---
title: MiniMax H3 Max Turbo | Runware Docs
url: https://runware.ai/docs/models/minimax-h3-max-turbo
description: Distilled H3 Max video generation for faster iteration with native audio and first-to-last frame control
---
# MiniMax H3 Max Turbo

![MiniMax H3 Max Turbo](https://assets.runware.ai/covers/minimax-h3-max-turbo.jpg)

MiniMax H3 Max Turbo is a distilled, speed-focused variant of H3 Max designed to preserve its prompt adherence and visual character at higher throughput. It generates 5 to 15 second videos at 480p or 768p from text or an opening image, with optional end-frame guidance for controlled transitions and synchronized audio generated with the video. It is well suited to rapid creative iteration, interactive experiences, and high-volume production workflows.

- **Status**: live
- **ID**: `minimax:h3@max-turbo`
- Try in Playground
- **Creator**: MiniMax
- **Release Date**: September 2, 2026
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Checkpoint

## Pricing

$0.025 from, per second · ~30s per request

**Rates** (per second)

- 480p: `$0.025`
- 768p: `$0.04`

**4 example generations**

- [first-frame](https://runware.ai/docs/models/minimax-h3-max-turbo/examples#example-textile-conservator-exhibition-briefing) · 768p · 6s: `$0.12` (~13s)
- [text-to-video](https://runware.ai/docs/models/minimax-h3-max-turbo/examples#example-vertical-specialty-mushroom-harvest-b-roll) · 768×1344 · 8s: `$0.16` (~35s)
- [text-to-video](https://runware.ai/docs/models/minimax-h3-max-turbo/examples#example-semiconductor-wafer-transfer-b-roll) · 768×1344 · 8s: `$0.16` (~44s)
- [first-last-frame](https://runware.ai/docs/models/minimax-h3-max-turbo/examples#example-seed-vault-art-pop-music-video) · 768p · 10s: `$0.20` (~26s)

times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing)

## Compatibility & Validation

When `inputs.frameImages` is provided, `width/height` cannot be used.

---

When `resolution` is provided, `inputs.frameImages` is required.

---

`width` and `height` must be used together.

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `480p (~16:9)` | `832x480` |
| `480p (4:3)` | `640x480` |
| `480p (1:1)` | `480x480` |
| `480p (3:4)` | `480x640` |
| `480p (~9:16)` | `480x832` |
| `480p (~21:9)` | `960x416` |
| `768p (~16:9)` | `1344x768` |
| `768p (4:3)` | `1024x768` |
| `768p (1:1)` | `768x768` |
| `768p (3:4)` | `768x1024` |
| `768p (~9:16)` | `768x1344` |
| `768p (~21:9)` | `1536x672` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/minimax-h3-max-turbo#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/minimax-h3-max-turbo#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/minimax-h3-max-turbo#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/minimax-h3-max-turbo#request-outputformat)

- **Type**: `string`
- **Default**: `MP4`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP4\`: Widely supported video container (H.264), recommended for general use.
- \`WEBM\`: Optimized for web delivery.
- \`MOV\`: QuickTime format, common in professional workflows (Apple ecosystem).

**Allowed values**: `MP4` `WEBM` `MOV`

### [outputQuality](https://runware.ai/docs/models/minimax-h3-max-turbo#request-outputquality)

- **Type**: `integer`
- **Min**: `20`
- **Max**: `99`
- **Default**: `95`

Compression quality of the output. Higher values preserve quality but increase file size.

### [webhookURL](https://runware.ai/docs/models/minimax-h3-max-turbo#request-webhookurl)

- **Type**: `string`
- **Format**: `uri`

Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/minimax-h3-max-turbo#request-deliverymethod)

- **Type**: `string`
- **Default**: `async`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/minimax-h3-max-turbo#request-uploadendpoint)

- **Type**: `string`
- **Format**: `uri`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [safety](https://runware.ai/docs/models/minimax-h3-max-turbo#request-safety)

- **Path**: `safety.checkContent`
- **Type**: `object (2 properties)`

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/minimax-h3-max-turbo#request-safety-checkcontent)

- **Path**: `safety.checkContent`
- **Type**: `boolean`

Enable or disable content safety checking. Increases total generation time and adds a small charge on top of the generation cost.

