Higgsfield API - AI Video Generation APIs

by Higgsfield

Higgsfield API, developers can transform images into videos and generate motion content from text prompts. The API is designed for social media creators, marketers, and developers who need quick, high-quality video generation without complex production pipelines.

Get API Key

Models Version

LIMITED TIME OFFER

Get $5 Free Credit on First Payment

No strings attached — add funds and get $5 bonus instantly

Claim Your $5 →

Higgsfield 1.0 Text to Image API Documentation

https://gateway.pixazo.ai/ai-model-api/v1

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Generate Soul Request - AI Model API

Request Code

POST https://gateway.pixazo.ai/ai-model-api/v1/generateSoul
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "prompt": "Woman on rooftop",
  "soul_style_id": "a5f63c3b-70eb-4979-af5e-98c7ee1e18e8",
  "width_and_height": "1536x1152",
  "image_reference_type": "image_url",
  "image_reference_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png"
}

import requests
import json

url = "https://gateway.pixazo.ai/ai-model-api/v1/generateSoul"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "prompt": "Woman on rooftop",
    "soul_style_id": "a5f63c3b-70eb-4979-af5e-98c7ee1e18e8",
    "width_and_height": "1536x1152",
    "image_reference_type": "image_url",
    "image_reference_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png"
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

const url = 'https://gateway.pixazo.ai/ai-model-api/v1/generateSoul';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};

const data = {
  prompt: 'Woman on rooftop',
  soul_style_id: 'a5f63c3b-70eb-4979-af5e-98c7ee1e18e8',
  width_and_height: '1536x1152',
  image_reference_type: 'image_url',
  image_reference_image_url: 'https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png'
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -v -X POST "https://gateway.pixazo.ai/ai-model-api/v1/generateSoul" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "prompt": "Woman on rooftop",
  "soul_style_id": "a5f63c3b-70eb-4979-af5e-98c7ee1e18e8",
  "width_and_height": "1536x1152",
  "image_reference_type": "image_url",
  "image_reference_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png"
}'

Output

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Generate Soul Request

Parameter	Required	Type	Description
prompt	Yes	string	Text description for image generation. Describes the desired image content, style, and visual characteristics. Be descriptive for better results. Example: `A serene mountain landscape at sunset with golden light`
width_and_height	Yes	enum string	Desired width and height of output image. Available options: `1152x2048`, `2048x1152`, `2048x1536`, `1536x2048`, `1344x2016`, `2016x1344`, `960x1696`, `1536x1536`, `1536x1152`, `1696x960`, `1152x1536`, `1088x1632`, `1632x1088`. Example: `1152x2048`
enhance_prompt	No	boolean	Whether to automatically enhance and refine the provided prompt. When `true`, the system will optimize your prompt for better image generation results. Example: `true`
style_id	No	string (UUID)	Chosen preset for soul image generation. If null then General soul style is applied. Use `/getTextToImageGetSoulStyles` to get available style IDs. Example: `464ea177-8d40-4940-8d9d-b438bab269c7`. Get some other style using the API: https://endpoints.appypie.com/api-details#api=ai-model-api-polling&operation=soul-styles
style_strength	No	number	Strength of the style application. Range from 0.0 (minimal style) to 1.0 (maximum style) with 0.01 step precision. Higher values create more pronounced artistic effects. Example: `0.8`
quality	No	enum string	Output image quality. Available options: `720p`, `1080p`. Higher quality takes longer to generate but produces better results. Example: `1080p`
seed	No	integer \| null	Seed for reproducibility. If null then random seed is applied. Must be between 1 and 1,000,000. Using the same seed with identical parameters will produce similar results. Example: `500000`
custom_reference_id	No	string (UUID) \| null	The ID of a character that has already been created. Use this to generate images in a specific character's style. Example: `3c90c3cc-0d44-4b50-8888-8dd25736052a`
custom_reference_strength	No	number	Strength of the custom reference application. Range from 0.0 (minimal effect) to 1.0 (maximum effect) with 0.01 step precision. Example: `0.9`
image_reference_type	No	string	Type of the image reference. Must be `image_url`. Required if `image_reference_image_url` is provided. Example: `image_url`
image_reference_image_url	No	string (URI)	URL of an image to be used as a source for image generation. Must be a valid URI with length between 1-2083 characters. Required if `image_reference_type` is provided. Example: `https://example.com/reference-image.jpg`
batch_size	No	enum integer	Number of images to generate in a single batch. Available options: `1`, `4`. Higher batch sizes take longer but can be more cost-effective. Example: `4`

Example Request

{
  "prompt": "Woman on rooftop",
  "soul_style_id": "a5f63c3b-70eb-4979-af5e-98c7ee1e18e8",
  "width_and_height": "1536x1152",
  "image_reference_type": "image_url",
  "image_reference_image_url": "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/model.png"
}

Response

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	YOUR_SUBSCRIPTION_KEY

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ai-model-api' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ai-model-api",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ai-model-api",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ai-model-api_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Higgsfield 1.0 Text to Image API Pricing

Resolution	Price (USD)
Per generation	$0.15
Per generation	$0.19
Per generation	$0.25
Per generation	$0.37

Higgsfield 1.0 Image to Video API Documentation

https://gateway.pixazo.ai/ai-model-api/v1

Authentication

All requests require an API key passed via header.

