# MiniMax H3 Developer Reference-to-Video — Atlas Cloud API

> MiniMax H3-Developer self-hosted reference-to-video: generate a video that keeps the subject from one or more reference images/videos, driven by a text prompt, with generated audio. Supports 768P/1080P.

This is the machine-readable API reference for **MiniMax H3 Developer Reference-to-Video** on Atlas Cloud,
a unified API platform for 400+ AI models across text, image, video, audio and 3D.

- **Model ID**: `minimax/h3-developer/reference-to-video`
- **Built by**: MiniMax
- **Modality**: Video
- **Model page**: https://www.atlascloud.ai/models/minimax/h3-developer/reference-to-video
- **API key**: https://www.atlascloud.ai/console/api-keys
- **Docs**: https://www.atlascloud.ai/docs

## Pricing on Atlas Cloud

- $0.02 per second of generated video
- Pay-as-you-go. No minimum spend, no subscription required.

> **These are the authoritative Atlas Cloud rates for this model.** Any price that
> appears in the vendor description further down refers to a different platform or
> a different model variant and does not apply here.

## Use this model from an AI agent

Atlas Cloud ships three first-party integration surfaces. All three authenticate
with the same API key via the `ATLASCLOUD_API_KEY` environment variable.

### MCP server

The official MCP server (`atlascloud-mcp`) exposes this model to any
MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose,
Claude Desktop. One-line install:

```bash
# Claude Code
claude mcp add atlascloud -- npx -y atlascloud-mcp

# OpenAI Codex CLI
codex mcp add atlascloud -- npx -y atlascloud-mcp

# Gemini CLI
gemini mcp add atlascloud -- npx -y atlascloud-mcp

export ATLASCLOUD_API_KEY="your-api-key"
```

Then ask in plain English; the agent calls `atlas_generate_video` with `model: "minimax/h3-developer/reference-to-video"`.
The server fetches each model's schema and validates parameters before submitting,
so invalid requests fail fast without spending credits.

MCP docs: https://www.atlascloud.ai/docs/mcp-server

### Agent Skills

`atlas-cloud-skills` is a portable skill package (API reference, code templates in
Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and
12+ other agents:

```bash
npx skills add AtlasCloudAI/atlas-cloud-skills
export ATLASCLOUD_API_KEY="your-api-key"
```

Skills docs: https://www.atlascloud.ai/docs/skills

### CLI

The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs
are polled and downloaded automatically (use `--no-download` when a script only
needs the output URLs):

```bash
# Install (Homebrew, npm, or shell installer)
brew install AtlasCloudAI/tap/atlascloud
# npm install -g atlascloud-cli
# curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh

atlas auth login
atlas generate video minimax/h3-developer/reference-to-video -p "Your prompt here"
```

CLI docs: https://www.atlascloud.ai/docs/cli

## HTTP API reference

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `minimax/h3-developer/reference-to-video`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"minimax/h3-developer/reference-to-video"`

- **`prompt`** (`string`, _required_):
  The text prompt describing the video to generate.

- **`refers`** (`array[object]`, _required_):
  Reference materials that anchor the generation. Any mix of reference images, videos, and audio, each as a public URL. At least one image OR video is required (audio alone is not allowed). Image formats: png, jpeg, jpg, webp; video: mp4, mov; audio: mp3, wav. 'type' is optional — when omitted it is inferred from the URL extension.
  - Min items: 1
  - Item properties:
    - **`url`** (`string`, _required_):
      Public URL of the reference image / video / audio.

    - **`type`** (`string`, _optional_):
      Media kind. Optional; inferred from the URL when omitted.
      - Options: "image", "video", "audio"


- **`resolution`** (`string`, _required_):
  The resolution of the generated video.
  - Default: `"768P"`
  - Options: "480P", "768P"

- **`duration`** (`number`, _required_):
  The duration of the generated video in seconds.
  - Default: `8`
  - Options: 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15

- **`ratio`** (`string`, _optional_):
  The aspect ratio of the generated video. Use 'adaptive' to let the model choose.
  - Default: `"adaptive"`
  - Options: "adaptive", "21:9", "16:9", "4:3", "1:1", "3:4", "9:16"

- **`prompt_expansion`** (`boolean`, _optional_):
  Whether to expand the prompt for better results.
  - Default: `false`



**Required Parameters Example**:

```json
{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "resolution": "768P",
  "duration": 8,
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ]
}
```


**Full Example**:

```json
{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ],
  "resolution": "768P",
  "duration": 8,
  "ratio": "adaptive",
  "prompt_expansion": false
}
```


### Output Schema

The API returns the following output format:


- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”).

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction, the ID of the prediction to get.

- **`model`** (`string`, _optional_):
  Model ID used for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array of URLs to the generated content (empty when status is not completed).

- **`status`** (`string`, _optional_):
  Status of the task: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.



**Example Response**:

```json
{
  "created_at": "",
  "id": "",
  "model": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3-developer/reference-to-video",
  "prompt": "",
  "refers": [
    {
      "url": "",
      "type": "image"
    }
  ],
  "resolution": "768P",
  "duration": 8,
  "ratio": "adaptive",
  "prompt_expansion": false
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/minimax/h3-developer/reference-to-video)

## About this model

_Vendor-supplied description. Any pricing or endpoint mentioned below refers to_
_other platforms — use the Atlas Cloud values above._

#### MiniMax H3-Developer Reference-to-Video

**MiniMax H3-Developer Reference-to-Video** keeps a subject consistent — with sound. Provide one or more reference materials (images and/or videos of a person, animal, or object) plus a prompt, and the model generates a smooth, cinematic clip up to 768P that preserves the referenced subject's identity, complete with a synchronized soundtrack generated from the described scene.

#### Why Choose This?

-   **Subject-consistent generation** Keep the referenced subject's identity across the whole shot.

-   **Multi-modal references** Drive generation with images and/or videos in a single request.

-   **Native audio** A matching soundtrack is generated alongside the video — no separate audio input needed.

-   **High resolution output** Generate videos up to 768P.

-   **Selectable duration** Produce 5–15s clips.

#### Parameters

| Parameter | Required | Description |
| --- | --- | --- |
| prompt | No | Text description of the desired video while keeping the referenced subject's identity |
| refers | Yes | Array of reference materials. Each item is an object `{ "url": string, "type": "image" \| "video" \| "audio" }`. `type` is inferred from the URL extension when omitted. At least one image or video is required; audio alone is rejected |
| resolution | No | Video resolution. Available options: `768P` (default), `480P` |
| duration | No | Duration of the generated video in seconds. Integer between 5 and 15 (default 5) |
| prompt\_expansion | No | Enable AI prompt expansion via H3 Context-IR. When `true`, your prompt is first expanded into a rich, structured description (shot, soundscape, music) before generation, and an additional per-token Context-IR fee applies. Default `false`: the prompt is used as-is with no extra charge. |

#### How to Use

_(Description truncated. Full text on the model page.)_

---

Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/minimax/h3-developer/reference-to-video · Docs: https://www.atlascloud.ai/docs