# Providers · searchSDK

Compare 15 provider integrations, explore their search and native API capabilities, and find the TypeScript reference for each.

Canonical: https://searchsdk.dev/providers
Markdown: https://searchsdk.dev/providers.md

## Context.dev

Web search with optional page content and query-relevant passages.

Normalized search returns descriptions and credits. Native APIs add scraping, parsing, brand data, batches, monitors, and account operations.

- [SDK reference](https://searchsdk.dev/docs/providers/context)
- [Provider reference](https://docs.context.dev/api-reference/web-scraping/search)

## TinyFish

Structured web search with ranked titles, URLs, and snippets.

Normalized search returns one page. Native APIs cover search, fetch, browser sessions, agents, research, and monitors.

- [SDK reference](https://searchsdk.dev/docs/providers/tinyfish)
- [Provider reference](https://docs.tinyfish.ai/search-api/reference)

## Exa

Web search with query-relevant highlights and native relevance.

Normalized sources and reported USD usage. Native APIs include content, answers, research, Websets, monitors, and management.

- [SDK reference](https://searchsdk.dev/docs/providers/exa)
- [Provider reference](https://exa.ai/docs/reference/search)

## Tavily

Agent-oriented web search with relevance-ranked content snippets.

Normalized basic search and credits. Native APIs preserve extraction, crawl, map, research, and explicit streaming.

- [SDK reference](https://searchsdk.dev/docs/providers/tavily)
- [Provider reference](https://docs.tavily.com/documentation/api-reference/endpoint/search)

## Brave

Independent-index web search with descriptions and extra snippets.

Normalized web results. Native search verticals, LLM Context, answers, suggestions, and enrichment remain separate.

- [SDK reference](https://searchsdk.dev/docs/providers/brave)
- [Provider reference](https://api-dashboard.search.brave.com/app/documentation/web-search/get-started)

## Perplexity

Ranked web results with extracted snippets and search filters.

Normalized Search API sources. Native clients preserve Sonar, Agent, embeddings, skills, analytics, and streaming.

- [SDK reference](https://searchsdk.dev/docs/providers/perplexity)
- [Provider reference](https://docs.perplexity.ai/api-reference/search-post)

## Parallel

Web retrieval using search queries and an optional research objective.

Normalized search excerpts. Native APIs include Extract, Tasks, FindAll, monitors, memory, Chat, and Responses.

- [SDK reference](https://searchsdk.dev/docs/providers/parallel)
- [Provider reference](https://docs.parallel.ai/api-reference/search/search)

## Linkup

Search with source results, sourced answers, and structured output modes.

Normalized searchResults. Native answers, fetch, research, tasks, and access-gated extraction keep their own shapes.

- [SDK reference](https://searchsdk.dev/docs/providers/linkup)
- [Provider reference](https://docs.linkup.so/pages/documentation/endpoints/search/overview)

## Firecrawl

Web search with optional scraping of returned pages.

Normalized web results. Native scraping, crawling, extraction, agents, monitors, and account APIs remain explicit.

- [SDK reference](https://searchsdk.dev/docs/providers/firecrawl)
- [Provider reference](https://docs.firecrawl.dev/features/search)

## You.com

Web and news search with snippets and optional page extraction.

Normalized web sources. Native Contents, Answer, Research, finance, images, and account balance retain their own shapes.

- [SDK reference](https://searchsdk.dev/docs/providers/you)
- [Provider reference](https://you.com/docs/api-reference/search/v1-search)

## Serper

Google search results across web and specialized result categories.

Normalized organic web hits. Native Google verticals, batches, GET/POST variants, and scraping use provider options.

- [SDK reference](https://searchsdk.dev/docs/providers/serper)
- [Provider reference](https://serper.dev/)

## SerpAPI

Structured search results from Google and other supported engines.

Normalized Google organic hits, one page. Native engine gateway, archives, locations, uploads, and Extract families.

- [SDK reference](https://searchsdk.dev/docs/providers/serpapi)
- [Provider reference](https://serpapi.com/search-api)

## Valyu

Web search with source content and provider-native relevance.

Normalized web search only. Typed adapter options and raw response access preserve provider-specific details; no generated native client.

- [SDK reference](https://searchsdk.dev/docs/providers/valyu)
- [Provider reference](https://docs.valyu.ai/api-reference/endpoint/search)

## SearXNG

Metasearch through an operator-selected SearXNG instance.

Normalized JSON web results only. Your server chooses the instance; JSON search must be enabled by its operator. No generated native client.

- [SDK reference](https://searchsdk.dev/docs/providers/searxng)
- [Provider reference](https://docs.searxng.org/dev/search_api.html)

## WonderSearch

Semantic retrieval over your own documents and workspace collections.

Corpus-only native client: passages, content, access, uploads, ingestion, and billing. Never relabeled as open-web results.

- [SDK reference](https://searchsdk.dev/docs/providers/wondersearch)
- [Provider reference](https://docs.evokoa.com/wondersearch/reference/search-api)