MiniMax Hailuo 02
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.
API Options
Platform-level options for task execution and delivery.
-
taskType
string required value: videoInference -
Identifier for the type of task being performed
-
taskUUID
string required UUID v4 -
UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.
-
outputType
string default: URL -
Video output type.
Allowed values 1 value
-
outputFormat
string default: MP4 -
File format for the generated video.
Allowed values 3 values
-
outputQuality
integer min: 20 max: 99 default: 95 -
Compression quality of the output. Higher values preserve quality but increase file size.
-
webhookURL
string URI -
Specifies a webhook URL where JSON responses will be sent 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 PLATFORM
- Webhooks
-
deliveryMethod
string default: async -
Determines how the API delivers task results.
Allowed values 1 value
- Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. Required for long-running tasks like video generation.
Learn more 1 resource
- Task Polling PLATFORM
-
uploadEndpoint
string 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.
// 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.jpgThe content data will be sent as the request body to the specified URL when generation is complete.
-
safety
object -
Content safety checking configuration for video generation.
Properties 2 properties
-
safety»checkContentcheckContent
boolean default: false -
Enable or disable content safety checking. When enabled, defaults to 'fast' mode.
-
safety»modemode
string default: none -
Safety checking mode for video generation.
Allowed values 3 values
- Disables checking.
- Checks key frames.
- Checks all frames.
-
-
ttl
integer min: 60 -
Time-to-live (TTL) in seconds for generated content. Only applies when
outputTypeis 'URL'.
-
includeCost
boolean default: false -
Include task cost in the response.
-
numberResults
integer min: 1 max: 20 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.
inputs object.-
inputs»frameImagesframeImages
array of objects min items: 1max items: 2 -
For image-to-video workflows, each item can be a plain image input (UUID, URL, Data URI, or Base64), or an object with an explicit
frameposition.When no frame is specified, images are distributed automatically:
- 1 image: First frame.
- 2 images: First and last frames.
- 3+ images: First and last frames, intermediates evenly spaced.
Properties 2 properties
-
inputs»frameImages»imageimage
string required -
Image input (UUID, URL, Data URI, or Base64).
-
inputs»frameImages»frameframe
object -
Target frame position for the image. Supports first and last frame.
Allowed values 4 values
- First frame of the video.
- Last frame of the video.
- Frame index 0 (first frame).
- Frame index -1 (last frame).
Generation Parameters
Core parameters for controlling the generated content.
-
model
string required value: minimax:3@1 -
Identifier of the model to use for generation.
Learn more 3 resources
-
positivePrompt
string required min: 2 max: 2000 -
Text prompt describing elements to include in the generated output.
Learn more 2 resources
-
width
integer paired with height -
Width of the generated media in pixels.
Learn more 2 resources
-
height
integer paired with width -
Height of the generated media in pixels.
Learn more 2 resources
-
duration
float -
Duration of the generation in seconds. Total frames = duration × fps.
-
fps
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.
providerSettings.minimax object.-
providerSettings»minimax»promptOptimizerpromptOptimizer
boolean default: false -
Enable automatic prompt optimization. Affects reproducibility.
