ChatGPT

Query ChatGPT via Wire — the answer, citations, and web sources it used

POSThttps://api.anakin.io/v1/wire/task

Run a prompt against ChatGPT and get the full answer with the web sources it cited when search is on — 1:1 with the real logged-in experience. Run it with the chatgpt action on POST /v1/wire/task.

Catalog: ai-assistants · action_id: chatgpt · Credits: 2 / call · Auth: none

Request Body

{
  "action_id": "chatgpt",
  "params": {
    "prompt": "best CRM for small teams",
    "web_search": true,
    "country": "us"
  }
}

Parameter	Type	Description
`action_id` required	string	Set to `chatgpt`
`params.prompt` required	string	The prompt to send to ChatGPT (max 4096 chars)
`params.web_search`	boolean	Request live web search. The response reports whether search actually ran. Default `false`
`params.additional_prompt`	string	Optional follow-up sent in the same conversation
`params.include_html`	boolean	Also include `answer_html` (rendered DOM, ~0.5 MB). Default `false`
`params.country`	string	2-letter proxy country for the session. Default `us`

Code Examples

curl -X POST https://api.anakin.io/v1/wire/task \
  -H "X-API-Key: your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "action_id": "chatgpt",
    "params": { "prompt": "best CRM for small teams", "web_search": true, "country": "us" }
  }'

import requests

res = requests.post(
    'https://api.anakin.io/v1/wire/task',
    headers={'X-API-Key': 'your_api_key'},
    json={
        'action_id': 'chatgpt',
        'params': {'prompt': 'best CRM for small teams', 'web_search': True, 'country': 'us'},
    },
)
job_id = res.json()['job_id']

const res = await fetch('https://api.anakin.io/v1/wire/task', {
  method: 'POST',
  headers: { 'X-API-Key': 'your_api_key', 'Content-Type': 'application/json' },
  body: JSON.stringify({
    action_id: 'chatgpt',
    params: { prompt: 'best CRM for small teams', web_search: true, country: 'us' },
  }),
});
const { job_id } = await res.json();

Response

202 Accepted

{ "status": "processing", "job_id": "…", "poll_url": "/v1/wire/jobs/…" }

Poll GET /v1/wire/jobs/{id} until status: "completed":

200 OK

{
  "status": "completed",
  "credits_used": 2,
  "execution_ms": 17889,
  "data": {
    "status": "ok",
    "data": {
      "prompt": "best CRM for small teams",
      "title": "Best CRMs for small teams",
      "answer_text": "For small teams, the strongest options are …",
      "answer_text_markdown": "…",
      "citations": [
        { "ref": 1, "url": "https://…", "title": "…", "domain": "…", "position": 1,
          "ref_type": "web", "description": "…", "result_source": "search", "date_published": "…", "cited": true }
      ],
      "search_sources": [], "web_search_queries": ["best CRM small teams 2026"], "web_search_triggered": true,
      "ads": [], "shopping": [], "entities": [], "recommendations": [], "business_locations": [],
      "model": "gpt-…", "country": "us", "timestamp": "…"
    },
    "meta": { "action_id": "chatgpt", "catalog_slug": "ai-assistants", "envelope_version": "v1" }
  }
}

Field	Type	Description
`data.data.answer_text`	string	The plain-text answer (also `answer_text_markdown`, and `answer_html` when `include_html`)
`data.data.citations`	array	`{ ref, url, title, domain, position, ref_type, description, result_source, date_published, cited }`
`data.data.search_sources`	array	Sources ChatGPT pulled during web search
`data.data.web_search_queries`	string[]	The queries ChatGPT actually searched
`data.data.web_search_triggered`	boolean	Whether live search ran
`data.data.ads`	array	Ad slots when served (see note)

Set web_search: true to force live sources — without it ChatGPT may answer from model knowledge with no citations. Since OpenAI stopped serving ads to non-logged-in sessions, ads is usually empty. Billed only on success.