Header	Type	Required	Description
Ocp-Apim-Subscription-Key	string	Yes	Your API subscription key

Image To Video Request - AI Model API

Request Code

POST https://gateway.pixazo.ai/ai-model-api/v1/generateImageToVideoRequest
Content-Type: application/json
Cache-Control: no-cache
Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY

{
  "model": "dop-lite",
  "prompt": "A serene lake with gentle ripples, birds flying overhead, cinematic lighting",
  "seed": 123456,
  "motions_id": "[MOTION_ID]",
  "motions_strength": 0.7,
  "input_images": ["https://example.com/images/lake-scene.jpg"],
  "enhance_prompt": true
}

import requests

url = "https://gateway.pixazo.ai/ai-model-api/v1/generateImageToVideoRequest"
headers = {
    "Content-Type": "application/json",
    "Cache-Control": "no-cache",
    "Ocp-Apim-Subscription-Key": "YOUR_SUBSCRIPTION_KEY"
}
data = {
    "model": "dop-lite",
    "prompt": "A serene lake with gentle ripples, birds flying overhead, cinematic lighting",
    "seed": 123456,
    "motions_id": "[MOTION_ID]",
    "motions_strength": 0.7,
    "input_images": ["https://example.com/images/lake-scene.jpg"],
    "enhance_prompt": True
}

response = requests.post(url, json=data, headers=headers)
print(response.json())

const url = 'https://gateway.pixazo.ai/ai-model-api/v1/generateImageToVideoRequest';
const headers = {
  'Content-Type': 'application/json',
  'Cache-Control': 'no-cache',
  'Ocp-Apim-Subscription-Key': 'YOUR_SUBSCRIPTION_KEY'
};
const data = {
  model: 'dop-lite',
  prompt: 'A serene lake with gentle ripples, birds flying overhead, cinematic lighting',
  seed: 123456,
  motions_id: '[MOTION_ID]',
  motions_strength: 0.7,
  input_images: ['https://example.com/images/lake-scene.jpg'],
  enhance_prompt: true
};

fetch(url, {
  method: 'POST',
  headers: headers,
  body: JSON.stringify(data)
})
.then(response => response.json())
.then(data => console.log(data))
.catch(error => console.error('Error:', error));

curl -X POST "https://gateway.pixazo.ai/ai-model-api/v1/generateImageToVideoRequest" \
-H "Content-Type: application/json" \
-H "Cache-Control: no-cache" \
-H "Ocp-Apim-Subscription-Key: YOUR_SUBSCRIPTION_KEY" \
--data-raw '{
  "model": "dop-lite",
  "prompt": "A serene lake with gentle ripples, birds flying overhead, cinematic lighting",
  "seed": 123456,
  "motions_id": "[MOTION_ID]",
  "motions_strength": 0.7,
  "input_images": ["https://example.com/images/lake-scene.jpg"],
  "enhance_prompt": true
}'

Output

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Try Now

Webhook (Optional)

Add the X-Webhook-URL header to your generate request to receive a POST callback instead of polling.

X-Webhook-URL: https://your-server.com/webhook/callback

Request Parameters - Image To Video Request

Field	Type	Required	Default	Description
model	enum string	Yes	—	The image-to-video model to use for generation. Available options: `dop-lite`, `dop-preview`, `dop-turbo`. Each model offers different quality and speed trade-offs. Example: `dop-lite`
prompt	string	Yes	—	Text description/prompt for video generation. Describes the desired video content, style, and motion. Be descriptive for better results. Example: `A peaceful sunset over mountains with clouds moving slowly`
seed	integer	Yes	—	Random seed for reproducible results. Must be between 1 and 1,000,000. Using the same seed with identical parameters will produce similar results. Example: `500000`
motions_id	string (UUID)	Yes	—	Unique identifier for the motion preset. This ID corresponds to predefined motion effects available in the system. You can get motion_id using the API: https://endpoints.appypie.com/api-details#api=ai-model-api-polling&operation=motions
motions_strength	number (0-1)	Yes	—	Intensity of the motion effect application. Range from 0.0 (minimal effect) to 1.0 (maximum effect) with 0.01 step precision. Higher values create more pronounced motion. Example: `0.75`
input_images	array of strings	Yes	—	Array of image URLs for video generation. Each URL must be a publicly accessible link pointing to a valid image file. Supported formats include JPEG, PNG, WebP. Must contain exactly 1 element for standard generation. Example: `["https://example.com/image1.jpg"]`
input_images_end	array of strings	No	null	Array of end frame image URLs for Start & End Frame functionality. Each URL must be a publicly accessible link pointing to a valid image file. Supported formats include JPEG, PNG, WebP. Minimum length: 1 element. Enables advanced frame interpolation between start and end images. Example: `["https://example.com/end-frame.jpg"]`
enhance_prompt	boolean	Yes	—	Whether to automatically enhance and refine the provided prompt. When `true`, the system will optimize your prompt for better video generation results. Example: `true`
check_nsfw	boolean	No	true	Whether to perform NSFW (Not Safe For Work) content detection. When `true`, the system will check for inappropriate content and may reject the request if detected.

