# MiniMax-H3 API

> a general-purpose multimodal generation model. H3 understands unified context across text, images, video, and audio, generating video with native stereo sound, up to 15 seconds at 2K resolution

- Model ID: `MiniMax-H3`
- Provider: MiniMax
- Price: Provider cost $0.08–0.13 / output second + input materials
- Web page: https://scalingtensor.com/models/MiniMax-H3

## How to call it

Authenticate with the `apiKey` request header. Submit a job, then poll for the result:

1. `POST https://restapi.scalingtensor.com/api/media/generate` with JSON `{ "model": "<model ID>", "params": { ... } }`. The response `data.jobId` identifies the job.
2. `GET https://restapi.scalingtensor.com/api/media/result?jobId=<jobId>` until the status is `completed` or `failed`.
3. A response `code` of 0 means success; otherwise read `msg`.

```bash
curl --request POST 'https://restapi.scalingtensor.com/api/media/generate' \
  --header 'apiKey: YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "model": "MiniMax-H3",
  "params": {
    "model": "MiniMax-H3",
    "ratio": "16:9",
    "content": [
      {
        "text": "Epic space-opera theatrical teaser: a female captain stands alone before a massive observation window as the last fleet gathers and jumps away in a blinding flash, the bridge shaking, leaving her behind.",
        "type": "text"
      }
    ],
    "duration": 5,
    "resolution": "2K"
  }
}'
```

## Input parameters

Parameters go inside the `params` object.

| Name | Type | Required | Description |
| --- | --- | --- | --- |
| `content` | object[] | true | Array of multimodal input describing the information used to generate the video. Each element is distinguished by type (text / image_url / video_url / audio_url) and can be labeled with a role. Every request must include one non-empty text item (the prompt is required); otherwise a parameter error is returned. |
| `resolution` | enum<string> | true | Video resolution. Availability differs by model: MiniMax-H3:768P,2K; MiniMax-H3-Max:480P,768P (defaults to 768P; 2K is not supported). Available options:480P,768P,2K. |
| `duration` | enum<integer> | true | Duration of the generated video in seconds. Required, integer. Available values differ by model: MiniMax-H3:4–15; MiniMax-H3-Max:5–15 (4 seconds is not supported). Available options:4,5,6,7,8,9,10,11,12,13,14,15. |
| `ratio` | enum<string> | false | Aspect ratio of the generated video. Defaults to adaptive (the most suitable ratio is chosen automatically based on the input; the actual ratio can be read from the ratio field of the query endpoint). Available values: adaptive,21:9,16:9,4:3,1:1,3:4,9:16. |
| `extra` | object | false | Additional generation options for MiniMax-H3-Max. Currently only prompt_expansion_mode is supported. If extra or this property is omitted, balanced is used. Do not pass balance, an empty string, a Boolean value, or other undeclared fields. |
| `callback_url` | string | false | Callback URL for task status changes. Once configured, the MiniMax server first sends a verification request containing a challenge field (you must return the challenge unchanged within 3 seconds to complete verification); after verification succeeds, it POSTs an update to this URL whenever the task status changes. The push body has the same structure as the response of the Query Task endpoint. |

## FAQ

### How much does the MiniMax-H3 API cost?

MiniMax-H3 is billed at the provider's actual cost for each job ($0.08–0.13 / output second + input materials). The charge is deducted from your prepaid ScalingTensor wallet.

### How do I call the MiniMax-H3 API?

Send POST /api/media/generate with "model": "MiniMax-H3" and the parameters in a params object, using your apiKey header. The call returns a jobId. Poll GET /api/media/result?jobId=... until the status is completed, then read the output URL from the result.

### Which parameters does MiniMax-H3 accept?

Required: content, resolution and duration. Optional: ratio, extra and callback_url. The parameter table on this page describes each one.

### Do I need a MiniMax account to use MiniMax-H3?

No. You call MiniMax-H3 with your ScalingTensor API key and pay from your ScalingTensor wallet. The same key works for every other model in the catalog.