Volcanic Freight Train Pursuit
{
"taskType": "videoInference",
"taskUUID": "5481c77d-0596-4375-918e-5e3fc20504f2",
"model": "minimax:3@1",
"positivePrompt": "A cinematic action sequence at a black volcanic plain during golden overcast light: a sleek armored freight train races across elevated steel tracks while two magnetic hoverbikes weave alongside it, scattering sparks from the rails. The camera begins with a low tracking shot beside the wheels, then rises into a sweeping aerial arc revealing rivers of glowing lava far below and ash streaming through the air. One rider leaps a broken section of track, barely landing on a cargo car, while another skims past jagged basalt towers as heat distortion ripples across the frame. Dense smoke plumes, whipping fabric, debris, convincing momentum, realistic suspension and impact reactions, polished blockbuster lighting, tactile metal surfaces, cinematic depth, intense but grounded action, premium trailer aesthetic.",
"width": 1920,
"height": 1080,
"duration": 6,
"fps": 25,
"providerSettings": {
"minimax": {
"promptOptimizer": false
}
}
}{
"taskType": "videoInference",
"taskUUID": "5481c77d-0596-4375-918e-5e3fc20504f2",
"videoUUID": "352b1681-5735-42d1-8da9-a780e3f14aa4",
"videoURL": "https://vm.runware.ai/video/os/a12d13/ws/5/vi/352b1681-5735-42d1-8da9-a780e3f14aa4.mp4",
"seed": 2061368469,
"cost": 0.49
}Aerial Ice Harbor Exodus
{
"taskType": "videoInference",
"taskUUID": "ecd42cca-ca75-4222-86b5-57b595a04517",
"model": "minimax:3@1",
"positivePrompt": "Starting from the provided first frame, create a high-motion cinematic aerial sequence over a frozen harbor at dawn. The camera dives forward and banks slightly as ice sheets crack apart around stranded cargo ships. Tugboats surge through narrow channels, throwing spray and shattered ice. Emergency vehicles race along the docks with flashing beacons, tiny figures scatter across catwalks, cranes swing cautiously over containers, snow gusts streak across the lens, and a distant ship horn implies urgency. Emphasize realistic physics, heavy machinery momentum, turbulent water, drifting frost, layered depth, dramatic scale, polished commercial-trailer look, natural cold lighting, strong atmosphere, coherent motion, and a tense evacuation mood.",
"width": 1920,
"height": 1080,
"duration": 6,
"fps": 25,
"providerSettings": {
"minimax": {
"promptOptimizer": true
}
},
"inputs": {
"frameImages": [
{
"image": "https://assets.runware.ai/assets/inputs/e9d9e021-000d-4643-b5ad-e56c19a70316.jpg",
"frame": "first"
}
]
}
}{
"taskType": "videoInference",
"taskUUID": "ecd42cca-ca75-4222-86b5-57b595a04517",
"videoUUID": "7cc7aff3-93d8-4e63-a851-7ec51be14a93",
"videoURL": "https://vm.runware.ai/video/os/a11d13/ws/5/vi/7cc7aff3-93d8-4e63-a851-7ec51be14a93.mp4",
"seed": 925574306,
"cost": 0.49
}Abandoned Aquarium Tunnel Escape
{
"taskType": "videoInference",
"taskUUID": "a0e7fe12-b6f9-4df6-a180-6073dde76d8e",
"model": "minimax:3@1",
"positivePrompt": "Create a polished cinematic action shot that transitions naturally between the provided first and last frame images. A lone courier races through a collapsing public aquarium passage as pressure fractures spread across the massive viewing panels. Water begins leaking, then surges in violent streams, fish scatter in panic, warning lights flicker, loose signage and benches slide across the floor, and the camera tracks with urgent forward motion. Emphasize realistic physics: splashing water, drifting bubbles, fragments of acrylic, rolling debris, fabric and straps reacting to momentum, footsteps slipping then recovering. Build escalating tension toward a final breakout into a vast atrium flooded by a roaring cascade from above. High detail, commercial trailer energy, dramatic lighting contrast, strong motion coherence, believable scale, dynamic perspective, immersive environment, no text overlays.",
