The API for GEO

Real-browser answers from 14 AI engines, the sources behind them and how both change over time, as JSON.

500 free credits · start right after sign-up

ChatGPT web search answer comparing wireless earbuds in a table with source chips and links. — ChatGPTchatgpt.com

API responseCompleted

Country: US
Credits: 1
Sources: 3

{
  "task": {
    "taskType": "CHATGPT"
  },
  "response": {
    "sources": [
      {
        "url": "https://www.wired.com/gallery/best-noise-canceling-earbuds/",
        "label": "Best Noise-Canceling Earbuds: Bose, Sony, Apple, and More | WIRED",
        "footnote": false,
        "position": 1,
        "attribution": "WIRED",
        "description": "",
        "datePublished": "March 29, 2026"
      },
      {
        "url": "https://www.tomsguide.com/audio/earbuds/best-noise-canceling-earbuds",
        "label": "Best noise-canceling earbuds in 2026: Tested and reviewed | Tom's Guide",
        "footnote": false,
        "position": 2,
        "attribution": "Tom's Guide",
        "description": "",
        "datePublished": "July 24, 2026"
      },
      {
        "url": "https://www.wired.com/story/best-wireless-earbuds/",
        "label": "Best Wireless Earbuds We’d Buy Right Now (2026): Apple, Sony, Bose, and More | WIRED",
        "footnote": false,
        "position": 3,
        "attribution": "WIRED",
        "description": "",
        "datePublished": "August 10, 2026"
      }
    ],
    "searchQueries": [
      "best wireless earbuds commuting noise cancellation battery life Sony Bose Apple"
    ],
    "text": "For commuting, I’d prioritize strong ANC (trains, buses, traffic) and 6+ hours of playback. These three are top picks: ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com))\n\n| Earbuds | Noise cancellation | Battery life (ANC on) |\n|---|---|---|\n| Bose QuietComfort Ultra Earbuds (2nd Gen) | Excellent — among the strongest ANC available | ~6 hrs (24 hrs with case) ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com)) |\n| Sony WF-1000XM5 | Excellent — very effective for commute noise | ~8 hrs (24 hrs with case) ([Tom's Guide](https://www.tomsguide.com/audio/earbuds/best-noise-canceling-earbuds?utm_source=chatgpt.com)) |\n| Apple AirPods Pro 3 | Excellent — especially for iPhone users | Up to ~8 hrs (24 hrs with case) ([WIRED](https://www.wired.com/story/best-wireless-earbuds/?utm_source=chatgpt.com)) |\n\n**Recommendation:**  \n- Best pure noise blocking: Bose.  \n- Best overall balance: Sony.  \n- Best if you use iPhone: AirPods Pro 3. ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com))\n\nSources: [WIRED noise-canceling earbuds guide](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com) · [Tom’s Guide ANC earbuds guide](https://www.tomsguide.com/audio/earbuds/best-noise-canceling-earbuds?utm_source=chatgpt.com) ·",
    "markdown": "For commuting, I’d prioritize strong ANC (trains, buses, traffic) and 6+ hours of playback. These three are top picks: ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com))\n\n| Earbuds | Noise cancellation | Battery life (ANC on) |\n|---|---|---|\n| Bose QuietComfort Ultra Earbuds (2nd Gen) | Excellent — among the strongest ANC available | ~6 hrs (24 hrs with case) ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com)) |\n| Sony WF-1000XM5 | Excellent — very effective for commute noise | ~8 hrs (24 hrs with case) ([Tom's Guide](https://www.tomsguide.com/audio/earbuds/best-noise-canceling-earbuds?utm_source=chatgpt.com)) |\n| Apple AirPods Pro 3 | Excellent — especially for iPhone users | Up to ~8 hrs (24 hrs with case) ([WIRED](https://www.wired.com/story/best-wireless-earbuds/?utm_source=chatgpt.com)) |\n\n**Recommendation:**  \n- Best pure noise blocking: Bose.  \n- Best overall balance: Sony.  \n- Best if you use iPhone: AirPods Pro 3. ([WIRED](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com))\n\nSources: [WIRED noise-canceling earbuds guide](https://www.wired.com/gallery/best-noise-canceling-earbuds/?utm_source=chatgpt.com) · [Tom’s Guide ANC earbuds guide](https://www.tomsguide.com/audio/earbuds/best-noise-canceling-earbuds?utm_source=chatgpt.com) ·",
    "model": "gpt-5-6",
    "shoppingCards": []
  }
}

See every response field

Engines

14 AI engines, one scraping API

Each task scrapes the engine's live website, the screen your customers see, and returns the answer and its sources as JSON.

