Best AI Video Models
Our shortlist of the strongest current AI video models on SandBase: the latest generations of Kling, Seedance, MiniMax H3, Wan, Veo, Gemini Omni, Grok Imagine and more.
All Best AI Video Models
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
Kling V4 Text to Video
Kling V4 Text to Video by Kuaishou turns a text prompt into a 3-30 second video at 720p or 1080p.
Kling V3 Pro Text to Video
Kling V3 Pro Text to Video by Kuaishou turns a text prompt into a 3-15 second 1080p video with optional native audio.
Kling O3 Pro Text to Video
Kling O3 Pro Text to Video by Kuaishou turns a text prompt into a 3-15 second 1080p video with optional native audio.
Seedance 2.5 Text to Video
ByteDance's next-generation text-to-video model, generating native single-shot clips up to 30 seconds at 720p with coherent motion, native audio, and director-level camera control for professional-gra...
Seedance 2.0 Text to Video
ByteDance's most advanced text-to-video model delivering cinematic output, native audio, multi-shot editing, and director-level camera control for professional-grade video creation.
MiniMax H3 Text to Video
Generate native-stereo 2K video from text with MiniMax H3.
MiniMax H3 Max Text to Video
MiniMax H3 Max by MiniMax turns a text prompt into a 5-15 second video with native audio at 480P or 768P, generating faster than MiniMax H3.
Wan 3.0 Text to Video
Wan 3.0 by Alibaba turns a text prompt into a video of up to 30 seconds at 30fps, with native dialogue, music, and sound effects.
Veo 3.1 Text to Video
Veo3.1 by Google - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
Gemini Omni Flash 1.2 Text to Video
Gemini Omni Flash 1.2 is Google's text-to-video model. Generate 3–15 second clips with synchronized audio from a written prompt, at 360p to 4K.
Grok Imagine Video 1.5 Text to Video
Grok Imagine Video 1.5 by xAI - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
Happy Horse 1.1 Text to Video
Happy Horse 1.1 is Alibaba's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.
Vidu Q4 Image to Video
Vidu Q4 Preview by Shengshu animates a first-frame image into a 3 to 16 second video at up to 4K. Prompts can direct motion, camera cuts, and spoken dialogue, with native speech and sound effects.
LTX 2.3 Pro Text to Video
Ltx 2.3 Pro is Lightricks's text-to-video AI model. Turn written scripts and prompts into professional-quality video clips with realistic motion, lighting, and scene composition.
Model lineup
The most used endpoints first.
| Model | Task | What it does |
|---|---|---|
| MiniMax H3 Text to Video | Text → video | Generate native-stereo 2K video from text with MiniMax H3 |
| Seedance 2.0 Text to Video | Text → video | ByteDance's most advanced text-to-video model delivering cinematic output, native audio, multi-shot editing, and director-level camera control for… |
| MiniMax H3 Max Text to Video | Text → video | MiniMax H3 Max by MiniMax turns a text prompt into a 5-15 second video with native audio at 480P or 768P, generating faster than MiniMax H3 |
| Seedance 2.5 Text to Video | Text → video | ByteDance's next-generation text-to-video model, generating native single-shot clips up to 30 seconds at 720p with coherent motion, native audio,… |
| Kling V3 Pro Text to Video | Text → video | Kling V3 Pro Text to Video by Kuaishou turns a text prompt into a 3-15 second 1080p video with optional native audio |
| Kling O3 Pro Text to Video | Text → video | Kling O3 Pro Text to Video by Kuaishou turns a text prompt into a 3-15 second 1080p video with optional native audio |
| LTX 2.3 Pro Text to Video | Text → video | Ltx 2.3 Pro is Lightricks's text-to-video AI model |
| Kling V4 Text to Video | Text → video | Kling V4 Text to Video by Kuaishou turns a text prompt into a 3-30 second video at 720p or 1080p |
| Wan 3.0 Text to Video | Text → video | Wan 3.0 by Alibaba turns a text prompt into a video of up to 30 seconds at 30fps, with native dialogue, music, and sound effects |
| Veo 3.1 Text to Video | Text → video | Veo3.1 by Google - generate cinematic videos from text descriptions with AI |
| Gemini Omni Flash 1.2 Text to Video | Text → video | Gemini Omni Flash 1.2 is Google's text-to-video model |
| Grok Imagine Video 1.5 Text to Video | Text → video | Grok Imagine Video 1.5 by xAI - generate cinematic videos from text descriptions with AI |
The current generation, in one place
This list covers the latest two or three generations of each major video model family. We update it when providers ship new versions, and older versions move to the family pages.
How we pick
- Current flagship or one release back from each family.
- Usage on SandBase and coverage of common workflows: text, image and reference to video.
- One representative endpoint per model; the family page lists every tier.
Browse by family: Kling, Seedance, MiniMax H3, Wan, Veo. Browse by task: text to video, image to video.
Start using Best AI Video Models on SandBase
One API key and one request shape for every model on this page.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Submit a run
Send a request to the Unified Run API with model bytedance/seedance/2.0/text-to-video. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "bytedance/seedance/2.0/text-to-video", "prompt": "A daisy field under a clear blue sky, the camera slowly pushes in on a single flower", "duration": 5}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
How often is this list updated?
Whenever a major family ships a new version. The list keeps the latest two or three generations per family.
Why only one endpoint per model?
To keep the comparison readable. Each family page lists every tier (Fast, Pro, 4K, Lite) and task.
Which model is the most used on SandBase?
MiniMax H3, Kling 3.0 and Seedance 2.0 have the highest video run counts on SandBase.
Can I test several models with one key?
Yes. Every model here uses the same POST /v1/run request with a different model value.
Build with Best AI Video Models.
One key, consistent APIs, and usage-based pricing across every model on this page.