# MiniMax Music 3 API

> Full songs with vocals from your lyrics and a style description, up to 5 minutes.

MiniMax Music 3 sings your lyrics over a complete arrangement. Describe genre, tempo, key, mood, vocals and instruments in the prompt and mark the song structure in the lyrics with tags such as [verse], [chorus] and [bridge], each on its own line. The duration (1 to 300 seconds, 60 by default) is an upper bound; the song may end earlier.

- Model id: `minimax/music-3`
- Made by: MiniMax
- Category: Text to Music
- Output: audio
- Price: $0.002 / second (60 s ≈ $0.12) (cheapest run $0.12 (120 API credits))
- Run: `POST https://api.doitong.com/v1/run/minimax/music-3`
- Quote: `POST https://api.doitong.com/v1/quote/minimax/music-3`
- Docs page: https://doitong.com/developers/models/minimax/music-3

## Pricing

Price: **$0.002 / second (60 s ≈ $0.12)**. Billed per second of output (`duration`, default 60).

The full example input below costs $0.06 = 60 API credits (30 s × 2 API credits).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.com/v1/quote/minimax/music-3` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `prompt` |  | string | yes |  |  | Music-generation prompt that can use a Structured Caption for precise control: combine section-specific arrangement and vocal details with global metadata specifying genre, BPM, key, and emotional progression. A general description covers the desired style and mood, how vocals and instruments are used, and the arrangement. |
| `lyrics` |  | string | yes |  |  | Lyrics to be sung; any words sharing a line with a leading structure tag are discarded under the model's input contract. Keep each tag on a separate line, including [intro], [verse], [pre-chorus], [chorus], [post-chorus], [bridge], [instrumental], [solo] and [outro]. |
| `duration` |  | number | no | `60` | 1 – 300 | Audio duration limit, measured in seconds, rather than a guaranteed output length. The response reports the actual duration, which can be shorter if generation stops early. |
| `seed` |  | integer \| null | no |  |  | Seed for reproducible generation, chosen randomly unless you supply a value. |
| `num_inference_steps` |  | integer | no | `30` | 1 – 100 | Euler step count for flow matching within each 8-second denoising chunk. |
| `guidance_scale` |  | number | no | `1.7` | 0 – 20 | Classifier-free guidance strength during flow matching. |

## Example input

Required parameters only:

```json
{
  "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
  "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe"
}
```

A fuller example:

```json
{
  "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
  "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
  "duration": 30
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/minimax/music-3?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
    "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
    "duration": 30
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/minimax/music-3?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
    "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
    "duration": 30
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
    "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
    "duration": 30,
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/minimax/music-3", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.com/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "minimax/music-3",
      "input": {
        "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
        "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
        "duration": 30
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "minimax/music-3",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 60,
    "usd": "0.06",
    "charged": 60,
    "refunded": 0
  },
  "input": {
    "prompt": "Genre: acoustic pop. BPM: 96. Key: C major. Warm and intimate, soft female vocal, guitar and light piano",
    "lyrics": "[verse]\nMorning light filtering through the pine\nEvery quiet street is yours and mine\n[chorus]\nSoftly the world begins to breathe",
    "duration": 30
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "duration": 5
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio` | object {url, content_type, file_name, file_size} | Output audio file in stereo WAV format, using 44.1 kHz and 16-bit samples. |
| `seed` | integer | Random seed used during generation. |
| `duration` | number | Reports how many seconds of audio were actually generated, which is not necessarily as long as requested. |

## Related models

- [MiniMax (Hailuo AI) Music](https://doitong.com/developers/models/minimax-music.md) (`minimax-music`): $0.035 / request
- [MiniMax (Hailuo AI) Music v1.5](https://doitong.com/developers/models/minimax-music/v1.5.md) (`minimax-music/v1.5`): $0.03 / request
- [Minimax Music](https://doitong.com/developers/models/minimax-music/v2.md) (`minimax-music/v2`): $0.03 / request
- [Minimax Music 2.5](https://doitong.com/developers/models/minimax-music/v2.5.md) (`minimax-music/v2.5`): $0.15 / request
- [Minimax Music 2.6](https://doitong.com/developers/models/minimax-music/v2.6.md) (`minimax-music/v2.6`): $0.15 / request
- [ACE Step](https://doitong.com/developers/models/ace-step.md) (`ace-step`): $0.0002 / second
- [ACE Step Audio Inpaint](https://doitong.com/developers/models/ace-step/audio-inpaint.md) (`ace-step/audio-inpaint`): $0.0002 / second of input audio
- [ACE Step Audio Outpaint](https://doitong.com/developers/models/ace-step/audio-outpaint.md) (`ace-step/audio-outpaint`): $0.0002 / second of output audio

## Links

- HTML page: https://doitong.com/developers/models/minimax/music-3
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=minimax/music-3
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.com/v1/models/minimax/music-3