Kennzahlen

Aggregierte Daten zu Sichtbarkeit, Share of Voice, Zitierungen und Positionen für Ihre Marke und ihre Wettbewerber, direkt für Diagramme nutzbar. Jeder Endpunkt akzeptiert die allgemeinen Filter und den Parameter output, die unter „Grundkonzepte“ beschrieben sind.

GET`/metrics/timeseries`

Liefert Zeitreihen für eine oder mehrere Kennzahlen, gruppiert nach Akteur (Ihr Projekt und die ausgewählten Wettbewerber). Wöchentliche und monatliche Werte folgen der oben beschriebenen Zeitraumlogik. Die optionalen Filter prompt_type (Suchintention) und brand_kind beschränken jede Kennzahl auf eine Prompt-Kategorie.

GET`/metrics/summary`

Aggregiert pro Akteur und Kennzahl (total/min/max/last). Ideal für KPI-Kacheln.

GET`/metrics/prompt_summary`

Liefert paginierte, pro Prompt aggregierte Kennzahlen (responses, mentions, citations, mention_rate, citation_rate, avg_mention_position, avg_position). Mit breakdown=model erhält jede Zeile zusätzlich die Dimension KI-Modell, sodass Kennzahlen pro Prompt und Modell zurückgegeben werden. Parameter: sort (responses, mentions, citations, mention_rate oder visibility, citation_rate, avg_mention_position, avg_position), sort_dir (asc/desc), breakdown (model), page, per_page (maximal 100).

GET`/metrics/sov`

Share of Voice auf Basis von Erwähnungen, übereinstimmend mit der Übersicht in der App.

over_time: für jedes Datum SOV = (actor_mentions / sum_all_mentions) × 100. Ist die Tagessumme 0, wird der letzte Wert unverändert fortgeschrieben.
current: verwendet das jüngste Datum mit einer Summe ungleich 0; gibt es keines, werden die Summen über den gesamten Zeitraum verwendet.
breakdown: die 4 Akteure mit dem größten Anteil und eine zusammengefasste Zeile Others (dazu eine detaillierte Liste others).
periods und sample: Jeder Zeitabschnitt nennt die Zahl der Erwähnungen (mentions), auf denen seine Anteile beruhen, ein Kennzeichen partial, eine Konfidenzstufe in confidence (none ohne Erwähnungen, low unter 30, medium unter 100, high ab 100) sowie margin_of_error, die Fehlermarge in Prozentpunkten für den ungünstigsten Fall bei einem Konfidenzniveau von 95 % (98 geteilt durch die Quadratwurzel von mentions, also etwa 18 Prozentpunkte bei 30 Erwähnungen und 10 bei 100; null ohne Erwähnungen). sample wiederholt den Zeitabschnitt, auf dem die Anteile in current beruhen, oder ist null, wenn das Zeitfenster keine Erwähnungen enthält.

GET`/metrics/top_sources`

Sortiert die Domains der Quellen nach der Anzahl der Antworten und der durchschnittlichen Erwähnungsrate (Anteil der Ausführungen in Prozent, in denen die Domain vorkam).

Berücksichtigt werden alle nicht abgelehnten Quellen, die mit Prompt-Ausführungen innerhalb des Zeitraums und der aktuellen Filter verknüpft sind.
total_responses: Anzahl verschiedener Prompt-Ausführungen, die mindestens eine Quelle auf dieser Domain geliefert haben.
avg_mention_rate (wird auch als avg_visibility zurückgegeben): (count of source rows for the domain / total executions) × 100.
Sortierung: sort=total_responses (Standard), sort=avg_mention_rate oder sort=avg_visibility.
Paginierung: page (>=1), per_page (Standard: 20, maximal 100).
Nach Domain filtern: query (LIKE ohne Beachtung der Groß- und Kleinschreibung), zum Beispiel query=github.

Codebeispiele

Download: OpenAPI Swagger Postman

KI fragen: In ChatGPT öffnen In Claude öffnen Als Markdown anzeigen

Sprache

Request

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30"

const response = await fetch("https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30", {
  headers: { "Authorization": "Bearer YOUR_API_KEY" }
});
const data = await response.json();

import requests

response = requests.get(
    "https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
data = response.json()

require 'httparty'

response = HTTParty.get(
  "https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30",
  headers: { "Authorization" => "Bearer YOUR_API_KEY" }
)
data = response.parsed_response

package main

import "net/http"

func main() {
	req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.llmpulse.ai/api/v1/metrics/timeseries?project_id=PROJECT_ID&metrics=mentions,visibility&granularity=day&range=30"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .GET()
            .build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    }
}

Response

{
  "project_id":"...",
  "from":"2025-02-01T00:00:00Z",
  "to":"2025-03-02T23:59:59Z",
  "granularity":"day",
  "filters":{ ... },
  "series":{
    "mentions":[
      { "actor": { "type":"project","id":1,"name":"Acme","domain":null }, "metric":"mentions",
        "data":[ { "date":"2025-02-01","value":12 }, ... ] },
      { "actor": { "type":"competitor","id":5,"name":"Contoso","domain":"contoso.com" }, "metric":"mentions", "data":[ ... ] }
    ],
    "visibility":[ ... ],
    "citations":[ ... ],
    "avg_position":[ ... ]
  },
  "request_id":"..."
}

