AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.027 per second of video
MiniMax's speed and cost-optimized H3 variant that generates 1080p video with sound. Ideal for rapid iteration and budget-conscious production.
At a lower cost than H3 Max, you can afford to generate many versions of the same shot and pick the best.
You get 1080p capability at lower cost than H3 Max.
The lower cost makes it practical to generate multiple variations.
Stereo sound comes automatically and is synchronized with the video.










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.
| MiniMax H3 Max TurboMiniMax | 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 15s 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 | $0.027 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 | 480p, 768p, 1080p | 5 to 15 s | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Always generated |
| Image to video | First frame, Last frame | 480p, 768p, 1080p | 5 to 15 s | Follows the input | Always generated |
$0/ month
$19/ month
$59/ month
$199/ month
MiniMax H3 Max Turbo is the budget option. When you need to generate quickly, iterate affordably, and don't need video or audio references, Turbo delivers on both fronts at a price that makes high-volume production practical. It trades the multimodal reference support of H3 and H3 Max for simplified features and lower cost.
H3 Max Turbo is the cost-optimized option. When you need to generate quickly, iterate affordably, and don't need video or audio references, Turbo delivers on both fronts. At a lower price point, you can afford to generate many variations and pick the best.
At a lower cost than H3 Max, you can afford to generate many versions of the same shot and pick the best. That affordability changes creative decision-making: instead of trying to get one shot right, you explore multiple directions.
You get 1080p capability at lower cost than H3 Max. The resolution is broadcast-ready and suitable for hero shots, commercials, and high-quality social content.
The lower cost makes it practical to generate multiple variations. That affordability enables more rapid testing and exploration.
Stereo sound comes automatically and is synchronized with the video. Silence it in the edit if you're scoring separately, but having it baked in is one less post-production step. The audio is always present and always synchronized.
Text-to-video and image-to-video only. No video or audio reference option, but that simplicity keeps the cost down. The stripped-down feature set focuses engineering on speed and cost, not reference handling.
When you're producing dozens of videos per week, the cumulative savings add up. H3 Max Turbo makes high-volume production economically viable for budget-conscious creators and agencies.
Simple workflow, fast results.
Specific prompts get better results. "A person turning to look at the camera, 3/4 profile, warm sunlight, high contrast" is better than "portrait video." Since you can't use video or audio references, text prompts carry more of the creative direction.
You pay per second of video. The rate scales with resolution: 480p is the cheapest tier, 768p is the middle tier, and 1080p is the highest cost. $0.027 per second of video Sound is always included. Use the calculator on this page to estimate a clip. The low per-second cost makes batch generation and variation affordable.
When you need 20 versions to pick the best, H3 Max Turbo's cost and speed make it the only practical choice. Generate multiple prompts, multiple framings, multiple styles, and select the winner.
Generate rough versions fast while you're building the edit. Swap in higher-quality versions from other models later if you need to. The speed makes it practical to generate proxy footage for editorial review before committing to final renders.
For TikTok, Instagram, and YouTube content where speed and cost per video matter more than reference capability. The weekly volume of posting makes H3 Max Turbo's cost advantage meaningful.
Generate, show the client, get notes, regenerate. Turbo's turnaround time keeps the feedback loop tight. The cost savings also mean you can afford to generate multiple directions for the client to choose from.
Try ideas fast without committing budget to reference video and audio integration. Test prompt styles, test compositions, test concepts, all at a price that doesn't require justifying every generation.
For news, live-event coverage, or rapidly-evolving social trends, H3 Max Turbo's speed gets you content to publish while the moment is relevant.
H3 Max supports video and audio reference inputs. H3 Max Turbo supports text and image inputs only, but it's roughly twice as fast and half the cost. Choose Turbo for pure text-to-video work. Choose Max when you need to reference motion from a video or mood from an audio track.
Base H3 is the most accurate and supports all input types (text, image, video, audio). H3 Max is fast and balanced. H3 Max Turbo is fastest and cheapest. Choose base H3 for high-accuracy work, especially with recognizable faces. Choose H3 Max for balanced speed and quality with multimodal references. Choose H3 Max Turbo for budget-conscious, high-volume text-to-video production where speed matters more than reference support.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the MiniMax H3 Max Turbo prompts for you. Every Craze plan, including Free, runs MiniMax H3 Max Turbo 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 $0.027 per second of video, with top-ups when you need more.
Batch generation and variations at scale: When you need 20 versions to pick the best, H3 Max Turbo's cost and speed make it the only practical choice. Placeholder and preview content: Generate rough versions fast while you're building the edit. Social media at scale: For TikTok, Instagram, and YouTube content where speed and cost per video matter more than reference capability. Rapid client iteration: Generate, show the client, get notes, regenerate.
MiniMax H3 Max Turbo is a speed and cost-optimized variant in the H3 family. It generates 1080p video with sound up to 15 seconds long.
H3 Max Turbo is designed for quick generation. Craze is measuring observed performance with your settings.
Text prompts and reference images. H3 Max Turbo supports text-to-video and image-to-video, but not video or audio reference inputs.
480p, 768p, and 1080p, for clips 5 to 15 seconds long.
Yes. It always generates stereo sound. Silence it in the edit if you need to add your own audio.
$0.027 per second of video. The cheapest rate in the H3 family. Check the calculator on this page to estimate a specific clip.
every Craze plan, including Free.
H3 Max Turbo is faster and cheaper. It doesn't support video and audio reference inputs, only text and image. Choose Turbo for text-to-video work, Max when you need video or audio references.
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