New model category

AI Video Model Catalog

Browse video generation models such as Veo, Kling, Runway, Pika, Luma, Hailuo, Seedance and Wan, while retaining historical status for discontinued entries such as Sora. The catalog tracks input modes, Arena AI rank, VBench scores, pricing unit, official sources and API availability.

Video model catalog fields

Video models are not context-window-plus-token-price products. They need output capability and generation-cost fields.

Text-to-Video

Generate video from prompts. Compare prompt following, camera control, duration, resolution and physical consistency.

PromptCameraPhysics

Image-to-Video

Generate from a first frame or reference image. Compare character consistency, motion control and style stability.

Reference imageCharacterMotion

World Models

Track interactive scenes, 3D, robotics simulation and game environments. Early pages should track availability before forcing price tables.

Simulation3DInteractive

Priority models

4

Catalog tracker

Each model row tracks modalities, access paths, pricing unit, price confidence, official sources and last verification date.

11
Product
Modalities / Source
Sora
OpenAI
text-to-videoimage-to-video
text, image, video โ†’ video
VBench 84.3%VBench++ 58.4%
Verified: 2026-09-15
Veo
Google
text-to-videoimage-to-video
text, image โ†’ video
VBench 85.1%VBench++ 66.7%
Verified: 2026-09-15
Kling
Kuaishou
text-to-videoimage-to-video
text, image โ†’ video
VBench 83.4%VBench++ 59%
Verified: 2026-09-15
Runway Gen-4
Runway
video generationediting
text, image, video โ†’ video
VBench++ 88.3%VBench++ 95.7%
Verified: 2026-09-15
Pika
Pika
video generationeffects
text, image, video โ†’ video
VBench 80.7%
Verified: 2026-09-15
Luma Ray
Luma AI
video generationcinematic motion
text, image โ†’ video
VBench 83.6%
Verified: 2026-09-15
Hailuo Video
MiniMax
text-to-videoimage-to-video
text, image โ†’ video
Verified: 2026-09-15
Seedance
ByteDance / Volcano Engine
video generationAPI
text, image โ†’ video
VBench++ 59.8%
Verified: 2026-09-15
Wan / Tongyi Wanxiang Video
Alibaba
text-to-videoimage-to-video
text, image โ†’ video
VBench 86.2%VBench++ 88.8%
Verified: 2026-09-15
Vidu
ShengShu
video generationimage-to-video
text, image โ†’ video
VBench 87.4%VBench++ 62.7%
Verified: 2026-09-15
SkyReels
SkyReels
text-to-videoimage-to-video
text, image, video โ†’ video
Verified: 2026-09-15

Fields to track

Pricing unit: second / generation / credit
Max duration and resolution
Text-to-video / image-to-video / video-to-video
Camera control and character consistency
API availability
Commercial license and region availability

Why video first

Video model demand is rising fast and the provider set is now large enough to compare. It is the best first step from text LLM comparison into multimodal models.