Utility Llms API
Scrape Utility Llms data with one API call. The SocialCrawl context corpus for AI agents, served through the API: the same content as llms.txt for the whole API or a single platform, as markdown or structured JSON. An agent with an API key can bootstrap itself with one call instead of scraping documentation pages. Free to call.
Last updated August 2026Maintained by the SocialCrawl team
Returns SocialCrawl's reference text for AI agents, for the whole API or a single platform, as markdown or as a structured object.
Use it when an agent should learn the API in one call instead of reading the documentation site. Free to call.
Searching 46 platforms in parallel
What can you do with the Llms API?
The Llms endpoint gives you structured Utility data with computed fields in a single request. No scraping infrastructure to build or maintain.
Example Request
curl -H "x-api-key: YOUR_API_KEY" \
"https://www.socialcrawl.dev/v1/utility/llms"import requests
response = requests.get(
"https://www.socialcrawl.dev/v1/utility/llms",
headers={"x-api-key": "YOUR_API_KEY"},
)
data = response.json()const response = await fetch(
"https://www.socialcrawl.dev/v1/utility/llms",
{
headers: { "x-api-key": "YOUR_API_KEY" },
},
);
const data = await response.json();Parameters
| Parameter | Required | Description |
|---|---|---|
| platform | No | Scope the context to one platform slug |
| format | No | markdown (default) returns the llms corpus text; json returns a structured context object (markdown | json) |
What does the Utility Llms API return?
This synthetic fixture shows the documented response shape and fields. Values are illustrative; this is not a live API response.
Example response
{
"success": true,
"platform": "utility",
"endpoint": "/v1/utility/llms",
"data": {
"kind": "agent_context",
"format": "markdown",
"scope": "all",
"content": "# SocialCrawl API\n\n> Unified social media data API. One API key, one response format, 46 platforms, 372 endpoints.\n\nLast updated: 2026-08-02\n\n## Base URL\n\nhttps://www.socialcrawl.dev/v1\n\n## Authentication\n\nPass your API key in the `x-api-key` header with every request.\n\n## Instructions\n\n- Authenticate every request with the `x-api-key` header. Never put the key in the URL or query string.\n- Never invent endpoint paths. Endpoints live at `/v1/{platform}/{resource}` and are `GET` unless marked otherwise (a small set of batch and web endpoints are `POST`/`PATCH`/`DELETE`); fetch `/llms-{platform}.txt` for one platform's exact resource list with methods, or `/llms-full.txt` for all of them.\n- For cross-platform questions (\"who is talking about X everywhere\"), prefer `GET /v1/search/everywhere` over fanning out per platform yourself. One call searches up to 15 sources and fuses the results.\n- Paginate every list the same way: read `pagination.next_cursor` from the response, send it back verbatim as the `cursor` query parameter, and stop when `pagination.has_more` is `false`. Never build or decode a cursor yourself.\n...",
"links": {
"llms_txt": "https://www.socialcrawl.dev/llms.txt",
"llms_full_txt": "https://www.socialcrawl.dev/llms-full.txt",
"openapi": "https://www.socialcrawl.dev/openapi.json",
"quickstart": "/v1/utility/quickstart"
}
},
"credits_used": 0,
"request_id": "req_example000000",
"cached": false
}Synthetic fixture for the documented response shape. Values are illustrative, not a production capture.
How does the Utility Llms API work?
Send a GET request with your API key and get back clean, structured JSON in our unified schema. Supported computed fields are populated when the source provides the required inputs.
Method
GET
Response
JSON
How do you scrape social media data in seconds?
The fastest social media scraping API for developers. Scrape profiles, posts, comments, and analytics from 46 platforms covering 10B+ monthly active users.
One schema, every platform
Query 46 platforms with identical response structures. Write your integration once.
Computed fields, not just scraped
When an endpoint supports these metrics and the source provides the required inputs, the normalized record includes engagement_rate, estimated_reach, content_category, and language — ready to use.
See your data before you code
Visual Data Explorer — paste any URL, get rich result cards, sortable tables, CSV export.
import requests
response = requests.get(
'https://www.socialcrawl.dev/v1/tiktok/profile',
params={'handle': 'charlidamelio'},
headers={'x-api-key': 'sc_YOUR_API_KEY'}
)
data = response.json(){
"success": true,
"platform": "tiktok",
"data": {
"author": {
"username": "charlidamelio",
"followers": 152400000
},
"engagement": {
"likes": 12400000000,
"engagement_rate": 0.087
},
"metadata": {
"language": "en",
"content_category": "lifestyle"
}
}
}Have a question? We got answers
Find answers to frequently asked questions about SocialCrawl's API, pricing, and capabilities.
Contact usWhat does GET /v1/utility/llms return?
Why fetch llms.txt through the API instead of the file?
Can I scope the agent context to one platform?
Is the llms endpoint free to call?
How do AI agents self-onboard with SocialCrawl?
Ask AI about SocialCrawl
Ready to scrape Utility Llms data?
Get your API key and start pulling Utility data in under 60 seconds.
