Higgsfield APIhiggsfield.ai ↗
Access trending AI-generated images from the Higgsfield community. Retrieve prompts, styles, dimensions, seeds, view/like counts, and creator profiles via one endpoint.
What is the Higgsfield API?
The Higgsfield AI API exposes 1 endpoint — search_generations — that returns trending community-generated AI images along with 10+ data fields per result including the full text prompt, style parameters, image dimensions, seed value, result image URL, view and like counts, and creator profile. It supports paginated browsing using an opaque cursor, making it straightforward to traverse large result sets.
curl -X GET 'https://api.parse.bot/scraper/873ffa1d-d0e2-45a7-b735-9b408be72533/search_generations?size=10&type=image' \ -H 'X-API-Key: $PARSE_API_KEY'
Typed, relational, agent-ready
A generated client with real types, enums, and the links between objects — the structure a flat JSON response can't carry. Autocompletes in your editor and reads cleanly to coding agents.
- Fully typed · autocompletes
- Objects link to objects
- Typed errors & pagination
Typed Python client. Set up the SDK in your uv project, then pull this API’s typed client:
uv add parse-sdk uv run parse init uv run parse add --marketplace higgsfield-ai-api
uv run parse add --marketplace pulls a pinned snapshot of this canonical API — it won’t change underneath you. To customize it, subscribe and swap to your own copy.
"""Walkthrough: Higgsfield SDK — bounded, re-runnable; every call capped."""
from parse_apis.higgsfield_ai_api import Higgsfield, ContentType, InvalidInput
client = Higgsfield()
# Browse trending AI-generated images
for gen in client.generations.list(type=ContentType.IMAGE, size=10, limit=3):
print(gen.prompt[:80], gen.style_name, f"{gen.width}x{gen.height}")
# Grab the first result for detailed inspection
item = client.generations.list(type=ContentType.IMAGE, limit=1).first()
if item:
print(item.id, item.username, item.views_count, item.likes_count)
print("image:", item.image_url)
print("seed:", item.seed, "style:", item.style_name)
# Typed error handling
try:
for gen in client.generations.list(size=100, limit=1):
print(gen.prompt)
except InvalidInput as e:
print("invalid input:", e)
print("exercised: generations.list")
Browse trending AI-generated images from the Higgsfield community. Returns generations ordered by trending score, each with its full prompt, generation parameters (dimensions, seed, style), result image URL, publication stats (views, likes), and creator profile. Results are auto-iterated via cursor-based pagination.
| Param | Type | Description |
|---|---|---|
| size | integer | Number of generations to return per page (1–50). |
| type | string | Content type filter. |
| cursor | string | Opaque pagination cursor returned by the previous response. Omit for the first page. |
{
"type": "object",
"fields": {
"count": "number of items returned in this page",
"items": "array of generation objects with prompt, image URL, style, dimensions, stats, and profile",
"total": "total number of generations matching the filter",
"cursor": "opaque cursor for the next page",
"has_more": "whether more pages are available"
},
"sample": {
"data": {
"count": 5,
"items": [
{
"id": "8b1ff7d8-36a5-4339-95a5-4969778322d6",
"seed": 174336,
"width": 1344,
"height": 2016,
"prompt": "Cinematic selfie in modern elevator...",
"status": "completed",
"user_id": "user_32bA1faqjrEn9Kf5I9x6l4jhluw",
"username": "arjun_asokan",
"image_url": "https://d8j0ntlcm91z4.cloudfront.net/user_32bA1faqjrEn9Kf5I9x6l4jhluw/hf_20260723_110036_8b1ff7d8-36a5-4339-95a5-4969778322d6.png",
"avatar_url": "https://d2ol7oe51mr4n9.cloudfront.net/user_32bA1faqjrEn9Kf5I9x6l4jhluw/08c3f09b-0011-4e2c-b49c-80d63d0b192e.png",
"created_at": 1784804436.384373,
"job_set_id": "92780de2-5cff-4084-a0e2-71d995e87b1d",
"style_name": "Digital camera",
"likes_count": 7,
"views_count": 757,
"job_set_type": "text2image_soul_v2",
"published_at": 1784804482.699517,
"style_strength": 1
}
],
"total": 66234,
"cursor": 0.06998197983957011,
"has_more": true
},
"status": "success"
}
}About the Higgsfield API
What the API Returns
The search_generations endpoint returns a paginated list of AI image generations from the Higgsfield community feed, ordered by trending score. Each item in the items array includes the original text prompt used to create the image, generation parameters (style, width/height dimensions, and seed), a direct URL to the result image, and publication statistics (views and likes). Each generation also carries a creator profile object, so you can attribute work and identify prolific community members.
Filtering and Pagination
Requests accept a size parameter (1–50) to control how many generations come back per page. An optional type parameter filters by content category. For subsequent pages, pass the cursor value returned in the previous response — omit it entirely for the first request. Each response includes has_more and total fields alongside the cursor, so you always know where you stand in the full result set.
Coverage and Freshness
Data reflects the publicly visible trending feed on higgsfield.ai/community/generations. Results are ordered by trending score, not chronologically, so the same generation may rank differently across requests as engagement changes. The total field reports the count of matching generations for the applied filter, while count reflects items returned in the current page.
The Higgsfield API is a managed, monitored endpoint for higgsfield.ai — not a raw scraper you maintain. Every endpoint is automatically health-checked on a schedule, and when higgsfield.ai changes and a check fails, the API is automatically queued for repair and re-verified. It is built to keep working as the site underneath it changes.
This isn't an official higgsfield.ai API — it's an independent, maintained REST wrapper over public data. Where the source has no official API (or only a limited one), Parse gives you a stable contract over a source that never promised one, and keeps it current. Need a new endpoint or field? You can revise it yourself in plain English and the agent rebuilds it against the live site in minutes — contributing the change back to the shared API is free.
Will this API break when the source site changes?+
Is this an official API from the source site?+
Can I fix or extend this API myself if I need a new endpoint or field?+
What happens if I call an endpoint that has an issue?+
- Build a prompt inspiration tool that surfaces trending Higgsfield prompts alongside their result images
- Track which AI styles and generation parameters are gaining traction by monitoring view and like counts over time
- Aggregate creator profiles to identify the most active or popular contributors in the Higgsfield community
- Compile a dataset of prompt-to-image pairs for research into text-to-image generation quality
- Power a discovery feed for a design or creative tool by pulling trending generations with image URLs and metadata
- Analyze which image dimensions and seeds correlate with higher engagement across community submissions
| Tier | Price | Credits/month | Rate limit |
|---|---|---|---|
| Free | $0/mo | 100 | 5 req/min |
| Hobby | $30/mo | 1,000 | 20 req/min |
| Developer | $100/mo | 5,000 | 100 req/min |
One credit = one API call regardless of which marketplace API you call. Exceeding the rate limit returns a 429 response. Authenticate with the X-API-Key header.
Does Higgsfield AI have an official developer API?+
What does search_generations actually return for each image?+
items array includes the full text prompt, the result image URL, style identifier, image dimensions, seed value, view count, like count, and a creator profile object. The response also provides total, count, cursor, and has_more for pagination.Can I retrieve generations sorted by newest or most liked instead of trending?+
Is there any data about private or unlisted generations, or individual user profile pages?+
How does pagination work and are there limits on how many results I can fetch?+
size parameter). Pass the cursor value from the previous response to fetch the next page. The has_more field tells you whether additional pages exist, and total gives the full match count for your filter.