Request

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30"

const response = await fetch("https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30", {
  headers: { "Authorization": "Bearer YOUR_API_KEY" }
});
const data = await response.json();

import requests

response = requests.get(
    "https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
data = response.json()

require 'httparty'

response = HTTParty.get(
  "https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30",
  headers: { "Authorization" => "Bearer YOUR_API_KEY" }
)
data = response.parsed_response

package main

import "net/http"

func main() {
	req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.llmpulse.ai/api/v1/metrics/summary?project_id=PROJECT_ID&metrics=mentions,citations&granularity=day&range=30"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .GET()
            .build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    }
}

Response

{
  "series": { ... },
  "summary": {
    "mentions": [
      { "actor": { "type":"project","id":1,"name":"Acme" }, "total":1450, "min":0, "max":120, "last":34 }
    ],
    "avg_position": [
      { "actor": { "type":"project","id":1,"name":"Acme" }, "total":3.42, "min":2.1, "max":5.3, "last":3.8 }
    ]
  }
}

Request

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50"

const response = await fetch("https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50", {
  headers: { "Authorization": "Bearer YOUR_API_KEY" }
});
const data = await response.json();

import requests

response = requests.get(
    "https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
data = response.json()

require 'httparty'

response = HTTParty.get(
  "https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50",
  headers: { "Authorization" => "Bearer YOUR_API_KEY" }
)
data = response.parsed_response

package main

import "net/http"

func main() {
	req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.llmpulse.ai/api/v1/metrics/prompt_summary?project_id=PROJECT_ID&range=30&sort=visibility&sort_dir=desc&per_page=50"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .GET()
            .build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    }
}

Response

{
  "project_id": 1,
  "breakdown": "model",
  "sort": "mention_rate", "sort_dir": "desc",
  "page": 1, "per_page": 50, "total": 230,
  "data": [
    {
      "prompt_id": 123,
      "prompt_text": "best CRM software",
      "model": "chatgpt",
      "responses": 50,
      "mentions": 30,
      "citations": 15,
      "visibility": 60.0,
      "mention_rate": 60.0,
      "citation_rate": 30.0,
      "avg_mention_position": 2.35,
      "avg_position": 3.1
    }
  ]
}

Request

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30"

const response = await fetch("https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30", {
  headers: { "Authorization": "Bearer YOUR_API_KEY" }
});
const data = await response.json();

import requests

response = requests.get(
    "https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
data = response.json()

require 'httparty'

response = HTTParty.get(
  "https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30",
  headers: { "Authorization" => "Bearer YOUR_API_KEY" }
)
data = response.parsed_response

package main

import "net/http"

func main() {
	req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.llmpulse.ai/api/v1/metrics/sov?project_id=PROJECT_ID&range=30"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .GET()
            .build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    }
}

Response

{
  "over_time":[
    { "actor": { "type":"project","id":1,"name":"Acme" },
      "data":[ { "date":"2025-02-01","value":42.8 }, ... ] }
  ],
  "current":[
    { "actor": { "type":"project","id":1,"name":"Acme" }, "share":48.12 },
    { "actor": { "type":"competitor","id":5,"name":"Contoso" }, "share":33.27 },
    { "actor": { "type":"competitor","id":7,"name":"Fabrikam" }, "share":18.61 }
  ],
  "breakdown": [
    { "rank":1, "actor": { "type":"project","id":1,"name":"Acme" }, "share":48.12 },
    { "rank":2, "actor": { "type":"competitor","id":5,"name":"Contoso" }, "share":33.27 },
    { "rank":3, "actor": { "type":"competitor","id":7,"name":"Fabrikam" }, "share":18.61 },
    { "rank":5, "actor": { "name":"Others" }, "share":12.00, "others":true }
  ],
  "others": [
    { "rank":5, "actor": { "type":"competitor","id":9,"name":"Globex" }, "share":7.00 }
  ]
}

Request

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30"

const response = await fetch("https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30", {
  headers: { "Authorization": "Bearer YOUR_API_KEY" }
});
const data = await response.json();

import requests

response = requests.get(
    "https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30",
    headers={"Authorization": "Bearer YOUR_API_KEY"}
)
data = response.json()

require 'httparty'

response = HTTParty.get(
  "https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30",
  headers: { "Authorization" => "Bearer YOUR_API_KEY" }
)
data = response.parsed_response

package main

import "net/http"

func main() {
	req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30", nil)
	req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
	client := &http.Client{}
	resp, err := client.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
}

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        HttpClient client = HttpClient.newHttpClient();
        HttpRequest request = HttpRequest.newBuilder()
            .uri(URI.create("https://api.llmpulse.ai/api/v1/metrics/top_sources?project_id=PROJECT_ID&range=30"))
            .header("Authorization", "Bearer YOUR_API_KEY")
            .GET()
            .build();
        HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());
    }
}

Response

{
  "project_id":"...",
  "from":"2025-02-01T00:00:00Z",
  "to":"2025-03-02T23:59:59Z",
  "filters":{ ... },
  "sort":"avg_mention_rate",
  "page":1,
  "per_page":20,
  "total":57,
  "data":[
    { "domain":"example.com", "total_responses":42, "avg_visibility":18.75, "avg_mention_rate":18.75 },
    { "domain":"another.com", "total_responses":37, "avg_visibility":15.10, "avg_mention_rate":15.10 }
  ],
  "request_id":"..."
}

Kennzahlen

GET/metrics/timeseries

GET/metrics/summary

GET/metrics/prompt_summary

GET/metrics/sov

GET/metrics/top_sources

GET`/metrics/timeseries`

GET`/metrics/summary`

GET`/metrics/prompt_summary`

GET`/metrics/sov`

GET`/metrics/top_sources`