---
title: MiniMax Hailuo 02 | Runware Docs
url: https://runware.ai/docs/models/minimax-hailuo-02
description: Cinematic AI video model for viral and commercial clips
---
# MiniMax Hailuo 02

![MiniMax Hailuo 02](https://assets.runware.ai/covers/minimax-hailuo-02.jpg)

MiniMax Hailuo 02 is a 1080p AI video model for cinematic, high motion scenes. It converts text prompts or still images into short, polished clips with strong instruction following and realistic physics. Ideal for commercial spots, trailers, music promos, and social shorts.

- **Status**: live
- **ID**: `minimax:3@1`
- Try in Playground
- **Creator**: MiniMax
- **Release Date**: June 19, 2025
- **Zero Data Retention**: Yes
- **Capabilities**: Text to Video, Image to Video, Checkpoint

## Pricing

$0.056 from, per second · ~2m 43s per request

**Rates** (per second)

- 768p: `$0.056`
- 1080p: `$0.0817`

**4 example generations**

- [first-last-frame](https://runware.ai/docs/models/minimax-hailuo-02/examples#example-historic-stone-laser-cleaning-reel) · 1366×768 · 6s: `$0.28` (~1m 48s)
- [text-to-video](https://runware.ai/docs/models/minimax-hailuo-02/examples#example-forensic-botany-docuseries-title-teaser) · 1080p · 6s: `$0.49` (~2m 52s)
- [text-to-video](https://runware.ai/docs/models/minimax-hailuo-02/examples#example-sculptural-hearing-jewelry-fashion-reel) · 1080p · 6s: `$0.49` (~2m 34s)
- [first-frame](https://runware.ai/docs/models/minimax-hailuo-02/examples#example-couture-beekeeping-suit-showcase-reel) · 1366×768 · 10s: `$0.56` (~4m 55s)

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

## Compatibility & Validation

Either provide `inputs.frameImages`, or specify `width/height`.

---

Parameter constraints vary based on the configuration:

| Dimensions | duration |
| --- | --- |
| `1920x1080` | `6` |
| `Other` | `6` `10` |

---

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

---

The following dimension combinations are supported:

| Configuration | Dimensions |
| --- | --- |
| `720p (16:9)` | `1366x768` |
| `1080p (16:9)` | `1920x1080` |

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/minimax-hailuo-02#request-tasktype)

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

Identifier for the type of task being performed.

### [taskUUID](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02#request-outputtype)

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

Video output type.

**Allowed values**: `URL`

### [outputFormat](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02#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-hailuo-02#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-hailuo-02#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-hailuo-02#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-hailuo-02#request-safety)

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

Content safety checking configuration for video generation.

#### [checkContent](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02#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-hailuo-02#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-hailuo-02#request-includecost)

- **Type**: `boolean`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02#request-inputs-frameimages)

- **Path**: `inputs.frameImages`
- **Type**: `array of strings or objects`
- **Min items**: `1`
- **Max items**: `2`

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-hailuo-02#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-hailuo-02#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-hailuo-02#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `minimax:3@1`

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-hailuo-02#request-positiveprompt)

- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `2000`

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-hailuo-02#request-width)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **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-hailuo-02#request-height)

- **Type**: `integer`
- **Required**: conditional — Required when inputs.frameImages is not provided
- **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)

### [duration](https://runware.ai/docs/models/minimax-hailuo-02#request-duration)

- **Type**: `integer`

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).

### [fps](https://runware.ai/docs/models/minimax-hailuo-02#request-fps)

- **Type**: `integer`
- **Value**: `25`

Frames per second for video generation. Higher values create smoother motion but require more processing time.

**Provider Settings**

Parameters specific to this model provider. These must be nested inside the \`providerSettings.minimax\` object.

### [promptOptimizer](https://runware.ai/docs/models/minimax-hailuo-02#request-providersettings-minimax-promptoptimizer)

- **Path**: `providerSettings.minimax.promptOptimizer`
- **Type**: `boolean`

Automatic prompt optimization. Affects reproducibility.

## Response Parameters

### [taskType](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02#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-hailuo-02#response-videouuid)

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

UUID of the output video.

### [videoURL](https://runware.ai/docs/models/minimax-hailuo-02#response-videourl)

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

URL of the output video.

### [videoBase64Data](https://runware.ai/docs/models/minimax-hailuo-02#response-videobase64data)

- **Type**: `string`

Base64-encoded video data.

### [videoDataURI](https://runware.ai/docs/models/minimax-hailuo-02#response-videodatauri)

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

Data URI of the output video.

### [NSFWContent](https://runware.ai/docs/models/minimax-hailuo-02#response-nsfwcontent)

- **Type**: `boolean`

Flag indicating if NSFW content was detected.

