Gemini

Opens gemini.google.com as a logged-out visitor in a standard browser and sends prompt. When Gemini grounds its answer in Google Search, the pages it used come back in sources and the [n](link) citations in markdown point at them. model is the model Gemini reports to guests.

Billing: 3 credits per answer, 1.5 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 5–30 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/gemini \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"How do heat pumps work in cold climates?"}'

Response fields

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

Example response

{
  "request": {
    "endpoint": "gemini",
    "prompt": "How do heat pumps work in cold climates?",
    "country": "us",
    "language": "en"
  },
  "text": "Cold-climate heat pumps keep heating well below freezing because they use variable-speed compressors and refrigerants that still absorb heat from outdoor air at -15 °C or lower…",
  "markdown": "Cold-climate heat pumps keep heating well below freezing because they use **variable-speed compressors** and refrigerants that still absorb heat from outdoor air at -15 °C or lower [1](https://www.example.gov/heat-pumps-cold-climates)…",
  "model": "3.5 Flash-Lite",
  "sources": [
    {
      "position": 1,
      "title": "Heat pumps in cold climates",
      "link": "https://www.example.gov/heat-pumps-cold-climates",
      "domain": "example.gov",
      "cited": true
    }
  ],
  "search_queries": [],
  "products": [],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 5,
    "cached": false,
    "engine": "gemini",
    "latency_ms": 61200,
    "parse_quality": "ok"
  }
}

Errors

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

Notes

• Most answers take 5–30 s (about 12 s at the median); answers that search the web take longer.
• 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: "gemini" with prompt and track, and report every run's answer with new_sources and mentions. See Monitors.
• The remote MCP server has a gemini 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
• ChatGPT
• Copilot Search
• Google AI Mode
• Brave AI
• Gemini API overview and pricing
• OpenAPI spec