GeoptieGeoptie Logo

REST API

The AI visibility and rank tracking API for your reporting stack

Pull the visibility, prompts, answers, citations and competitor data from Geoptie into BigQuery, Looker Studio, client dashboards or your own product. One bearer key, JSON over HTTPS, and no monthly request quota.

Data from
  • ChatGPT
  • Claude
  • Perplexity
  • Gemini
  • AI Overviews
  • AI Mode
  • Copilot
curl -sS "https://api.geoptie.com/v1/brands" \
  -H "Authorization: Bearer $GEOPTIE_API_KEY"
Response · 200
{
  "data": [
    {
      "id": "3f2a6c1e-0b7d-4e59-9a41-2c8d5e7f9b10",
      "name": "Example Brand",
      "domain": "example.com",
      "engines": ["chatgpt", "claude", "perplexity", "gemini"],
      "country": "US"
    }
  ],
  "has_more": false,
  "next_cursor": null
}
  • v1

    stable REST API

  • 7

    AI engines covered

  • 120/min

    requests, no monthly cap

  • $99

    per month, Professional plan

Trusted by marketing teams and agencies

AKQA
Amgen
ARM Worldwide
Mazda
Capgemini
Decathlon
Dentsu
HCLTech
HSAD
Infineon
Redbrain
Verizon
Webrepublic
Wpromote
AKQA
Amgen
ARM Worldwide
Mazda
Capgemini
Decathlon
Dentsu
HCLTech
HSAD
Infineon
Redbrain
Verizon
Webrepublic
Wpromote

What is an AI visibility API?

An AI visibility API returns how AI engines such as ChatGPT, Claude, Perplexity, Gemini and Google's AI answers mention and cite a brand, as data your own systems can use. It also works as an AI rank tracker API: visibility and position for every tracked prompt, on every engine, each day.

Geoptie's REST API serves the same metrics as the dashboard, so the numbers in a warehouse, a BI dashboard, a client report or a Slack alert match what your team sees.

Your first request in under a minute

Create a key in the dashboard and send it as a bearer token. GET /v1/brands proves the key works and returns the brand ids every other endpoint uses.

Set up in three steps

  1. 1

    Create a key

    In the dashboard under API keys, for the whole workspace or for chosen brands.

  2. 2

    Call GET /v1/brands

    It proves the key works and returns the brand ids every other endpoint uses.

  3. 3

    Pull the data you need

    Visibility, prompts, answers, citations and competitors, by brand and engine.

curl -sS "https://api.geoptie.com/v1/brands" \
  -H "Authorization: Bearer $GEOPTIE_API_KEY"

Endpoint catalogue

Brands

  • GET/v1/brands
  • POST/v1/brands
  • GET/v1/brands/{id}
  • GET/v1/brands/{id}/visibility

Prompts and answers

  • GET/v1/brands/{id}/prompts
  • POST/v1/brands/{id}/prompts
  • GET/v1/prompts/{id}/responses
  • GET/v1/prompts/{id}/mentions

Citations

  • GET/v1/brands/{id}/citations
  • GET/v1/brands/{id}/citations/urls
  • GET/v1/brands/{id}/citations/domains
  • GET/v1/brands/{id}/citations/trends

Competitors

  • GET/v1/brands/{id}/competitors
  • GET/v1/brands/{id}/competitors/trends
  • POST/v1/brands/{id}/tracked-competitors
  • POST/v1/brands/{id}/ignored-competitors

Recommendations and audits

  • GET/v1/brands/{id}/recommendations
  • POST/v1/brands/{id}/recommendations/generate
  • POST/v1/audit-reports
  • GET/v1/audit-reports/{id}

Content

  • POST/v1/brands/{id}/generations
  • POST/v1/brands/{id}/generations/{generationId}/draft
  • POST/v1/brands/{id}/optimizations
  • GET/v1/brands/{id}/topics

48 operations in total, including updates and deletes. The full reference is in the API docs.

Built for production reporting

The API returns the numbers your dashboard shows, in a shape that drops straight into a warehouse or a client report.

Same numbers as the dashboard

Precomputed visibility, position and share of voice, not raw rows to reassemble, so a client report matches what your team sees.

Read and write

Track prompts, manage topics and competitors, work the recommendation queue, run audits and generate content through the same API.

Workspace and brand-scoped keys

Give a client, a dashboard or an internal team a key that reaches only their own brand. Revoking takes effect within a minute.

Paced, predictable jobs

Cursor pagination, ISO 8601 dates and rate-limit headers on every response, so a scheduled job paces itself without hitting a 429.

Errors you can act on

Standard HTTP status codes with a stable error code, and an X-Request-Id on every response for support to trace.

Stable versioning

v1 is stable. New fields are added without notice, and breaking changes ship as /v2 with 90 days' notice.

What teams build with it

Client dashboards

Agencies feed each client's AI visibility into Looker Studio or their own portal, with a brand-scoped key per client.

Warehouse sync

A nightly job copies visibility, citations and competitor data into BigQuery or Snowflake next to SEO and analytics data.

Alerts

A scheduled check posts to Slack or email when a priority prompt drops on an engine.

AI assistants

The same key powers the Geoptie MCP server for Claude Code, Cursor and Codex.

Included on Professional and Enterprise

Most popular

Professional

$99/month

  • 10 brands and 100 prompts
  • REST API and MCP server
  • White-label reports
  • Unlimited seats
Get started

Enterprise

$399/month

  • Unlimited brands and 400 prompts
  • REST API and MCP server
  • White-label reports
  • Unlimited seats
Get started

Compare all plans

AI visibility API FAQ

What data does the Geoptie API return?
Everything the dashboard shows: brand visibility over time and per engine, tracked prompts, the full answers engines returned, the brands they named, the pages and domains they cited, competitor share of voice, topics, recommendations, audit reports and generated content.
Which plans include API access?
Professional ($99 a month) and Enterprise ($399 a month). One key works for both the REST API and the MCP server. Starter does not include API access.
How does authentication work?
Every request sends an API key as a bearer token in the Authorization header. Keys are created in the dashboard, cover either the whole workspace or chosen brands, and are shown only once. Create one key per integration so you can revoke it without affecting the others.
What are the API rate limits?
120 requests per minute per key on every eligible plan, with no monthly request quota. Some endpoints add their own limit: reading full answer text is capped at 600 an hour, and endpoints that run a model allow a few calls per minute and two at a time.
Can I pull competitor data through the API?
Yes. The competitors endpoints return your brand against its competitors on the same prompts, competitor trends over time, and one competitor in detail. You can also track, edit or ignore competitors through the API.
Can I give a client API access to only their brand?
Yes. Brand-scoped keys reach only the brands you choose, and everything outside that scope returns 404. They suit client dashboards, contractors and internal teams that need one brand's data.
Which AI engines does the API cover?
ChatGPT, Claude, Perplexity, Gemini, Google AI Overviews, Google AI Mode and Microsoft Copilot. Each brand tracks any four of the seven, and its current selection is returned on the brand object.
Is there an MCP server as well?
Yes. The Geoptie MCP server uses the same key and the same limits, and lets Claude Code, Cursor, Codex and other MCP clients query and act on your data in conversation.

Put AI visibility next to the rest of your data

Start on Professional, create a key, and your first request returns your brands in under a minute.

Get started