### [cost](https://runware.ai/docs/models/minimax-hailuo-02#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-hailuo-02/68857806-b236-459c-bf69-73ffa7710bfe.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "798e413e-4c6f-439f-b77d-ed1fcc0609c7",
  "model": "minimax:3@1",
  "positivePrompt": "A polished six-second title sequence for a premium forensic botany docuseries, presented as one continuous photorealistic shot. Inside a secure evidence greenhouse at night, a forensic botanist in a dark laboratory coat walks beside rows of sealed glass specimen cabinets, carrying a stainless-steel tray with a single pressed fern fragment. She stops beneath a scanning lamp and smoothly slides the tray into its illuminated cradle. The camera begins inches above wet leaves in extreme macro, then glides forward between foliage and rises into a precise over-the-shoulder composition as the tray enters the scanner. Ventilation fans stir leaves, condensation runs down glass, suspended pollen drifts through narrow beams of emerald and amber light, and the scanner casts a moving white line across the specimen. As the scan passes, fine veins and evidence markings resolve into the elegant engraved title VERDANT EVIDENCE on the dark tray surface. Hold the final centered title for readability while the botanist remains softly silhouetted behind it. Restrained prestige-documentary art direction, deep forest green, oxidized brass, charcoal black, clinical highlights, realistic optics, shallow depth of field, subtle film grain, controlled suspense, no additional words or logos.",
  "width": 1920,
  "height": 1080,
  "duration": 6,
  "fps": 25,
  "providerSettings": {
    "minimax": {
      "promptOptimizer": true
    }
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/minimax-hailuo-02/85f48288-9754-4c57-8d1b-5293295c6341.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "73a8673d-6265-4e5e-973c-ce2bf339372e",
  "model": "minimax:3@1",
  "positivePrompt": "A polished six-second luxury fashion product reel for sculptural hearing jewelry. In a sunlit Bauhaus-inspired salon, a poised silver-haired woman in a minimalist ivory high-neck dress wears a clearly visible cobalt-blue hearing device with a slender brushed-silver ear cuff and tiny coral enamel detail. Begin in an extreme close profile focused sharply on the device, revealing its premium materials and precise fit. She slowly lifts her chin and turns toward camera while one hand gently brushes her hair behind the ear, keeping the product unobstructed. The camera performs a smooth controlled arc from profile into a refined three-quarter portrait, subtly pulling back while maintaining crisp focus on the ear jewelry. Large translucent acrylic mobiles in cobalt, coral, and pale amber rotate slowly in the background; soft geometric reflections drift across the cream walls and a faint breeze moves loose strands of hair and sheer curtains. Warm directional afternoon light, clean editorial styling, realistic skin texture, elegant restrained movement, shallow depth of field, premium fashion-film finish, accurate anatomy and product continuity. No text, logos, interface elements, cuts, or additional people.",
  "width": 1920,
  "height": 1080,
  "duration": 6,
  "fps": 25,
  "providerSettings": {
    "minimax": {
      "promptOptimizer": true
    }
  }
}
```

---

### first-frame (first-frame)

[Watch video](https://assets.runware.ai/examples/minimax-hailuo-02/d7c86cf9-df33-4b7f-ad92-1f1a52cc57fb.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "4d6f9ff5-cf04-4d80-a3d4-d967916297dc",
  "model": "minimax:3@1",
  "positivePrompt": "Continue naturally from the opening fashion photograph as a polished 10-second protective-workwear showcase. The beekeeper begins walking slowly toward camera along the glasshouse aisle while the camera performs a smooth low dolly backward and subtle clockwise arc, preserving her full silhouette and the suit’s ivory tailoring. Her canvas sleeves crease realistically, utility pockets shift with each step, leather gloves swing gently, and the fine veil catches amber highlights. A soft breeze moves the rosemary and lifts the veil’s outer fabric without exposing her face. Bees flow around her in believable loose spirals, passing near the lens with natural depth of field rather than forming patterns. Midway, she turns one shoulder toward the light and calmly raises a wooden honey frame, revealing brass fasteners, reinforced cuffs, and precise seam construction. Sunbeams slide across the mesh and warm honeycomb; tiny airborne pollen glows in the backlight. Finish in a confident three-quarter hero pose beside a pale hive as the camera eases closer to a waist-up product view, honey frame held at her side. Premium agricultural fashion editorial, restrained choreography, warm honey gold, sage and chalk palette, photorealistic fabric physics, cinematic 35mm lens, elegant continuous shot, no cuts, no captions, no logos.",
  "width": 1366,
  "height": 768,
  "duration": 10,
  "fps": 25,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/dd9c326a-6a09-4f3c-9f84-67831e674432.jpg",
        "frame": "first"
      }
    ]
  }
}
```

---

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

[Watch video](https://assets.runware.ai/examples/minimax-hailuo-02/db8a594e-4e27-4727-b814-478e44917055.mp4)

```json
{
  "taskType": "videoInference",
  "taskUUID": "c281db32-1819-49de-9e10-78ac7eeeb86c",
  "model": "minimax:3@1",
  "positivePrompt": "Create a polished six-second social media service ad connecting the supplied before and after frames. Maintain the exact limestone lion corbel, conservator, workbench, studio, lighting and composition throughout. Begin on the soot-blackened carving. The conservator steadily sweeps the handheld pulsed-laser wand from left to right across the lion's face and mane. A narrow scanning line travels with the wand; black contamination curls away as a delicate gray plume and tiny dry flakes, revealing pale honey limestone in a crisp advancing band. Show realistic hand movement, cable drag, airborne dust and progressive cleaning—no melting, fire, dramatic sparks or damage to the stone. The camera performs a subtle slow push-in with gentle parallax while keeping the lion's eyes sharp. Finish precisely on the clean endpoint with the wand at the right cheek and a few final soot particles settling onto the steel bench. Premium architectural-conservation cinematography, tactile macro detail, restrained charcoal, limestone cream and teal palette, credible workshop atmosphere, no captions, logos or interface graphics.",
  "width": 1366,
  "height": 768,
  "duration": 6,
  "fps": 25,
  "inputs": {
    "frameImages": [
      {
        "image": "https://assets.runware.ai/assets/inputs/c53fd008-1bc2-4741-8619-5051aaec6773.jpg",
        "frame": "first"
      },
      {
        "image": "https://assets.runware.ai/assets/inputs/5208e2d2-81a2-4b59-935a-a07dbb8a21ce.jpg",
        "frame": "last"
      }
    ]
  }
}
```