Search

Run a prompt across the AI models and get each model’s answer plus the sources it cited.

Overview

/v1/search is the primitive the rest of the API is built on. Pass a query and get back the full prose answer from each model, ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews, with the sources each one cited, in one JSON response.

Omit models for the three default surfaces, set fullSweep for all five, or pass it to narrow to the ones you need (you only pay for the models you query, see Per-model pricing).

Reference

POST/v1/search

$0.01 to $0.06/model · billed per model queried, so all 5 models = $0.20. Pass models to query fewer.

Parameters

`query`required	string	The query to run against the AI models.
`models`optional	array of enum (chatgpt \| claude \| perplexity \| gemini \| google_ai_overview)	Optional model subset. Omit to query the default surfaces (chatgpt, perplexity, gemini). Pass ["perplexity"] or ["perplexity","claude"] when the user names specific surfaces or wants to reduce cost. The full set is chatgpt, claude, perplexity, gemini, google_ai_overview — to query all of them, set fullSweep instead of listing them.
`fullSweep`optional	boolean	Query all five AI surfaces instead of the three default ones, adding claude and google_ai_overview. Costs more per call. Use it when the user wants complete cross-model coverage, is comparing surfaces against each other, or asks specifically about Claude or Google AI Overviews. Ignored when models is given.

Request

curl https://www.cite42.dev/api/v1/search \
  -X POST \
  -H "Authorization: Bearer $CITE42_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query":"best startup CRM"}'

Response

{
  "query": "best startup CRM",
  "results": [
    {
      "model": "chatgpt",
      "ok": true,
      "answer": "Acme CRM, Rival CRM, and Legacy CRM stand out for startup teams.",
      "citations": [
        {
          "url": "https://reviews.example/startup-crm",
          "title": "Startup CRM guide"
        }
      ],
      "latencyMs": 4120
    }
  ],
  "measurement": {
    "methodologyVersion": "2026-07-21-v2",
    "surfaces": [
      {
        "model": "chatgpt",
        "provider": "OpenAI",
        "access": "official-api",
        "webSearch": "auto"
      }
    ]
  },
  "requestId": "…",
  "billing": {
    "cost": {
      "microCredits": 20000,
      "usd": "0.20"
    },
    "balance": {
      "microCredits": 1336000,
      "usd": "13.36"
    }
  }
}