ChatGPT

Opens chatgpt.com as a logged-out visitor in a standard browser, sends prompt and returns the answer. Guests get ChatGPT's default free model, reported in model. With web_search (default true) ChatGPT searches the web before answering, so the answer cites sources; false lets it decide (it then searches for about two thirds of shopping and local prompts). Shopping prompts often come back with products (prices in the visitor's currency) and local prompts with places.

Billing: 4 credits per answer, 2 from the cache with max_age. AI answers cost the same in POST /v1/batches: the batch lane does not halve them. A failed, refused or empty answer is refunded (503, nothing billed).

Latency: answers typically take 10–30 s; requests wait up to 90 s. Set a client timeout of at least 120 s, or queue prompts with batches or a monitor instead of holding requests open.

Variance: assistants answer the same prompt differently from run to run and by country. To measure visibility, ask each prompt several times and compare shares, not single answers. See AI visibility tracking.

Request body

Example request

Authenticate with Authorization: Bearer $SERPKITE_API_KEY (GET requests may pass ?api_key= instead). The official SDKs read SERPKITE_API_KEY for you. See Authentication.

curl https://api.serpkite.com/v1/chatgpt \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"What are the best CRMs for a 10-person startup?","track":["hubspot.com","Pipedrive"]}'

Response fields

Every billed response also carries credit and latency headers (X-Credits-Used, X-Credits-Remaining, X-Request-Id…).

Example response

{
  "request": {
    "endpoint": "chatgpt",
    "prompt": "What are the best CRMs for a 10-person startup?",
    "country": "us",
    "web_search": true
  },
  "text": "For a 10-person startup, HubSpot CRM and Pipedrive are the usual shortlist. HubSpot's free plan covers contacts, deals and email tracking, and paid tiers add automation as you grow. Pipedrive is built around a visual sales pipeline and is quick to set up. Zoho CRM is the budget pick with a free plan for up to three users.",
  "markdown": "For a 10-person startup, **HubSpot CRM** and **Pipedrive** are the usual shortlist [1](https://www.example.com/best-crm-for-startups).\n\n- **HubSpot CRM**: the free plan covers contacts, deals and email tracking; paid tiers add automation [2](https://www.hubspot.com/products/crm).\n- **Pipedrive**: built around a visual sales pipeline, quick to set up [1](https://www.example.com/best-crm-for-startups).\n- **Zoho CRM**: the budget pick, free for up to three users [3](https://www.example.org/crm-pricing-2026).",
  "model": "instant",
  "sources": [
    {
      "position": 1,
      "title": "The best CRM software for startups in 2026",
      "link": "https://www.example.com/best-crm-for-startups",
      "domain": "example.com",
      "snippet": "We tested 14 CRMs with small sales teams…",
      "cited": true
    },
    {
      "position": 2,
      "title": "Free CRM software | HubSpot",
      "link": "https://www.hubspot.com/products/crm",
      "domain": "hubspot.com",
      "cited": true
    },
    {
      "position": 3,
      "title": "CRM pricing compared (2026)",
      "link": "https://www.example.org/crm-pricing-2026",
      "domain": "example.org",
      "date": "2026-09-14",
      "cited": true
    }
  ],
  "search_queries": [],
  "products": [],
  "mentions": [
    {
      "term": "hubspot.com",
      "mentioned": false,
      "cited": true,
      "sources": [
        2
      ],
      "text_position": -1
    },
    {
      "term": "Pipedrive",
      "mentioned": true,
      "cited": false,
      "sources": [],
      "text_position": 0.071
    }
  ],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 5,
    "cached": false,
    "engine": "chatgpt",
    "latency_ms": 31840,
    "parse_quality": "ok"
  }
}

Errors

Errors use one shape: {"error":{"code","message","request_id"}}. Errors are never billed. Full list in Errors.

Notes

• ChatGPT does not show guests the searches it runs, so search_queries is usually empty.
• We ask like a logged-out visitor in a standard browser and never sign in. When the assistant refuses the visit or asks the visitor to sign in, the call fails with 503 upstream_blocked and is free. See AI assistants.
• engine is not accepted (the path names the assistant), and neither are search options such as q, num or location: they return 400 invalid_request.
• Monitors take endpoint: "chatgpt" with prompt and track, and report every run's answer with new_sources and mentions. See Monitors.
• The remote MCP server has a chatgpt tool. See MCP server.
• The prompt is handled like a search query: never logged, and cached for at most an hour under a hashed key. See Privacy and data retention.

Related

• AI assistants overview
• AI visibility tracking guide
• Gemini
• Copilot Search
• Google AI Mode
• Brave AI
• ChatGPT API overview and pricing
• OpenAPI spec