API Documentation

Access your AI visibility data with the REST API, native Rust CLI, official SDKs for 12 languages, or MCP. Build dashboards, ETL pipelines, and automated workflows.

Get Started Free Download OpenAPI spec

LLM Pulse API

Build dashboards, ETL pipelines and automations with a clean, well-typed API.

LLM Pulse is an AI visibility analytics platform that monitors how your brand appears in AI-generated responses from ChatGPT, Perplexity, Gemini, and other LLMs. The API gives you programmatic access to all your visibility data, including brand mentions, citation sources, sentiment analysis, and share of voice metrics. Use it to build custom dashboards, automate reports, or integrate AI visibility tracking into your existing tools.

Authentication

Use a Bearer token from your API Key.

Authorization: Bearer YOUR_API_KEY

Base URL

Use this base URL for all endpoints below. Examples already include the full path.

https://api.llmpulse.ai/api/v1

Using an AI agent? Read the llms.txt

We serve a machine-readable version of these docs so coding agents (Claude Code, Cursor, ChatGPT, etc.) can find the right endpoint without parsing this page.

/api-docs/llms.txt : short index, generated from the live route table.

/api-docs/llms-full.txt : full reference (every endpoint, every parameter).

100% UI-to-API parity, found a gap? We''ll close it

We aim for 100% UI-to-API parity, anything you can see in the LLM Pulse dashboard should be reachable through the API. If you find a gap, report it and we commit to implementing it, typically within hours to a few days.

Authentication

Send your key in the Authorization header as a Bearer token. Rotate/revoke under Settings → API Keys.

Missing or malformed headers return 401 ERR_MISSING_AUTH. Unknown keys return 401 ERR_INVALID_API_KEY. Revoked keys return 403 ERR_REVOKED_API_KEY.

Each call runs in the context of the API key’s user. Projects must belong to that user; otherwise 404 ERR_PROJECT_NOT_FOUND.

These endpoints accept POST/PATCH/PUT/DELETE and require an API key with the read_write scope. A token with the read scope receives 403 ERR_INSUFFICIENT_SCOPE. Writes share a tighter rate limit (60/min/key) in addition to the global 300/min/key budget.

Quick start

The logical flow is: list resources → (optionally) fetch dimensions → query metrics. The first call to /dimensions/projects already validates your API key.

List your projects: GET /dimensions/projects
(Optional) Fetch project dimensions (competitors, models, locales, tags)
Request metrics under /metrics/*

Health Check

GET/ping

Cheapest way to verify a key works and measure round-trip latency. Returns pong, the authenticated user id and the server time. Pass project_id to also assert the key can reach that project.

Params:

project_idoptional

Account & Limits

GET/account

Plan, tracking cadence, subscription window, how much of each quota is used (prompts, projects, competitors per project, monthly GEO Writer tasks, team members) and the API rate limits that apply to your key. Call it before anything that spends quota so you can report what is left instead of finding the ceiling by hitting it. Limits resolve through the account owner, so a team member sees the capacity that applies to them. An unlimited quota returns limit and remaining as null, with unlimited set to true.

Params: none.

Official CLI & SDKs

Use the native CLI from a terminal or add a typed SDK to your application. Both are generated from the published OpenAPI document and work with the same API keys and base URL shown in this reference.

Rust CLI

A native Rust client for macOS, Linux, and Windows with named profiles plus JSON, table, and CSV output. Use it for quick checks, shell scripts, scheduled exports, and CI jobs.

Download the CLI Read the CLI guide

SDKs for 12 languages

Official generated clients for TypeScript, Python, Go, Java, Kotlin, C#, PHP, Ruby, Rust, Swift, Dart, and R. Each client stays aligned with the published OpenAPI document.

Browse SDK repositories Read the SDK guide

API Playground

Test API endpoints live

API Key

Endpoint

Parameters

Request Preview

curl -X GET "https://api.llmpulse.ai/api/v1/ping" -H "Authorization: Bearer YOUR_API_KEY"

Response

\--

Response will appear here...