Minimum Request

{
  "model": "dop-lite",
  "prompt": "A serene lake with gentle ripples, birds flying overhead, cinematic lighting",
  "seed": 123456,
  "motions_id": "[MOTION_ID]",
  "motions_strength": 0.7,
  "input_images": ["https://example.com/images/lake-scene.jpg"],
  "enhance_prompt": true
}

Full Request (all options)

{
  "model": "dop-lite",
  "prompt": "A serene lake with gentle ripples, birds flying overhead, cinematic lighting",
  "seed": 123456,
  "motions_id": "[MOTION_ID]",
  "motions_strength": 0.7,
  "input_images": ["https://example.com/images/lake-scene.jpg"],
  "input_images_end": ["https://example.com/images/lake-end-frame.jpg"],
  "enhance_prompt": true,
  "check_nsfw": true
}

Response

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "QUEUED",
  "polling_url": "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
}

Request Headers

Header	Value
Content-Type	application/json
Cache-Control	no-cache
Ocp-Apim-Subscription-Key	Your API subscription key

Response Handling

Common status codes for Image To Video Request.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
403	Forbidden
404	Not Found
429	Too Many Requests
500	Internal Server Error

Response Handling

Common status codes.

Code	Meaning
202	Accepted — Request queued
400	Bad Request
401	Unauthorized
402	Insufficient Balance
403	Forbidden
429	Too Many Requests
500	Internal Server Error

Error Responses

Queue system errors and model validation errors.

Queue System Errors

// 402 — Insufficient balance
{
  "error": "Insufficient Balance",
  "message": "Your wallet does not have enough balance."
}

// 400 — Model not found
{
  "error": "Model not found",
  "message": "Model 'ai-model-api' not found or is disabled"
}

Error via Status/Webhook

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "ERROR",
  "model_id": "ai-model-api",
  "error": "Description of the error",
  "output": null
}

Retrieving Results

Poll the universal status endpoint to check progress and retrieve results.

Endpoint

GET https://gateway.pixazo.ai/v2/requests/status/{request_id}
Ocp-Apim-Subscription-Key: YOUR_API_KEY

cURL Example

curl -H "Ocp-Apim-Subscription-Key: YOUR_API_KEY" \
  "https://gateway.pixazo.ai/v2/requests/status/ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"

Response (Completed)

{
  "request_id": "ai-model-api_019dxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",
  "status": "COMPLETED",
  "model_id": "ai-model-api",
  "error": null,
  "output": {
    "media_url": [
      "https://pub-582b7213209642b9b995c96c95a30381.r2.dev/v1/ai-model-api_019dxxxx-xxxx/output.ext"
    ],
    "media_type": "application/octet-stream"
  },
  "created_at": "2026-03-31T10:00:00.000Z",
  "updated_at": "2026-03-31T10:00:15.000Z",
  "completed_at": "2026-03-31T10:00:15.000Z"
}

Response Fields

Field	Type	Description
request_id	string	Unique request identifier
status	string	QUEUED, PROCESSING, COMPLETED, FAILED, or ERROR
model_id	string	Model that processed the request
error	string\|null	Error message if failed
output.media_url	array	URLs to generated media (R2 CDN)
output.media_type	string	MIME type of the output
created_at	string	When request was created
completed_at	string\|null	When request completed
polling_url	string	Status URL (initial response only)

Status Values

Status	Description
QUEUED	Request accepted, waiting to be processed
PROCESSING	Being processed by the model
COMPLETED	Done — output contains the result
FAILED	Failed — check error field
ERROR	System error — not charged

Status Flow

QUEUED → PROCESSING → COMPLETED
                    → FAILED
                    → ERROR

Typical Workflow

Send a generate request to the API endpoint
Save the request_id from the response
Poll every 5-10 seconds: GET /v2/requests/status/{request_id}
When status is "COMPLETED", download from output.media_url

Tip: Use X-Webhook-URL header to get a callback instead of polling.

Higgsfield 1.0 Image to Video API Pricing

Resolution	Duration	Price (USD)
dop-lite	5s	$0.135
dop-preview	5s	$0.573
dop-turbo	5s	$0.416