See every engine

Live

Cost

Over 57× cheaper than the OpenAI API

The OpenAI API with web search costs $57.86 for 1,000 ChatGPT answers. querying.ai opens chatgpt.com in a real browser and scrapes the answers your customers see, for $1.00 on the Max plan.

OpenAI API

$57.86

chat-latest + web_search

querying.ai Max plan

$1.00

chatgpt.com in a real browser

Cost of 1,000 answers

How we measured

Ten shopping questions sent to the OpenAI Responses API with web search set to the US, after one warm-up call. Each answer ran one search. Token counts are averages.

Read the full measurement

List prices on October 3, 2026

OpenAI charges $5.00 per 1M input tokens, $0.50 cached, $30.00 per 1M output tokens and $10.00 per 1,000 searches. On querying.ai, 1,000 ChatGPT answers use 1,000 credits.

1,000 ChatGPT answers on each plan

Basic	$2.50	23× cheaper
Pro	$1.18	49× cheaper
Scale	$1.04	55× cheaper
Max	$1.00	57× cheaper

ChatGPT

Follow-ups, ads and card details from ChatGPT

Keep asking in the same ChatGPT conversation with followUps. Every answer comes back with the ads ChatGPT showed under it, and include.entityDetails adds the panel each product, place or brand card opens.

ChatGPTcountry: "US"

Best robot vacuum mop combos under $1000

For 2026, I’d focus on models that do more than drag a damp cloth around: look for a self-cleaning mop system, automatic dust emptying, smart mapping, and a way to keep carpets dry.

Dreame L40s Ultra KitECOVACS DEEBOT T90 PRO OMNIeufy X10 Pro OmniRoborock Qrevo SeriesDreame X50 Ultra Kit

followUps[0]

Which one is best for pet hair?

Of the models we discussed, my first choice would be the Dreame L40s Ultra Kit for a home with pets and a mix of hard floors and carpet.

eufy Omni C28MOVA P50 Pro Ultra

See the answer. Check its sources. Track it.

With one API, collect the AI answers your customers see, find the source passages that match each answer and track your mention rate over time.

Collect consumer answers and sources from ChatGPT, Gemini, Perplexity, Copilot, Bing AI, Google AI, Meta AI, Qwen, Doubao, Baidu and Naver AI as JSON.

Input: A prompt, an engine, a country.
Real browser: A real ChatGPT session, opened in that country.
Output: The answer, its sources and search queries, plus each engine's extras.

Explore Answers →

Audit one AI answer for your brand: whether it is named and at what rank, which pages the engine searched and cited, and what to do next.

Input: A finished answer task or an AI answer with its citations, plus your brand and competitors.
Paragraph match: The pages the engine searched and cited are read, and every brand on them is matched to the answer.
Output: Brand rank and visibility stage, searched and cited pages with their channels, prioritized actions and paragraph-level evidence.

Explore Citation Analysis →

Save a prompt set, pick engines and a cadence. Every answer is scored for your brand and competitors, and you track how your mention rate and share of voice against competitors change.

Input: Prompts, brand aliases, competitors, engines, a cadence.
On a schedule: Fires on schedule; every answer is scored for mentions and citations.
Output: Mention rate per engine, and your share of voice against competitors.

Explore Monitors →

How it works

Submit a task. Receive the result by webhook.

Every task runs async. Post it, get an id back right away, and receive the result at your webhook as JSON: the answer, citations and timing.

Post a prompt

Choose the engine and the country. Add a webhook URL, or poll the task by its id.

POST /v1/async/task

curl -X POST https://api.querying.ai/v1/async/task \-H "Authorization: Bearer $QUERYING_API_KEY" \-H "Content-Type: application/json" \-d '{"taskType": "CHATGPT","payload": { "prompt": "Best running shoes for flat feet in 2026", "country": "US" },"webhook": { "url": "https://yours.app/hooks/querying" }}'

Get the task id at once
Your server moves on while a real browser opens the engine in that country and asks.
200 OK
```
{"success": true,"task": { "id": "753c5cb2-ceda-4219-9c27-c59e9a1803ac", "status": "QUEUED" }}
```

Receive the answer as JSON

The answer, the products and brands it names, the pages it read and cited, and the searches it ran. Each delivery gets up to five attempts with backoff.