Get API Key

Code Examples

Download: OpenAPI Swagger Postman

Ask AI: Open in ChatGPT Open in Claude View as Markdown

Language

Quick Start Example

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

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, _ := client.Do(req)
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);

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());

Authorization Header

curl -X GET -H "Authorization: Bearer YOUR_API_KEY" \
  "https://api.llmpulse.ai/api/v1/ping"

req, _ := http.NewRequest("GET", "https://api.llmpulse.ai/api/v1/ping", nil)
req.Header.Set("Authorization", "Bearer YOUR_API_KEY")
client := &http.Client{}
resp, _ := client.Do(req)
defer resp.Body.Close()

$client = new GuzzleHttp\Client();
$response = $client->request('GET', 'https://api.llmpulse.ai/api/v1/ping', [
    'headers' => ['Authorization' => 'Bearer YOUR_API_KEY']
]);
$data = json_decode($response->getBody(), true);

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.llmpulse.ai/api/v1/ping"))
    .header("Authorization", "Bearer YOUR_API_KEY")
    .GET()
    .build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());

Browse the API reference

Every endpoint, grouped by the resource it belongs to.

Core Concepts

The rules every endpoint shares: filters, metric definitions, JSON and CSV output, caching, error codes and versioning.

Projects

A project is one tracked brand: its domain, locale, prompts and competitors. Almost every other endpoint takes a project_id, so start here.

Metrics

Aggregated visibility, share of voice, citation and position data for your brand and its competitors, ready to chart.

Competitors

The brands you track alongside your own. The competitor ids returned here are the actor_id values the metrics endpoints report against.

Prompts

The questions we run against the AI models every week, and the execution records each run produces.

Collections & Tags

Collections (labelled Tags in the app) group prompts by topic, funnel stage or campaign so every metric can be filtered by them. A prompt can belong to several.

Answers (AI responses)

The AI responses behind every metric, with their full text, mentions, citations and sentiment analysis.

Mentions & Citations

The raw records behind the visibility metrics: one row per brand mention or per cited URL.

Sentiments

Sentiment records with their comments, topics and scores, plus the category catalog used to label them.

Sources & Citation Intelligence

Every URL the models cited, plus grouped URL, domain and host views, page-cache metadata, mention evidence inside cited pages, occurrence lists and sanitized...

AI Model Insights

Aggregate parts of the in-app AI Model Insights report.

AI & Agent Traffic

What AI actually sends to your site: referral traffic covers humans arriving from AI assistants, agent traffic covers the AI crawlers hitting your origin...

Shopping & Ads

Commercial surfaces inside AI answers: the product cards models return and the paid placements that run alongside them, with the merchants and advertisers...

Owned Media & Communities

Which of your own channels and which community conversations AI answers cite.

Reputation & Studies

Multi-model analyst reports: the monthly reputation scoring of your brand against its competitors, and the custom AI studies you define over any subjects and...

Search Console

Google Search Console performance data (impressions, clicks, CTR, average position) for projects with a connected GSC property. Growth plan or above required.

Recommendations

The same recommendation runs that power the in-app Recommendations page, plus the endpoint that launches a new one.

GEO Writer

Create and manage AI-powered GEO Writer tasks. Tasks are processed asynchronously, so create one and poll it until it completes.

Technical GEO Reports

Launch the Technical GEO bundle for a URL, then list, poll and retrieve each report. Reports run asynchronously.

Annotations

Mark a date on the project timeline (a campaign launch, a site migration, a redesign) so a chart shows what happened when. Available on every plan.

Webhooks

Receive a signed HTTP POST every time something happens in a project, with no polling.

Integrations

Ready-made ways to call the API: code snippets in seven languages, the Postman collection, and the MCP server for AI clients.

OAuth 2.1

OAuth 2.1 with PKCE and Dynamic Client Registration, so an MCP client can connect to LLM Pulse without the user pasting an API key.

Changelog

Every change to the REST API and MCP tools, newest first.