AI video models
28 models from 9 labs, one credit balance. Pick one to open it in the AI Video Maker.
ByteDance
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Seedance 2.0 ByteDance's flagship: multi-shot stories, native audio, up to 1080p. | text to video, first and last frame, up to 9 reference images | 480p, 720p, 1080p | 4–15 seconds | optional | 5 credits/s |
| Seedance 2.5 Longest Seedance: up to 30 seconds with audio. | text to video, first and last frame, up to 9 reference images | 480p, 720p, 1080p | 4–30 seconds | optional | 30 credits/s |
| Seedance 2.0 Fast Seedance 2.0 quality at a lower price and faster turnaround. | text to video, first and last frame, up to 9 reference images | 480p, 720p | 4–15 seconds | optional | 4 credits/s |
| Seedance 2.0 Mini The cheapest Seedance for quick tests and memes. | text to video, first and last frame, up to 9 reference images | 480p, 720p | 4–15 seconds | optional | 3 credits/s |
| Seedance 1.0 Pro Stable, cinematic Seedance 1.0 in 5 or 10 seconds. | text to video, image to video | 480p, 720p, 1080p | 5, 10 seconds | none (silent video) | 5 credits/s |
MiniMax
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| MiniMax H3 Hailuo's H3: strong physics and faces, up to 2K. | text to video, first and last frame, up to 9 reference images | 768P, 2K | 4–15 seconds | none (silent video) | 8 credits/s |
Vidu
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Vidu Q4 Image and multi-reference video with audio, up to 4K. | image to video, up to 9 reference images | 540p, 720p, 1080p, 2k, 4k | 3–16 seconds | optional | 5 credits/s |
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Gemini Omni Flash 1.1 Google's fast omni model: video with sound from text or images. | text to video, first and last frame, up to 9 reference images | 360p, 720p, 1080p, 4k | 4, 6, 8, 10 seconds | always included | 6 credits/s |
| Gemini Omni Google's omni video model with sound, up to 4K. | text to video, up to 9 reference images | 720p, 1080p, 4k | 4, 6, 8, 10 seconds | always included | 6 credits/s |
| Veo 3.1 Fast Google Veo 3.1 with native audio at a lower price. | text to video, first and last frame | 720p, 1080p, 4k | 4, 6, 8 seconds | always included | 9 credits/s |
| Veo 3.1 Quality Google's highest-fidelity Veo 3.1 tier. | text to video, first and last frame | 720p, 1080p, 4k | 4, 6, 8 seconds | always included | 37 credits/s |
| Veo 3.1 Lite The most affordable Veo 3.1 for high volume. | text to video, first and last frame | 720p, 1080p, 4k | 4, 6, 8 seconds | always included | 2 credits/s |
Kling AI
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Kling 2.5 Turbo Fast Kling with dynamic motion and camera control. | text to video, first and last frame | 1080p | 5, 10 seconds | none (silent video) | 10 credits/s |
| Kling 2.6 Kling with native sound effects and speech. | text to video, image to video | 1080p | 5, 10 seconds | optional | 12 credits/s |
| Kling 2.1 Master Kling 2.1's top tier for detailed, cinematic shots. | text to video, image to video | 1080p | 5, 10 seconds | none (silent video) | 20 credits/s |
| Kling 2.1 Pro Animate a photo, optionally into a chosen end frame. | first and last frame | 1080p | 5, 10 seconds | none (silent video) | 12 credits/s |
| Kling 3.0 Kling 3.0 with optional audio, 3 to 15 seconds. | text to video, first and last frame | 720p, 1080p | 3–15 seconds | optional | 30 credits/s |
| Kling 3.0 Turbo Quick, affordable Kling 3.0 in 720p or 1080p. | text to video, image to video | 720p, 1080p | 3–15 seconds | none (silent video) | 15 credits/s |
| Kling 4.0 Kling's newest model: up to 30 seconds, keyframes and references. | text to video, first and last frame, up to 9 reference images | 720p, 1080p | 3–30 seconds | none (silent video) | 18 credits/s |
Alibaba
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Wan 2.5 Alibaba's Wan 2.5 in 720p or 1080p. | text to video, image to video | 720p, 1080p | 5, 10 seconds | none (silent video) | 10 credits/s |
| Wan 2.6 Wan 2.6 with multi-shot clips up to 15 seconds. | text to video, image to video | 720p, 1080p | 5, 10, 15 seconds | none (silent video) | 7 credits/s |
| Wan 3.0 Wan 3.0: frames, references and audio, 2 to 30 seconds. | text to video, first and last frame, up to 9 reference images | 480P, 720P, 1080P | 2–30 seconds | optional | 10 credits/s |
| Wan 3.0 Prime Wan 3.0 Prime: the highest-quality Wan, up to 30 seconds. | text to video, first and last frame, up to 9 reference images | 480P, 720P, 1080P | 2–30 seconds | optional | 10 credits/s |
PixVerse
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| PixVerse V6 Cheap, stylish clips from 1 to 15 seconds, optional audio. | text to video, first and last frame, up to 7 reference images | 360p, 540p, 720p, 1080p | 1–15 seconds | optional | 2 credits/s |
HappyHorse
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| HappyHorse 1.0 HappyHorse 1.0: fast 720p and 1080p clips up to 15 seconds. | text to video, image to video, up to 9 reference images | 720p, 1080p | 3–15 seconds | none (silent video) | 10 credits/s |
| HappyHorse 1.1 HappyHorse 1.1: fast 720p and 1080p clips up to 15 seconds. | text to video, image to video, up to 9 reference images | 720p, 1080p | 3–15 seconds | none (silent video) | 10 credits/s |
xAI
| Model | Inputs | Resolutions | Length | Audio | From |
|---|---|---|---|---|---|
| Grok Imagine xAI's Grok Imagine video, 6 to 30 seconds. | text to video, image to video | 480p, 720p, 1080p | 6–30 seconds | none (silent video) | 2 credits/s |
| Grok Imagine Video 1.5 Grok Imagine 1.5: a photo becomes a realistic clip with sound. | image to video | 480p, 720p | 1–15 seconds | always included | 4 credits/s |
Not sure which model?
Start with Seedance 2.0 Fast for quick drafts, Veo 3.1 or Seedance 2.0 for dialogue and sound, Kling for dynamic motion, and Wan 3.0 or Kling 4.0 for long clips.
Open the AI Video Maker