> ## Documentation Index
> Fetch the complete documentation index at: https://docs.modelslab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Enterprise MiniMax H3 API

> Run MiniMax H3 video models on dedicated enterprise GPU servers. Text-to-video, first-and-last-frame animation and reference-driven video with full server control.

> [!TIP]
>
> Not on Enterprise yet? Get your enterprise plan at [ModelsLab](https://modelslab.com/enterprise?utm_source=docs.modelslab.com\&utm_medium=referral\&utm_campaign=docs\&utm_content=enterprise-api-minimax-h3-overview)

MiniMax H3 runs directly on your own enterprise container — requests are posted straight at your
dedicated server instead of going through the shared queue.

The model exposes three capabilities across two generation endpoints:

| Capability | Endpoint | `model_id` |
| - | - | - |
| Text to video | `/minimax_h3/text2video` | not required |
| First & last frame to video | `/minimax_h3/img2video` | `h3-minimax-start-end-frame` |
| Reference to video | `/minimax_h3/img2video` | `h3-minimax-r2v` |

Text to video has an endpoint to itself, so it takes no `model_id`. Both image-to-video modes share
one endpoint and nothing in the payload separates them, so `model_id` is **required** there.

## Available Endpoints

> [card] [Text to Video](https://docs.modelslab.com/enterprise-api/minimax-h3/text2video.md)
>
> This endpoint generates a video from a text prompt using the MiniMax H3 model.

> [card] [Image to Video](https://docs.modelslab.com/enterprise-api/minimax-h3/img2video.md)
>
> This endpoint animates between a first and a last frame, or generates a video from image, video and audio references.

> [card] [Fetch Queued Videos](https://docs.modelslab.com/enterprise-api/minimax-h3/fetch.md)
>
> This endpoint fetches already generated or queued videos by ID.

> [card] [Clear Server Cache](https://docs.modelslab.com/enterprise-api/minimax-h3/clear-cache.md)
>
> This endpoint clears the server cache.

> [card] [Clear Server Queue](https://docs.modelslab.com/enterprise-api/minimax-h3/clear-queue.md)
>
> This endpoint clears the server queue.

> [card] [Restart Server](https://docs.modelslab.com/enterprise-api/minimax-h3/restart-server.md)
>
> This endpoint restarts the server.

> [card] [System Details](https://docs.modelslab.com/enterprise-api/minimax-h3/system-details.md)
>
> This endpoint retrieves system and server details.

> [card] [Update Server](https://docs.modelslab.com/enterprise-api/minimax-h3/update-server.md)
>
> This endpoint updates the server to the latest version.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.