MiniMax H3 API
MiniMax H3 generates native-stereo 2K video from text, frames or references, with faster Max and Max Turbo tiers and H3 Image for generation and editing.
Explore the model lineup
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
MiniMax H3 Max Turbo Text to Video
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, turns a text prompt into a 5-15 second video with native audio.
MiniMax H3 Max Turbo Image to Video
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, animates a first frame (and optional last frame) into a 5-15 second video with native audio.
MiniMax H3 Max Turbo Video Extend
MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, continues an existing video with 1-15 seconds of new footage with native audio.
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.
MiniMax H3 Max Image to Video
MiniMax H3 Max by MiniMax animates a first frame, optionally toward a last frame, into a 5-15 second video with native audio at 480P or 768P.
MiniMax H3 Max Reference to Video
MiniMax H3 Max by MiniMax generates a 5-15 second video with native audio at 480P or 768P that keeps subjects, motion, and voice consistent with reference images, videos, and audio.
MiniMax H3 Text to Video
Generate native-stereo 2K video from text with MiniMax H3.
MiniMax H3 Image to Video
Generate native-stereo 2K video from a first frame and optional last frame with MiniMax H3.
MiniMax H3 Reference to Video
Generate native-stereo 2K video guided by image, video, and audio references with MiniMax H3.
MiniMax H3 Image Highspeed Edit
MiniMax H3 Image Highspeed Edit is the faster version of MiniMax H3 Image Edit, editing and composing images from 1 to 16 reference images with the same parameters and 1K, 2K or 4K output.
MiniMax H3 Image Edit
MiniMax H3 Image Edit edits and composes images from 1 to 16 reference images with MiniMax's H3 image model, following the instruction while keeping subjects consistent, with 1K, 2K or 4K output.
MiniMax H3 Image Text to Image
MiniMax H3 Image is MiniMax's flagship image generation model from the H3 family, turning text prompts into detailed, photorealistic images with built-in prompt enhancement, aspect ratios from 1:3 to ...
MiniMax H3 Image Highspeed Text to Image
MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 image generation model, with the same prompt enhancement, aspect ratios from 1:3 to 3:1 and 1K, 2K or 4K output at lower latency.
Model lineup
The most used endpoints first.
| Model | Task | What it does |
|---|---|---|
| MiniMax H3 Reference to Video | Reference → video | Generate native-stereo 2K video guided by image, video, and audio references with MiniMax H3 |
| MiniMax H3 Image to Video | Image → video | Generate native-stereo 2K video from a first frame and optional last frame with MiniMax H3 |
| MiniMax H3 Text to Video | Text → video | Generate native-stereo 2K video from text with MiniMax H3 |
| 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 |
| MiniMax H3 Max Image to Video | Image → video | MiniMax H3 Max by MiniMax animates a first frame, optionally toward a last frame, into a 5-15 second video with native audio at 480P or 768P |
| MiniMax H3 Max Reference to Video | Reference → video | MiniMax H3 Max by MiniMax generates a 5-15 second video with native audio at 480P or 768P that keeps subjects, motion, and voice consistent with… |
| MiniMax H3 Max Turbo Text to Video | Text → video | MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, turns a text prompt into a 5-15 second video with native audio |
| MiniMax H3 Max Turbo Image to Video | Image → video | MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, animates a first frame (and optional last frame) into a 5-15 second… |
| MiniMax H3 Max Turbo Video Extend | Video → video | MiniMax H3 Max Turbo, the fastest tier of the H3 family post-trained by fal, continues an existing video with 1-15 seconds of new footage with… |
| MiniMax H3 Image Highspeed Edit | Image edit | MiniMax H3 Image Highspeed Edit is the faster version of MiniMax H3 Image Edit, editing and composing images from 1 to 16 reference images with the… |
| MiniMax H3 Image Edit | Image edit | MiniMax H3 Image Edit edits and composes images from 1 to 16 reference images with MiniMax's H3 image model, following the instruction while keeping… |
| MiniMax H3 Image Text to Image | Text → image | MiniMax H3 Image is MiniMax's flagship image generation model from the H3 family, turning text prompts into detailed, photorealistic images with… |
MiniMax H3 on SandBase
MiniMax H3 is the most used video family on SandBase. The core H3 endpoints generate 2K video with native stereo audio.
- H3: text, image (first frame plus optional last frame) and reference to video. Reference mode is guided by image, video and audio references.
- H3 Max: 5–15 second clips with native audio at 480P or 768P, generated faster than H3.
- H3 Max Turbo: the fastest tier, with text and image to video plus Video Extend for 1–15 more seconds.
- H3 Image: text-to-image and editing with 1–16 reference images, plus Highspeed variants.
For MiniMax Hailuo 2.3, see MiniMax Hailuo & H3.
Start using MiniMax H3 API 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 minimax/h3/text-to-video. Only the model field changes between models on this page.
TERMINALcurl https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "minimax/h3/text-to-video", "prompt": "A slow macro shot of steamed milk pouring into espresso, forming latte art, warm morning light", "duration": 6}' - 03
Fetch the result
The response includes a run id. Poll it every few seconds until the status is completed, then download the output URL.
TERMINALcurl https://api.sandbase.ai/v1/run/$RUN_ID \ -H "Authorization: Bearer $SANDBASE_API_KEY"
Questions, answered
Which H3 tier should I use?
Use H3 for 2K final output, H3 Max for faster 768P clips, and H3 Max Turbo for the lowest latency.
What resolution does MiniMax H3 output?
H3 outputs 2K. H3 Max and Max Turbo output 480P or 768P.
Can H3 extend a video?
Yes. H3 Max Turbo Video Extend adds 1–15 seconds with native audio.
Does MiniMax H3 also generate images?
Yes. H3 Image and H3 Image Highspeed generate and edit images at 1K, 2K or 4K.
Build with MiniMax H3 API.
One key, consistent APIs, and usage-based pricing across every model on this page.