Sora (original, 2024) OpenAI	42±2	comparison only
99	Wan 2.1 T2V 1.3B Alibaba	40±4	api $0.040/sec +local	~8.6GB	replicate.com ↗
100	Mochi 1 Genmo	40±2	api price unknown +local	~6.5GB	replicate.com ↗
101	Runway Gen-3 Alpha Runway	40±3	comparison only
102	Open-Sora Plan v1.3 (I2V) Peking University (PKU-YuanGroup)	39±7*	local	~24GB	how to run ›
103	UniVideo Kuaishou (Kling AI)	39±3*	comparison only
104	T2V-Turbo (MS) UC Santa Barbara	39±6*†	comparison only
105	HunyuanVideo Tencent	39±3	api price unknown +local	~28GB	fal.ai ↗
106	Pandora (world model) Maitrix.org (MBZUAI / UC San Diego)	39±7*	comparison only
107	T2V-Turbo-v2 UC Santa Barbara	38±5*	api price unknown +local	~9.4GB	replicate.com ↗
108	Vidu 1.5 ShengShu (Vidu)	38±3*	comparison only
109	T2V-Turbo (VC2) UC Santa Barbara	38±3†	local	~9.4GB	how to run ›
110	Runway Gen-4 Turbo Runway	37±3*	api $0.050/sec		docs.dev.runwayml.com ↗
111	MAGI-1 4.5B Sand AI	37±5*	comparison only
112	LTX-2.3 Lightricks	36±3	api $0.040/sec +local	~34GB	docs.ltx.io ↗
113	CogVideoX1.5-5B Zhipu AI (THUDM)	36±2	local	~38GB	how to run ›
114	CogVideoX-2B Zhipu AI (THUDM)	36±2	local	~5.3GB	how to run ›
115	Pika 2.2 Pika	36±2	api $0.040/sec		fal.ai ↗
116	Allegro Rhymes AI	35±2	local	~9.3GB	how to run ›
117	Kling 1.0 Kuaishou (Kling AI)	35±7*	comparison only
118	VideoCrafter2 Tencent AI Lab	34±2	local	~9.4GB	how to run ›
119	Cosmos-1.0-Autoregressive-4B NVIDIA	34±5*†	comparison only
120	Pika 1.0 Pika	32±3	comparison only
121	Open-Sora 1.1 HPC-AI Tech	32±7*	local	~14GB	how to run ›
122	LaVie (base T2V) Shanghai AI Lab (Vchitect)	32±2	local	~4.9GB	how to run ›
123	LTX-Video 0.9 (2B) Lightricks	32±3*	local	~5.3GB	how to run ›
124	Cosmos-1.0-Autoregressive-5B-Video2World NVIDIA	31±5*†	comparison only
125	NOVA-0.6B T2V BAAI	29±3*	local	~9.3GB	how to run ›
126	ZeroScope v2 576w cerspense	27±3	local	~7.9GB	how to run ›
127	Hotshot-XL Hotshot	27±2	local	~10GB	how to run ›
128	Lumiere (T2V) Google	27±4*	comparison only
129	DynamiCrafter (1024) CUHK / Tencent AI Lab (DynamiCrafter)	27±4*	comparison only
130	Open-Sora 1.2 HPC-AI Tech	27±3	local	~39GB	how to run ›
131	Runway Gen-2 Runway	27±2	comparison only
132	PikaLab (September 2023) Pika	27±2	comparison only
133	VideoCrafter1 T2V Tencent AI Lab / HKUST	26±2	local	~8.1GB	how to run ›
134	Show-1 Show Lab / NUS	25±2	local	~83GB	how to run ›
135	LVDM (text-to-video) HKUST / Tencent AI Lab	25±3*	local	~6.1GB	how to run ›
136	ModelScope T2V 1.7B Alibaba DAMO Academy	25±2	local	~4.6GB	how to run ›
137	Floor33 Pictures (August 2023) Floor33 Pictures	24±2	comparison only
138	ZeroScope v2 XL (576w → XL pipeline) cerspense	24±2	local	~15GB	how to run ›
139	CogVideo 9B (original) Tsinghua / Zhipu	23±7*	local	~52GB	how to run ›
—	AnimateDiff SD 1.5 v2 motion adapter AnimateDiff authors	no reviewed results	local	~7.8GB	how to run ›
—	Stable Video Diffusion (SVD, 14 frames) Stability AI	no reviewed results	local	~8GB	how to run ›
—	Stable Video Diffusion XT (25 frames) Stability AI	no reviewed results	local	~8GB	how to run ›

Includes 46 comparison-only models with no verified API or download · hide them

142 of 142 catalogue models listed here · sources and licences

* new or thinly tested: ranked on too few benchmark results · † only the maker’s own numbers so far · ~RAM is estimated; full context may need more memory