#### [mode](https://runware.ai/docs/models/minimax-h3-max-turbo#request-safety-mode)

- **Path**: `safety.mode`
- **Type**: `string`
- **Default**: `fast`

Safety checking mode for video generation.

**Allowed values**:

- `fast` Checks key frames.
- `full` Checks all frames.

### [ttl](https://runware.ai/docs/models/minimax-h3-max-turbo#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/minimax-h3-max-turbo#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/minimax-h3-max-turbo#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Inputs**

Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object.

### [frameImages](https://runware.ai/docs/models/minimax-h3-max-turbo#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`
- **Size (each)**: `256 px to 5760 px`
- **Aspect ratio (each)**: `1:2.5 to 2.5:1`
- **File size (each)**: `up to 30 MB`

An array of frame-specific image inputs to guide video generation. Each item can be either a plain image input (UUID, URL, Data URI, or Base64) or an object that pairs an image with a target position in the video.

The `frameImages` parameter allows you to constrain specific frames within the video sequence, ensuring that particular visual content appears at designated points. Position can be specified using `frame` (named positions or frame indices) or `timestamp` (seconds), depending on model support. This is different from `referenceImages`, which provide overall visual guidance without constraining specific timeline positions.

When the `frame` parameter is omitted, automatic distribution rules apply:

- **1 image**: Used as the first frame.
- **2 images**: First and last frames.

**Examples**:

**Shorthand format:** When you don't need to specify a frame position, you can pass a plain image input directly.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402"
]
```

**Object format:** When you need to specify a position, use an object with `image` and either `frame` or `timestamp` (model-dependent).

```json
"frameImages": [
  {
    "image": "aac49721-1964-481a-ae78-8a4e29b91402",
    "frame": "first"
  }
]
```

**First and last frames:** With two images, they automatically become the first and last frames of the video sequence. You can mix shorthand and object formats.

