Tavily web search with optional LLM-generated answer
Runs a web search via Tavily and returns ranked results plus an optional LLM-generated answer synthesised from the top sources. Set include_answer=true to enable answer synthesis. Use search_depth=advanced for higher-relevance results (also unlocks chunks_per_source). Filter results to specific domains via include_domains (comma-separated), or exclude via exclude_domains. Time-bounded queries via time_range (d / w / m / y) or explicit start_date / end_date (YYYY-MM-DD).
Request
- Base URL: https://www.socialcrawl.dev/v1
- URL: https://www.socialcrawl.dev/v1/tavily/search
- Auth: API key in header x-api-key
Query parameters
The search query: natural-language free text.
Latency-vs-relevance tradeoff. basic is the default; advanced unlocks chunks_per_source and higher-relevance ranking.
Search category. Defaults to general. Use news for time-sensitive queries and finance for market data.
Time window relative to now. Accepts day / week / month / year (or shorthand d / w / m / y).
Number of results to return (1-20). Defaults to 5.
Max relevant chunks returned per source (1-5). Only honoured when search_depth=advanced. Defaults to 3.
Include images alongside the result content.
Include AI-generated descriptions for the returned images.
Include an LLM-generated answer string synthesised from the top sources.
Include the raw HTML/text alongside the cleaned content.
Comma-separated list of domains to restrict results to (e.g. nytimes.com,reuters.com).
Comma-separated list of domains to exclude from results.
ISO 3166-1 alpha-2 country code to bias results toward.
Inclusive lower bound on result publish date (YYYY-MM-DD).
Inclusive upper bound on result publish date (YYYY-MM-DD).
Headers
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.
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
Example response
{
"success": true,
"platform": "tavily",
"endpoint": "/v1/tavily/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.