Grok

Query xAI's Grok via Wire — the answer plus the web sources it cited

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

Run a prompt against xAI's Grok and get the answer with the web sources it used. Grok runs on your own connected account (auth_mode: "required") — pass its credential_id. Run it with the grok_prompt action on POST /v1/wire/task.

Catalog: grok · action_id: grok_prompt · Credits: 10 / call · Auth: required

Request Body

{
  "action_id": "grok_prompt",
  "credential_id": "11111111-2222-3333-4444-555555555555",
  "params": { "prompt": "best CRM for small teams", "model": "fast" }
}

Parameter	Type	Description
`action_id` required	string	Set to `grok_prompt`
`credential_id` required	string (UUID)	Your connected Grok account — from GET /v1/wire/identities
`params.prompt` required	string	Your question for Grok (≤ 16384 chars)
`params.model`	string	`fast` (Grok 3), `expert` (Grok 4), or `auto`. Default `fast`
`params.timeout`	number	Max seconds to wait for the answer. Default `90`

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": "grok_prompt",
    "credential_id": "11111111-2222-3333-4444-555555555555",
    "params": { "prompt": "best CRM for small teams", "model": "fast" }
  }'

import requests

res = requests.post(
    'https://api.anakin.io/v1/wire/task',
    headers={'X-API-Key': 'your_api_key'},
    json={
        'action_id': 'grok_prompt',
        'credential_id': '11111111-2222-3333-4444-555555555555',
        'params': {'prompt': 'best CRM for small teams', 'model': 'fast'},
    },
)
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: 'grok_prompt',
    credential_id: '11111111-2222-3333-4444-555555555555',
    params: { prompt: 'best CRM for small teams', model: 'fast' },
  }),
});
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": 10,
  "data": {
    "status": "ok",
    "data": {
      "prompt": "…", "model": "fast", "web_search": true,
      "answer_text": "…", "answer_complete": true,
      "sources": [ { "url": "https://…", "title": "…" } ],
      "conversation_id": "…", "account_email": "…", "accounts_tried": 1, "prompt_sent_at": "…"
    },
    "meta": { "action_id": "grok_prompt", "catalog_slug": "grok", "envelope_version": "v1" }
  }
}

Field	Type	Description
`data.data.answer_text`	string	The answer
`data.data.answer_complete`	boolean	Whether the stream finished within `timeout`
`data.data.sources`	array	Web sources cited — `{ url, title }`
`data.data.model`	string	The Grok model used
`data.data.conversation_id`	string	The Grok conversation id

Auth required — omitting credential_id returns 401 AUTH_REQUIRED. Premium engine: 10 credits/call. model: "expert" uses Grok 4 (slower, deeper). Billed only on success.