AI Video Generation Models: Compare Pricing, Speed & Capabilities

TextImageVoiceVideo

Filters

15s768p

New

HeyGen

HeyGen Video 1$$$

HeyGen's general-purpose video generation model for short-form business video.

i2vAudio

from $0.02/s≈$0.12 · 5s

15s1080p

New

xAI

Grok Imagine Video 1.5 Lite$$$

xAI's faster, lower-cost Grok Imagine Video, distilled from Grok Imagine Video 1.5.

i2v

from $0.02/s≈$0.12 · 5s

8s1080p

Google

Veo 3.1 Lite$$$

Google's most affordable Veo with native audio.

Audio

from $0.06/s≈$0.30 · 5s

8s4k

Google

Veo 3.1 Fast$$$

Fast, audio-native video generation from Google.

i2vAudio

from $0.12/s≈$0.60 · 5s

8s4k

Google

Veo 3.1$$$

Google's flagship video model with native audio.

i2vAudio

from $0.48/s≈$2.40 · 5s

10s720p

Runway

Runway Gen-4 Turbo$$$

Fast image-to-video from Runway.

i2v

from $0.06/s≈$0.30 · 5s

10s1080p

Runway

Runway Gen-4.5$$$

Runway's latest text- and image-to-video model.

i2v

from $0.14/s≈$0.72 · 5s

10s1080p

Runway

Runway Aleph 2.0$$$

Video-to-video editing from Runway.

v2v

from $0.34/s≈$1.68 · 5s

10s1080p

ByteDance

Seedance 1.5 Pro$$$

The Pro tier of the Seedance 1.5 line, with an audio price axis.

i2vAudio

from $0.006/s≈$0.03 · 5s

20s1080p

Black Forest Labs

FLUX 3 Video$$$

Black Forest Labs' FLUX video model with sharp, controllable motion.

i2v

from $0.20/s≈$1.02 · 5s

10s1080p

HeyGen

Avatar IV$$$

HeyGen's talking-avatar model: animate a portrait with natural speech and performance.

i2vAudio

from $0.06/s≈$0.30 · 5s

12s1080p

OpenAI

Sora 2 Pro$$$

OpenAI's premium video model with synchronized audio.

i2vAudio

from $0.36/s≈$1.80 · 5s

9s1080p

Luma

Luma Ray 3$$$

Luma's reasoning video model with HDR-grade visuals.

i2v

from $0.08/s≈$0.38 · 5s

15s720p

Kuaishou

Kling 3.0 Pro$$$

Kuaishou's Pro-tier Kling 3.0 with native audio.

i2vAudio

from $0.13/s≈$0.67 · 5s

15s720p

Kuaishou

Kling 3.0 Std$$$

Kuaishou's standard Kling 3.0 tier at a lower rate.

i2vAudio

from $0.10/s≈$0.50 · 5s

10s720p

Kuaishou

Kling Video O1$$$

Kuaishou's O1 video model for structured, controllable clips.

i2v

from $0.13/s≈$0.67 · 5s

15s1080p

Kuaishou

Kling 3.0$$$

Kuaishou's flagship with native audio and long clips.

i2vAudio

from $0.04/s≈$0.21 · 5s

10s1080p

Kuaishou

Kling 2.5 Turbo Pro$$$

Fast, sharp 1080p generation from Kuaishou.

i2v

from $0.08/s≈$0.42 · 5s

10s1080p

ByteDance

Seedance 2.5$$$

The newest Seedance generation with clips up to 30 seconds.

i2vAudio

from $0.06/s≈$0.28 · 5s

10s720p

ByteDance

Seedance 2.0 Mini$$$

The compact, lowest-cost Seedance 2.0 variant.

i2vAudio

from $0.02/s≈$0.09 · 5s

10s720p

ByteDance

Seedance 1 Lite$$$

The cheapest way to generate video.

i2v

from $0.01/s≈$0.05 · 5s

10s720p

ByteDance

Seedance 2.0 Fast$$$

ByteDance's fast lane with native audio.

i2vAudio

from $0.02/s≈$0.09 · 5s

10s1080p

ByteDance

Seedance 2.0$$$

ByteDance's flagship video model with audio.

i2vAudio

from $0.04/s≈$0.18 · 5s

10s1080p

Alibaba

Wan 3.0 Prime$$$

Alibaba's premium Wan 3.0 tier for maximum fidelity.

i2v

from $0.08/s≈$0.41 · 5s

10s1080p

Alibaba

Wan 3.0$$$

The newest generation of Alibaba's open video family.

i2v

from $0.06/s≈$0.30 · 5s

10s1080p

Alibaba

Happyhorse 1.1$$$

Alibaba's latest Happyhorse video model with improved 1080p pricing.

i2v

from $0.12/s≈$0.59 · 5s

10s1080p

Alibaba

Happyhorse 1.0$$$

Alibaba's first-generation Happyhorse video model.

i2v

from $0.12/s≈$0.59 · 5s

10s1080p

Deprecated

Alibaba

Wan 2.7$$$

Alibaba's previous-generation image-to-video model.

i2v

from $0.03/s≈$0.15 · 5s

15s768p

MiniMax

Hailuo 3 Max$$$

MiniMax's top-tier Hailuo for the most demanding generations.

i2vAudio

from $0.06/s≈$0.30 · 5s

15s2K

MiniMax

Hailuo 3$$$

MiniMax's flagship 2K video model with native audio.

i2vAudio

from $0.16/s≈$0.78 · 5s

10s1080p

MiniMax

Hailuo 2.3 Fast$$$

MiniMax's quick, affordable video lane.

i2v

from $0.03/s≈$0.14 · 5s

10s1080p

MiniMax

Hailuo 2.3$$$

MiniMax's flagship for expressive human motion.

i2v

from $0.05/s≈$0.27 · 5s

6s720p

xAI

Grok Imagine Video$$$

xAI's fast video model with native audio.

i2vAudio

from $0.05/s≈$0.24 · 5s

15s720p

xAI

Grok Imagine Video 1.5$$$

xAI's image-to-video model with synchronized audio.

i2vAudio

from $0.10/s≈$0.48 · 5s