"width": 1920,
"height": 1080,
"duration": 6,
"fps": 25,
"providerSettings": {
"minimax": {
"promptOptimizer": false
}
},
"inputs": {
"frameImages": [
{
"image": "https://assets.runware.ai/assets/inputs/c92c52f0-41a4-4a51-b765-ade0fb706bb1.jpg",
"frame": "first"
},
{
"image": "https://assets.runware.ai/assets/inputs/35245028-dafc-4d88-ade7-604d22a5979e.jpg",
"frame": "last"
}
]
}
}{
"taskType": "videoInference",
"taskUUID": "a0e7fe12-b6f9-4df6-a180-6073dde76d8e",
"videoUUID": "114081bf-8a1f-46dc-84bc-8b7242d71789",
"videoURL": "https://vm.runware.ai/video/os/a08d21/ws/5/vi/114081bf-8a1f-46dc-84bc-8b7242d71789.mp4",
"seed": 1588222136,
"cost": 0.49
}Stormbreaker Freight Train Pursuit
{
"taskType": "videoInference",
"taskUUID": "c2cdf677-710a-4196-bf68-f28f3ca9a44b",
"model": "minimax:3@1",
"positivePrompt": "Using the provided first frame as the opening shot, create a tense cinematic pursuit sequence. The silver freight train thunders forward across elevated tracks over flooded grasslands while a lone rider on a black electric motorcycle accelerates alongside on the maintenance road. Strong wind drives sheets of water sideways, puddles burst under the tires, and spray peels off the train wheels. The camera begins low and wide near the road, then sweeps forward in a fast tracking move, briefly rises to reveal the vast storm front, and settles into a close parallel run beside the rider. Preserve realistic vehicle scale, traction, suspension response, wheel rotation, water interaction, and believable momentum. Dramatic blue-gray atmosphere, sodium safety lights flickering on the train cars, high contrast, premium trailer-grade cinematography, intense but grounded action.",
"width": 1920,
"height": 1080,
"duration": 6,
"fps": 25,
"providerSettings": {
"minimax": {
"promptOptimizer": false
}
},
"inputs": {
"frameImages": [
{
"image": "https://assets.runware.ai/assets/inputs/3ff7eb00-c45d-4e63-a88c-dddc89bd6f52.jpg",
"frame": "first"
}
]
}
}{
"taskType": "videoInference",
"taskUUID": "c2cdf677-710a-4196-bf68-f28f3ca9a44b",
"videoUUID": "383528a7-9286-49c9-b4e1-4792f042b9ec",
"videoURL": "https://vm.runware.ai/video/os/a15d18/ws/5/vi/383528a7-9286-49c9-b4e1-4792f042b9ec.mp4",
"seed": 1389354438,
"cost": 0.49
}Wind-Torn Coastal Freight Platform
{
"taskType": "videoInference",
"taskUUID": "68e1842e-a8b5-40b5-93ee-e7c802f63f47",
"model": "minimax:3@1",
"positivePrompt": "A tense cinematic aerial-drama sequence on a remote ocean freight platform during violent morning wind. Start grounded on the deck with the rescue helicopter idle, then build into a forceful takeoff as rotors accelerate, tarps snap, puddles ripple, sea spray blasts sideways, crew members lean into the gusts, straps and loose fabric react with convincing physics, camera pushes forward with subtle handheld energy, realistic metal reflections, natural motion blur, premium commercial cinematography, coherent geography, storm clouds opening toward the horizon by the final frame.",
"width": 1920,
"height": 1080,
"duration": 6,
"fps": 25,
"providerSettings": {
"minimax": {
"promptOptimizer": false
}
},
"inputs": {
"frameImages": [
{
"image": "https://assets.runware.ai/assets/inputs/29b1d629-035e-4fc4-a207-f11c2543b926.jpg",
"frame": "first"
},
{
"image": "https://assets.runware.ai/assets/inputs/1483289a-907b-43af-9955-866e1fb078e1.jpg",
"frame": "last"
}
]
}
}{
"taskType": "videoInference",
"taskUUID": "68e1842e-a8b5-40b5-93ee-e7c802f63f47",
"videoUUID": "3cca68ca-d24c-40e2-a5c1-f7bbd1ee6978",
"videoURL": "https://vm.runware.ai/video/os/a15d18/ws/5/vi/3cca68ca-d24c-40e2-a5c1-f7bbd1ee6978.mp4",
"seed": 428555498,
"cost": 0.49
}