AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.032 per second of video
Google DeepMind's lightweight video model for 1080p clips up to 8 seconds. Create from text or images at a lower cost per second than standard Veo 3.1.
Full HD is the standard for web, social, and streaming platforms.
Text to video, image to video, optional sound: Lite supports a single first-frame image for image-to-video.
When you're testing ideas or making multiple takes, Lite's lower cost makes experiments affordable.
You describe the video in plain language.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| Veo 3.1 LiteGoogle DeepMind | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 1080p | Up to 1080p | Up to 4K | Up to 720p |
| Length | Up to 8s per clip | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | Generated with the picture | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.032 per second of video | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Length | Aspect ratios | Sound |
|---|---|---|---|---|---|
| Text to video | Text prompt | 720p, 1080p | 4, 6, 8 s | 16:9, 9:16 | On or off |
| Image to video | First frame | 720p, 1080p | 4, 6, 8 s | Follows the input | On or off |
$0/ month
$19/ month
$59/ month
$199/ month
Veo 3.1 Lite is the entry point to the Veo family. You get full Veo quality at 1080p for the lowest cost, perfect for web, social media, and projects where 4K isn't required. It's built on the same core architecture as standard Veo 3.1 and Veo 3.1 Fast but optimized for efficiency without sacrificing visual consistency or detail fidelity.
Full HD is the standard for web, social, and streaming platforms. Veo 3.1 Lite generates native 1080p at the most affordable rate per second, so you're not paying for resolution you don't need. A 1080p video looks sharp on most screens, especially when delivered through social media apps that re-encode anyway.
Text to video, image to video, optional sound: Lite supports a single first-frame image for image-to-video. You give up 4K resolution and video extension capabilities.
When you're testing ideas or making multiple takes, Lite's lower cost makes experiments affordable. Batch quick tests to find what works, then upgrade to 4K for the hero shot if needed. The per-second savings compound when you're generating ten variations instead of one.
You describe the video in plain language. Craze breaks it into shots, writes the prompt for Lite, and generates them. No Veo prompt syntax to learn. Just say what you want and Craze handles the model integration.
Veo 3.1 Lite supports text-to-video and image-to-video generation. You describe a scene and it animates from your prompt. You provide a reference image and Lite animates from it while preserving the style and composition. Sound generation is optional on every clip, so you can add ambient audio, dialogue, or effects, or leave it off for music you'll layer in later.
Veo 3.1 Lite does not support video extension. If you need to extend existing clips, use Veo 3.1 or Veo 3.1 Fast. The model generates clips up to 8 seconds at 1080p or 720p, preserving detail and writing to natural physics.
You pay per second of video, starting at $0.032 per second of video. Pricing changes with resolution and whether sound is enabled. Clips can be 4, 6, or 8 seconds at either 720p or 1080p. The calculator shows the rate for your choices.
Instagram, TikTok, YouTube Shorts, and web platforms deliver at 1080p or below. Veo 3.1 Lite gives you full quality at the resolution they actually use. You're not paying for 4K when your platform only displays 1080p.
When you're fast-prototyping an idea, Lite's lower cost makes iteration affordable. Test pacing, messaging, and visual direction without the 4K budget. For creators exploring multiple creative directions, the savings scale across dozens of variations.
1080p is perfect for education. Veo 3.1 Lite can turn a script into a finished sequence at a price that works for smaller creators and limited budgets. Explainer videos, tutorials, and educational content don't require broadcast 4K.
When you need many clips at once, Lite's lower per-second cost makes batch generation economical. Generate a series of clips for a campaign or course without the UHD budget.
Veo 3.1 Lite tops out at 1080p and costs less per second. Veo 3.1 reaches 4K and supports video extension. Veo 3.1 Fast is the 4K speed choice. All three generate up to 8-second clips from text or images with optional sound. Lite is for HD delivery and lower budgets. Veo 3.1 is for broadcast and UHD specs. Veo 3.1 Fast is for creators who need both speed and resolution.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the Veo 3.1 Lite prompts for you. Every Craze plan, including Free, runs Veo 3.1 Lite and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.032 per second of video, with top-ups when you need more.
Social media and web creators: Instagram, TikTok, YouTube Shorts, and web platforms deliver at 1080p or below. Rapid prototyping and testing: When you're fast-prototyping an idea, Lite's lower cost makes iteration affordable. Educational and explainer videos: 1080p is perfect for education. Batch video creation and content series: When you need many clips at once, Lite's lower per-second cost makes batch generation economical.
Veo 3.1 Lite is Google DeepMind's lighter, more affordable video model. It creates clips up to 8 seconds in 1080p or 720p from a text prompt or reference image, with optional sound.
Google DeepMind released Veo 3.1 Lite on March 31, 2026.
720p or 1080p. Veo 3.1 Lite maxes out at 1080p, which is perfect for HD output and web delivery.
Each clip runs up to 8 seconds. For longer pieces, Craze generates several clips and cuts them together on the timeline.
Yes, Veo 3.1 Lite can generate sound together with the picture. Sound is optional on Craze, so you can turn it off for clips you plan to score.
$0.032 per second of video. Veo 3.1 Lite is the most affordable Veo model. Use the cost calculator on this page to estimate your clip.
every Craze plan, including Free. Every paid plan includes monthly credits that cover Veo 3.1 Lite generations.
Veo 3.1 Lite maxes out at 1080p and costs less. Standard Veo 3.1 reaches 4K. Both support 8-second clips and optional sound from text or image input. Lite has no video extension.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video
