Copilot Search

Asks Microsoft Copilot Search (bing.com/copilotsearch, Bing's AI answer) as a logged-out visitor and returns its answer, the sources it cited and, for shopping prompts, the sponsored product cards Bing shows next to it. The Copilot app itself (copilot.microsoft.com) asks every logged-out visitor to sign in, so it is not offered; Copilot Search is the answer Bing gives 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 15–40 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/copilot \
  -H "Authorization: Bearer $SERPKITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"best mattress for side sleepers","country":"us"}'

Response fields

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

Example response

{
  "request": {
    "endpoint": "copilot",
    "prompt": "best mattress for side sleepers",
    "country": "us",
    "language": "en"
  },
  "text": "Side sleepers usually do best on a medium-soft to medium mattress that cushions the shoulders and hips…",
  "markdown": "Side sleepers usually do best on a **medium-soft to medium** mattress that cushions the shoulders and hips [1](https://www.example.com/side-sleeper-mattress-guide)…",
  "sources": [
    {
      "position": 1,
      "title": "Best mattresses for side sleepers, tested",
      "link": "https://www.example.com/side-sleeper-mattress-guide",
      "domain": "example.com",
      "cited": true
    }
  ],
  "search_queries": [],
  "products": [
    {
      "position": 1,
      "title": "Example Hybrid Mattress, Queen",
      "price": "$899.00",
      "extracted_price": 899,
      "currency": "USD",
      "merchant": "Example Sleep",
      "link": "https://shop.example.com/hybrid-queen",
      "image": "https://shop.example.com/img/hybrid-queen.jpg"
    }
  ],
  "meta": {
    "request_id": "req_01J8ZK4M6Q2V7",
    "credits_used": 3,
    "cached": false,
    "engine": "copilot",
    "latency_ms": 22400,
    "parse_quality": "ok"
  }
}

Errors

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

Notes

• products are Bing's sponsored product cards for the prompt; link is the merchant's page.
• 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: "copilot" with prompt and track, and report every run's answer with new_sources and mentions. See Monitors.
• The remote MCP server has a copilot 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
• Gemini
• Google AI Mode
• Brave AI
• Copilot Search API overview and pricing
• OpenAPI spec