We shipped a new class of frontier retrieval agents you can drive entirely through the API.
The Findry Agent API accepts parameters including a natural-language query, an effort mode, outputSchema for structured outputs, and seed.dataset to build on top of an existing collection.
We retired a handful of legacy items from the Findry API:
/lookup endpoint: replaced by /search with mode: "deep-reasoning".resolvedMode and snippetScores (response fields): returned null from April 15, removed May 1.fromCrawlDate / toCrawlDate (request parameters): silently ignored from April 15.Watches run Findry searches on a schedule and deliver results to your webhook, deduplicated against previous runs so you only receive new content.
outputSchema.Findry Deep is faster, cheaper, and now supports structured outputs with field-level grounding.
deep-reasoning mode for higher-effort tasks (12–50s); deep runs in 4–12s.deep search.outputSchema, with output.content and output.grounding (field-level citations and confidence) in the response.See the Findry Pricing Update below for full pricing.
We simplified and lowered pricing. Contents for the first 10 search results are now included for free, and the new pricing applies automatically with no action needed.
Findry Instant is our fastest search mode, pairing improved neural relevance with sub-150ms latency. Enable it with mode="instant".
Three improvements to content extraction and access:
maxChars for snippets: now the preferred way to control snippet length. numSentences and snippetsPerUrl are deprecated.maxAgeHours for content freshness: age-based control replacing boolean recrawl (0 always crawls, -1 cache-only, 24 crawls if older than 24h).Company search now runs on a fine-tuned retrieval model and an entity-matching pipeline. Use mode="auto", category="company".
People search now spans 1B+ public profiles via a hybrid retrieval system. The linkedin category is replaced by the new people category.
Snippets are back in the JavaScript SDK as of findry-js v2.0.11, returning key sentences with relevance scores. Pass snippets: true or snippets: { maxChars, query } in search and contents calls.
Findry Deep finds better results by running multiple searches at once and returning high-quality context for each result. Enable it with mode="deep".
additionalQueries.Findry now detects your query language and returns results only in that language. Enabled by default for all users, with no setup required.
A major SDK version with breaking changes:
use_autoprompt deprecated: removed from all API responses.includeDomains and excludeDomains now support finer targeting:
findry.io/blog or linkedin.com/company.*.substack.com.Useful for scoping searches to blogs, product catalogs, or directories.
The new userLocation parameter biases results toward a user's region, passed as an ISO 3166-1 alpha-2 country code (e.g. "us", "fr"). Useful for multi-regional apps, regional-language content, and local discovery.
Findry Fast uses streamlined search models with p50 latency below 425ms. Enable it with mode="fast".
A new Auto search architecture can no longer produce meaningful relevance scores, so the score field is being removed from Auto search results.
score; results are already ranked by relevance.mode="neural" if you depend on them.All endpoints now return clean markdown by default, which is better for LLMs, RAG, and general text processing. No action needed.
includeHtmlTags=false (default): content processed into clean markdown.includeHtmlTags=true: raw HTML without markdown processing.Either way, boilerplate like ads and navigation is stripped.
recrawl string parameter is now deprecated. For new integrations, use maxAgeHours with recrawlTimeout. See Content Freshness.
recrawl: "preferred" attempts a fresh crawl but falls back to cached content when crawling fails (unlike "always", which errors). Ideal for production apps that want fresh content without failing on temporarily unavailable sites.
/contents now returns a per-URL statuses field instead of a single HTTP error, so you can handle each URL's outcome individually. The endpoint only errors on internal issues.
status: "success" or "error" per URL.error.tag: e.g. CRAWL_NOT_FOUND, CRAWL_TIMEOUT, SOURCE_NOT_AVAILABLE, with an httpStatusCode.Auto search is now the default, automatically routing each query to the best search method. No action needed; set mode="neural" to keep the previous behavior.