```json
"frameImages": [
  "aac49721-1964-481a-ae78-8a4e29b91402",
  {
    "image": "3ad204c3-a9de-4963-8a1a-c3911e3afafe",
    "frame": "last"
  }
]
```

**Format 1: string[]**:

- **Type**: `string`

Image input (UUID, URL, Data URI, or Base64).

**Format 2: object[]**:

#### [image](https://runware.ai/docs/models/minimax-h3-max-turbo#request-inputs-frameimages-format-2-image)

- **Path**: `inputs.frameImages.image`
- **Type**: `string`
- **Required**: true

Image input (UUID, URL, Data URI, or Base64).

#### [frame](https://runware.ai/docs/models/minimax-h3-max-turbo#request-inputs-frameimages-format-2-frame)

- **Path**: `inputs.frameImages.frame`
- **Type**: `object`

Target frame position for the image. Supports first and last frame.

**Allowed values**:

- `first` First frame of the video.
- `last` Last frame of the video.
- `0` Frame index 0 (first frame).
- `-1` Frame index -1 (last frame).

**Core Parameters**

Primary parameters that define the task output.

### [model](https://runware.ai/docs/models/minimax-h3-max-turbo#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `minimax:h3@max-turbo`

Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router).

**Learn more** (3 resources):

- [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn)
- [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn)
- [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn)

### [positivePrompt](https://runware.ai/docs/models/minimax-h3-max-turbo#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `7000`

Text prompt describing elements to include in the generated output.

**Learn more** (1 resource):

- [Prompts](https://runware.ai/docs/learn/prompts) (learn)

### [width](https://runware.ai/docs/models/minimax-h3-max-turbo#request-width)

- **Type**: `integer`
- **Default**: `1344`
- **Paired with**: height

Width of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [height](https://runware.ai/docs/models/minimax-h3-max-turbo#request-height)

- **Type**: `integer`
- **Default**: `768`
- **Paired with**: width

Height of the generated media in pixels.

**Learn more** (2 resources):

- [Dimensions](https://runware.ai/docs/learn/dimensions) (learn)
- [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn)

### [resolution](https://runware.ai/docs/models/minimax-h3-max-turbo#request-resolution)

- **Type**: `string`

Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input.

**Allowed values**: `480p` `768p`

### [duration](https://runware.ai/docs/models/minimax-h3-max-turbo#request-duration)

- **Type**: `integer`
- **Min**: `5`
- **Max**: `15`
- **Default**: `5`

Length of the generated video in seconds. The total number of frames produced is determined by duration multiplied by the model's frame rate (fps).

### [seed](https://runware.ai/docs/models/minimax-h3-max-turbo#request-seed)

- **Type**: `integer`
- **Min**: `0`
- **Max**: `4294967295`

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [promptExpansion](https://runware.ai/docs/models/minimax-h3-max-turbo#request-settings-promptexpansion)

- **Path**: `settings.promptExpansion`
- **Type**: `string`
- **Default**: `balanced`

Level of automatic prompt rewriting applied before generation. Affects reproducibility.

**Allowed values**:

- `disabled` No prompt rewriting.
- `balanced` Balanced rewriting.
- `quality` Quality-first rewriting, at the cost of longer generation time.

## Response Parameters

### [taskType](https://runware.ai/docs/models/minimax-h3-max-turbo#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `videoInference`

Identifier for the type of task this response belongs to.

### [taskUUID](https://runware.ai/docs/models/minimax-h3-max-turbo#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier echoed from the original request, used to match async responses to their tasks.

### [videoUUID](https://runware.ai/docs/models/minimax-h3-max-turbo#response-videouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/minimax-h3-max-turbo#response-videourl)

- **Type**: `string`
- **Format**: `uri`

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/minimax-h3-max-turbo#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/minimax-h3-max-turbo#response-videodatauri)

- **Type**: `string`
- **Format**: `uri`

Data URI of the output video.

### [seed](https://runware.ai/docs/models/minimax-h3-max-turbo#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [NSFWContent](https://runware.ai/docs/models/minimax-h3-max-turbo#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/minimax-h3-max-turbo#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/minimax-h3-max-turbo/3ec8facf-8638-4e84-90f7-ba46423f084d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "1e599520-1b28-48c8-b0bf-5be4ee51e1bb",
  "model": "minimax:h3@max-turbo",
  "positivePrompt": "Photorealistic eight-second vertical stock footage inside a climate-controlled specialty mushroom farm. A dense cluster of pearl oyster mushrooms fills the foreground, growing from a suspended substrate block beneath cool white cultivation lights. Begin with an extreme close-up of condensation beads trembling along the pale gills as fine irrigation mist drifts through the frame. At two seconds, a farm worker's clean dark-green nitrile-gloved hand enters slowly from the lower right, supports the cluster, and twists it free in one careful, believable harvesting motion. As the mushrooms lift away, the camera gently dollies backward and tilts up, revealing repeating rows of hanging grow blocks fading into humid blue-gray depth. End with the harvested cluster held upright near the center while mist catches the light behind it. Smooth stabilized camera movement, shallow depth of field transitioning to a slightly wider view, accurate hand anatomy, realistic mushroom texture and weight, restrained cool sage, ivory, and steel-blue palette, soft diffused highlights, natural documentary cinematography, no time-lapse, no cuts, no faces, no labels, no logos, no text. Subtle synchronized ambience of ventilation fans, faint water hiss, glove rustle, and a soft fibrous snap during harvest.",
  "width": 768,
  "height": 1344,
  "duration": 8,
  "settings": {
    "promptExpansion": "quality"
  }
}
```