POST https://yours.app/hooks/querying

{"task": { "id": "753c5cb2-ceda-4219-9c27-c59e9a1803ac", "status": "COMPLETED" },"response": {"model": "gpt-6","text": "# Best running shoes for flat feet in 2026\n\nIf you have …","entities": [{ "name": "Brooks Adrenaline GTS 25", "type": "product" },{ "name": "ASICS GEL-Kayano 33", "type": "product" },…],"sources": [{"position": 1,"url": "https://www.runnersworld.com/gear/a25750345/running-shoes-flat-feet/","cited": true},…],"searchQueries": ["best running shoes for flat feet 2026 stability shoes reviews updates"],"durationMs": 34886}}

A real ChatGPT task from November 5, 2026, shortened. The same request in Python and TypeScript

Agents

Connect querying.ai to your AI stack

Give an agent your API key and it runs every engine, manages monitors and reads the results on its own, over MCP, skills or the REST API.

mcp.json

{
  "mcpServers": {
    "querying": {
      "url": "https://mcp.querying.ai/mcp",
      "headers": {
        "Authorization": "Bearer vt_live_…"
      }
    }
  }
}

Remote MCP server

Add one URL to any MCP client to run engines, monitors and search from chat with your key.

Read the docs ↗

/.well-known/agent-skills/

Agent skills

SKILL.md files teach coding agents each job, from collecting answers to tracking visibility.

index.json →

querying.ai

Docs agents read

auth.md covers keys and limits, openapi.json describes every endpoint and llms.txt maps the site.

Use cases

What teams run on querying.ai

Every number below comes from querying.ai's own public boards: the 15 category monitors of the AI Index and the ChatGPT Model Tracker.

All use cases

GEO & AEO Monitoring

Track how AI search surfaces mention your brand, products, and competitors across engines, countries, and prompts.

Learn more

Competitive Intelligence

See what AI engines recommend in your market: which brands get cited and which products surface.

Learn more

Agency Dashboards

Monitor dozens of clients across engines and regions simultaneously with batch APIs and webhooks.

Learn more

Research & Analysis

Study AI search behavior across markets with structured data for academic research, content strategy, and SEO.

Learn more

Pricing

Credits get cheaper as you scale

Bigger plans buy cheaper credits, down to $1.00 per 1,000 on Max. You pay only for successful tasks.

Free

500 credits, one time

Try every engine before adding a payment method.

≈ 400-500 tasks

2 concurrent tasks
Every engine we serve
Every region we serve
Webhooks + polling

Basic

$20/month

8,000 credits included

One product tracked, or an API integration you're starting.

≈ 6,400-8,000 tasks / month

50 concurrent tasks
Every engine we serve
Every region we serve
Webhooks + polling
Email support

Recommended

Pro

$200/month

53% off vs Basic

170,000 credits included

A brand tracked daily across engines, countries and prompts.

≈ 136,000-170,000 tasks / month

200 concurrent tasks
Everything in Basic
Batch submission
Priority support

Scale

$500/month

58% off vs Basic

480,000 credits included

Several brands, or one brand across many engines, countries and prompts.

≈ 384,000-480,000 tasks / month

500 concurrent tasks
Everything in Pro
Usage review on request
Priority support

Max

$1,000/month

60% off vs Basic

1,000,000 credits included

≈ 800,000-1,000,000 tasks / month

An agency or platform running many brands at once.

1,000 concurrent tasks
Everything in Scale
Usage review on request
Priority support

Enterprise

Custom

Volume pricing

Talk to us

Negotiated

Committed volume and terms that fit procurement.

Everything in Max
Custom engine mix
Shared support channel

Task estimates use answer-engine rates of 1-1.25 credits. Other products and optional analysis are priced separately.

See what a credit buys, per engine

Start with 500 free credits

Run your first task in the Playground, or call the API with your key.

See pricing

Connecting an AI agent? Start with auth.md

The API for GEO

14 AI engines, one scraping API

Over 57× cheaper than the OpenAI API

How we measured

List prices on October 3, 2026

1,000 ChatGPT answers on each plan

Follow-ups, ads and card details from ChatGPT

See the answer. Check its sources. Track it.

AnswersThe AI answers your customers see.

Citation AnalysisWhere your brand stands in an AI answer.

MonitorsYour mention rate and share of voice, tracked on a schedule.

Submit a task. Receive the result by webhook.

Post a prompt

Get the task id at once

Receive the answer as JSON

Connect querying.ai to your AI stack

Remote MCP server

Agent skills

Docs agents read

What teams run on querying.ai

GEO & AEO Monitoring

Competitive Intelligence

Agency Dashboards

Research & Analysis

Credits get cheaper as you scale

Start with 500 free credits