twitter

AI-powered X (Twitter) search via xAI Grok

Natural-language search over X (Twitter) powered by xAI's Grok 4.3 model with the built-in x_search tool. Returns a synthesised answer plus X source citations. Pin results to specific authors via from_handles (or exclude with exclude_handles), and narrow to a time window with from_date / to_date. Costs 5 credits per call regardless of how many internal x_search invocations the model performs (see tool_calls_count in the response for visibility). Auto-refunds on upstream failure. Best for freeform questions like 'what is @elonmusk saying about xAI this week' that would otherwise require multiple structured calls to /v1/twitter/profile, /v1/twitter/user/tweets, etc. Read a thin answer as thin retrieval, never as an empty corpus. This is a discovery surface: the model runs a handful of internal searches and answers from what they returned, so a reply such as 'limited posts appear on this topic' is a statement about that retrieval, not about X. Keyword search over the same window routinely finds substantially more. Most calls take 10 to 30 seconds and broad multi-keyword prompts up to about a minute, so set a client timeout of at least 100 seconds; that makes it a poor fit for tight iteration loops. An identical request repeated within 30 minutes is answered from cache, free, so polling the same question more often than that returns the same answer.

get/twitter/ai-search

Request

  • Base URL: https://www.socialcrawl.dev/v1
  • URL: https://www.socialcrawl.dev/v1/twitter/ai-search
  • Auth: API key in header x-api-key

Query parameters

querystring required

Natural-language prompt describing what you want to learn from X. The model autonomously searches X using the x_search tool with any handle / date filters you provide.

from_handlesstring

Comma-separated X handles (max 10). Restricts the search to posts from these accounts only. Mutually exclusive with exclude_handles.

exclude_handlesstring

Comma-separated X handles (max 10) to exclude from search results. Mutually exclusive with from_handles.

from_datestring

ISO 8601 start date (YYYY-MM-DD). Limits the search window to posts on or after this date.

to_datestring

ISO 8601 end date (YYYY-MM-DD). Limits the search window to posts on or before this date.

Headers

Cache-Controlstring

Send no-cache to bypass the response cache and force a live fetch. Billed at the normal endpoint cost; the fresh result is written back to cache for the next caller. Only the no-cache directive triggers this. See the Response Schema guide for details.

Idempotency-Keystring

Optional UUID that makes the request safely retriable. The key is reserved atomically per account before billing. A concurrent retry receives 409 IDEMPOTENCY_IN_PROGRESS with a Retry-After of 1 second while the original is young, growing to a quarter of the time it has been running (at most 30); a crashed reservation expires after 5 minutes. A replay keeps the cached payload immutable except for billing metadata: credits_used becomes 0, idempotent_replay becomes true, and credits_remaining is refreshed to the current balance. A known current balance appears in both the body and X-Credits-Remaining header; no balance row resolves to 0. On a transient lookup failure, body credits_remaining is null and X-Credits-Remaining is omitted. Completed outcomes expire after 24 hours. If the claim store is unavailable, the request fails closed before billing. GET endpoints do not combine idempotent replay with Server-Sent Events: use Accept: application/json when sending this header. The unsupported key-plus-SSE combination is rejected before billing.

Response

Successful response

successboolean required

Whether the request succeeded

platformstring required

Platform name

endpointstring required

API endpoint path

credits_usedinteger required

Number of credits consumed

credits_remaininginteger nullable required

Current account balance, or null when this response could not establish one. Free cache hits always return null because they do not establish an authoritative post-request balance. An idempotency replay also returns null when its current-balance lookup fails. It is never a fabricated zero, so a zero here means the account really is empty. The authoritative reading is the one on a billed response, which comes straight from the deduction.

request_idstring required

Unique request identifier for support

cachedboolean required

Whether the response was served from cache

idempotent_replayboolean

True only when this response is an idempotency replay

Example response

{
  "success": true,
  "platform": "twitter",
  "endpoint": "/v1/twitter/ai-search",
  "credits_used": 1,
  "credits_remaining": 4999,
  "request_id": "req-abc123",
  "idempotent_replay": true,
  "meta": {
    "hint": {
      "code": "search_multi",
      "message": "You searched \"matcha\" on 3 platforms one call at a time; /v1/search/multi returns each platform's own search rows in one call at the same price per platform, and a platform with no rows is not charged.",
      "method": "GET",
      "path": "/v1/search/multi?query=matcha&platforms=instagram,tiktok,youtube"
    }
  }
}

Changes

No recorded changes to this operation across all 1 revision of this API.