Hailuo API Generate Video

Hailuo API provides video generation services with various models supporting text-to-video and image-to-video conversions.

Pricing

Model	Price (USD)	Special Requirements
t2v-01	$0.20	None
i2v-01	$0.20	None
i2v-01-director	$0.20	None
t2v-01-director	$0.20	None
i2v-01-live	$0.20	None
s2v-01	$0.30	Must detect human face in input image

Model Requirements

Text-to-Video (t2v-01, t2v-01-director)

Required fields: prompt

Optional fields: expand_prompt

image_url should not be provided

Image-to-Video (i2v-01, i2v-01-live, i2v-01-director)

Required fields: image_url

Optional fields: prompt, expand_prompt

Subject Reference Video (s2v-01)

Required fields: prompt, image_url

Optional fields: expand_prompt

Input image must contain detectable human face

Higher pricing tier ($0.30 per generation)

Input Constraints

Text Prompt (`prompt`)

Maximum length: 2000 characters

Required for: t2v-01, s2v-01, i2v-01-director, t2v-01-director

Optional for: i2v-01, i2v-01-live

Image Requirements (`image_url`)

File formats: JPG, PNG only

Size limit: 10MB maximum

Dimensions:

Minimum: 300px (width or height)

Maximum: 4096px (width or height)

Aspect ratio: Must be between 2:5 and 5:2

Required for: i2v-01, i2v-01-live, s2v-01, i2v-01-director

Configuration Options

Service Mode

Currently only supports "public" mode (or Pay-As-You-Go)

Important Notes

For s2v-01 model:

Face detection is mandatory in the input image

Failed face detection will result in task failure

Higher price (

0.30 v s

0.20 for other models)

Image processing:

All dimensions must be within 300px to 4096px range

Aspect ratio must be between 2:5 and 5:2

Only JPG and PNG formats are accepted

Images larger than 10MB will be rejected

Billing:

Cost is calculated per generation

Charges are applied upon successful task completion only

Request

Header Params

x-api-key

string

optional

Body Params application/json

model

enum<string>

required

Model name, currently only supports 'hailuo'

Allowed value:

hailuo

task_type

enum<string>

required

Task type, currently only supports 'video_generation'

Allowed value:

video_generation

input

object

required

prompt

string

optional

Required for t2v-01,t2v-01-director and s2v-01 models. Text prompt for video generation.

<= 2000 characters

model

enum<string>

required

Model type for video generation

Allowed values:

i2v-01i2v-01-livet2v-01s2v-01t2v-01-directori2v-01-director

image_url

string <uri>

optional

Required for i2v-01, i2v-01-live, and s2v-01 models. Image URL must be jpg/png, 300px-4096px, aspect ratio between 2:5 and 5:2, max 10MB

expand_prompt

boolean

optional

Whether to expand the input prompt

config

object

required

service_mode

enum<string>

required

Service mode for the request

Allowed value:

public

webhook_config

object

optional

Example

{
    "model": "hailuo",
    "task_type": "video_generation",
    "input": {
        "prompt": "string",
        "model": "i2v-01",
        "image_url": "http://example.com",
        "expand_prompt": true
    },
    "config": {
        "service_mode": "public",
        "webhook_config": {
            "endpoint": "http://example.com",
            "secret": "string"
        }
    }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Successful response

Body

code

enum<integer>

required

Response status code

Allowed value:

200

message

string

required

Response message

data

object

required

task_id

string <uuid>

required

Unique task identifier

model

string

required

Model used for generation

task_type

string

required

Type of task performed

status

string

required

Current status of the task

config

object

optional

input

object

required

output

object

required

meta

object

required

error

object

optional

Example

{
    "code": 200,
    "message": "string",
    "data": {
        "task_id": "736fde4d-9029-4915-8189-01353d6982cb",
        "model": "string",
        "task_type": "string",
        "status": "string",
        "config": {},
        "input": {},
        "output": {
            "percent": 0,
            "cover_url": "http://example.com",
            "video_url": "http://example.com",
            "download_url": "http://example.com",
            "desc": "string",
            "prompt_img_url": "string",
            "status": 0,
            "user_origin_prompt": true,
            "width": 0,
            "height": 0,
            "model_id": "string",
            "message": "string"
        },
        "meta": {
            "created_at": "2019-08-24T14:15:22Z",
            "started_at": "2019-08-24T14:15:22Z",
            "ended_at": "2019-08-24T14:15:22Z",
            "usage": {
                "type": "string",
                "frozen": 0,
                "consume": 0
            },
            "is_using_private_pool": true
        },
        "error": {
            "code": 0,
            "raw_message": "string",
            "message": "string",
            "detail": {}
        }
    }
}

Generate Video

Pricing#

Model Requirements#

Text-to-Video (t2v-01, t2v-01-director)#

Image-to-Video (i2v-01, i2v-01-live, i2v-01-director)#

Subject Reference Video (s2v-01)#

Input Constraints#

Text Prompt (prompt)#

Image Requirements (image_url)#

Configuration Options#

Service Mode#

Important Notes#

Request

Request samples

Responses

Pricing

Model Requirements

Text-to-Video (t2v-01, t2v-01-director)

Image-to-Video (i2v-01, i2v-01-live, i2v-01-director)

Subject Reference Video (s2v-01)

Input Constraints

Text Prompt (`prompt`)

Image Requirements (`image_url`)

Configuration Options

Service Mode

Important Notes