GA4 by LLM
AI-referred site traffic broken out per LLM source — sessions, users, and pageviews for each assistant — plus the previous period.
curl --request GET \
--url 'https://api.aiclicks.io/api/v1/ga4/by-llm?domain_id=8f1d3c0a-2f9b-4c11-9b80-7a82e1f0c3f3&days=30' \
--header 'Authorization: Bearer ak_live_xxx'
import httpx, os
resp = httpx.get(
"https://api.aiclicks.io/api/v1/ga4/by-llm",
params={"domain_id": "8f1d3c0a-2f9b-4c11-9b80-7a82e1f0c3f3", "days": 30},
headers={"Authorization": f"Bearer {os.environ['AICLICKS_API_KEY']}"},
)
resp.raise_for_status()
by_llm = resp.json()["data"]["by_llm"]
for src, m in sorted(by_llm.items(), key=lambda kv: kv[1]["sessions"], reverse=True):
print(f"{src:<12} {m['sessions']:>6} sessions")
const url = new URL("https://api.aiclicks.io/api/v1/ga4/by-llm");
url.searchParams.set("domain_id", "8f1d3c0a-2f9b-4c11-9b80-7a82e1f0c3f3");
url.searchParams.set("days", "30");
const resp = await fetch(url, {
headers: { Authorization: `Bearer ${process.env.AICLICKS_API_KEY}` },
});
const { data } = await resp.json();
console.log(data.by_llm);
{
"data": {
"by_llm": {
"chatgpt": { "sessions": 720, "users": 560, "pageviews": 1800 },
"perplexity": { "sessions": 300, "users": 250, "pageviews": 760 },
"claude": { "sessions": 220, "users": 170, "pageviews": 550 }
},
"previous_by_llm": {
"chatgpt": { "sessions": 610, "users": 500, "pageviews": 1600 },
"perplexity": { "sessions": 250, "users": 210, "pageviews": 640 }
}
},
"domain_id": "8f1d3c0a-2f9b-4c11-9b80-7a82e1f0c3f3",
"days": 30,
"llm_source": null,
"generated_at": "2026-07-13T10:00:11.218Z"
}
{ "detail": "domain_id query parameter is required. List the domains this key can access with GET /api/v1/domains, then pass ?domain_id=<uuid>." }
{ "detail": "Invalid or revoked API key" }
{ "detail": "API access is not enabled for this team. Contact support@aiclicks.io." }
{ "detail": "Too many requests. Please try again later." }
The same AI-referred traffic as GA4 summary, split by the AI assistant that referred it — ChatGPT vs Perplexity vs Claude vs Gemini vs Copilot, and so on. Use it to see which assistants actually drive visitors to the site, not just which ones mention the brand.
by_llm is keyed by the normalized source name; each value carries sessions, users, and pageviews. previous_by_llm is the same map for the immediately preceding window of equal length.
domain_id is a required query parameter. Use GET /api/v1/domains to discover which domains the calling key can access. When the domain has no connected GA4 property (or no AI-referred traffic in the window), both maps come back empty ({}) with a 200.
Authorizations
Your API key formatted as Bearer ak_live_<your-key>. Create one in the dashboard under Settings → Developers.
Optional UUID for log correlation. If omitted, we generate one and echo it back in the response.
Query parameters
UUID of the domain. Find domains via GET /api/v1/domains. Omitting this returns 400.
Trailing look-back window, 1–365. Defaults to 30. previous_by_llm covers the window of equal length immediately before it.
Optional. Restrict to a single AI/LLM referral source — chatgpt, perplexity, claude, gemini, copilot, you, deepseek, grok, … With a filter set, the maps contain at most that one key. Omit for all sources.
Response
The per-source payload.
Map keyed by normalized LLM source name (chatgpt, perplexity, claude, gemini, copilot, other_llm, …). Each value is { sessions, users, pageviews }. Empty {} when there is no data.
The same map for the immediately preceding window of equal length. A source present in one map but not the other simply had no traffic that period.
Echo of the requested domain.
Echo of the requested window.
Echo of the requested llm_source filter, or null when unset.
ISO-8601 timestamp of when the server produced (or cached) this response.
Response headers
| Header | Description |
|---|---|
X-Cache | HIT or MISS. Whether the response came from cache. |
X-Request-Id | Unique request id. Echoes incoming if you set one. |
X-RateLimit-Limit | Max requests per minute for this key. |
X-RateLimit-Remaining | Requests remaining in the current minute. |
X-RateLimit-Reset | Unix epoch seconds when the window resets. |
Caching
Cached for a short window per (domain_id, days, llm_source). Freshly synced GA4 data appears after the TTL expires.
Empty result
{
"data": { "by_llm": {}, "previous_by_llm": {} },
"domain_id": "8f1d3c0a-2f9b-4c11-9b80-7a82e1f0c3f3",
"days": 30,
"llm_source": null,
"generated_at": "2026-07-13T10:00:11.218Z"
}