---

### text-to-video (text-to-video)

[Watch video](https://assets.runware.ai/examples/minimax-h3-max-turbo/930acb21-4b1d-469d-bc25-bae2fb5ad853.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "16fb3e15-b845-4e55-8c10-be532562c075",
  "model": "minimax:h3@max-turbo",
  "positivePrompt": "Photorealistic premium industrial b-roll, one continuous 8-second shot inside a state-of-the-art semiconductor cleanroom. Portrait composition. Begin with a close macro view of a silicon wafer cassette beneath cool white cleanroom lights; a precision robotic end effector enters the frame and gently lifts one perfectly rigid circular wafer. As the wafer rises, the camera smoothly tracks upward and makes a subtle arc around it, revealing shifting iridescent bands of magenta, cyan, gold, and violet across its microscopic circuit pattern. Cold white machinery and a softly blurred technician in a full cleanroom suit remain in the deep background. The robot carries the wafer toward a polished inspection stage and lowers it precisely into place during the final two seconds. Finish with a controlled rack focus from the robotic gripper to the intricate geometric die pattern on the settled wafer. Sterile high-tech atmosphere, crisp metallic detail, realistic reflections, shallow depth of field, restrained cinematic contrast, smooth stabilized camera motion, accurate mechanical movement, no cuts, no logos, no legible text, no interface graphics. Subtle synchronized cleanroom ventilation hum and quiet servo movement, no speech and no music.",
  "width": 768,
  "height": 1344,
  "duration": 8,
  "settings": {
    "promptExpansion": "quality"
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/minimax-h3-max-turbo/65e714cf-a43e-490d-bdce-0836b413807d.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "bc33bf71-d326-437d-8346-b5f1f120c73f",
  "model": "minimax:h3@max-turbo",
  "positivePrompt": "Continue naturally from the supplied first frame as a polished six-second museum guide presenter clip. The textile conservator maintains warm eye contact with the lens, takes a small breath, then speaks directly to visitors with precise synchronized lip movement: “This indigo coat survived two centuries. Low light lets its original blue survive another.” Her expression shifts from thoughtful pride to a gentle reassuring smile. She makes one restrained open-palm gesture toward the softly blurred coat behind her, then returns her gloved hand to a relaxed position. Preserve her identity, clothing, studio arrangement, and the artifact’s appearance throughout. Use a single uninterrupted medium close-up with a barely perceptible slow camera push-in, stable documentary framing, realistic blinking, subtle breathing, natural facial motion, and accurate hand anatomy. Low amber conservation lighting contrasts with deep indigo, dark teal, muted ochre, and verdigris tones. Clear female speech with intimate museum-room acoustics and faint quiet room tone; no music, captions, graphics, logos, cuts, or additional people.",
  "resolution": "768p",
  "duration": 6,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/b8daac88-5f89-441b-9d42-4a4175fa2fd8.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

### first-last-frame (first-last-frame)

[Watch video](https://assets.runware.ai/examples/minimax-h3-max-turbo/343c424c-9988-468a-ba95-15e62e0d8c2b.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "47b5f1a2-1570-4961-aa79-79a90f7ee91b",
  "model": "minimax:h3@max-turbo",
  "positivePrompt": "Create a finished ten-second art-pop music-video performance segment as one continuous, unbroken shot, transitioning precisely from the supplied first frame to the supplied last frame. Preserve the vocalist’s identity, blunt black bob, ivory sculptural coat, charcoal clothing, proportions, and position, as well as the underground seed vault’s architecture and symmetrical cabinet layout. Begin in near stillness with the camera making a slow, perfectly centered dolly toward the vocalist as she looks directly into the lens and starts singing. On successive musical beats, steel specimen drawers unlatch and slide open in a wave traveling from the foreground toward the back of the vault. Air builds gradually: first a few pale seeds and translucent husks drift past, then blank archival envelopes and thousands of seeds rise into a graceful helical current around her without obscuring her face. Her coat hem responds naturally to the wind while she remains grounded and commanding. The cold cyan practical lighting gradually blooms into rich amber backlight with cyan edges, turning the austere archive into a ceremonial, kinetic performance space. End on the supplied final composition with every drawer open and the airborne spiral fully formed. Cinematic live action, brutalist archival production design, elegant restrained choreography, realistic cloth and particle physics, subtle 35mm grain, deep perspective, smooth stabilized movement, consistent anatomy, no cuts, no extra performers, no logos, captions, or readable text. Generate synchronized audio: a dark 96 BPM art-pop track with bowed double bass, dry analog kick, granular seed-rattle percussion, distant choral harmonics, and cabinet latches striking rhythmically. The vocalist sings clearly and intimately: “What we buried learned to breathe; every sleeping field remembers me.” Her mouth movements align naturally with the lyric, and the arrangement swells as the drawers open.",
  "resolution": "768p",
  "duration": 10,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/6d4ec0f8-712a-439a-b30b-4b54e900c038.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/2d123046-197b-4d53-9340-e91ccc8c84b1.jpg",
        "frame": "last"
      }
    ]
  }
}
```