跳到正文
DEV Community· Ricardo Batista·· 7 天前AI 評分67

哪些網頁搜尋 API 提供免費額度,可用於構建 AI 智能體?

Which web search API has a free tier for building an AI agent?

AI 導讀

這份網頁搜尋 API 比較指出,Linkup 每月提供 $20 額度,約可進行 4,000 次標準搜尋,但帳戶須使用工作電郵。Parallel 快速模式每月最多可搜尋 5,000 次,但需提供信用卡;Exa 每月 $10 額度約可搜尋 1,428 次,是毋須信用卡並接受任何電郵的月度方案中額度最高者。

正文

Linkup has the largest monthly free tier of the web search APIs in this comparison: $20 of credit a month, about 4,000 standard searches, for an account with a work email. Parallel gives up to 5,000 searches a month, but only in its fast mode and with a card on file. Of the monthly tiers that need no card and accept any email, Exa's $10 a month, about 1,400 searches, is the largest. To start with no account at all, Exa, Tavily, Firecrawl and Parallel run keyless MCP servers, with limits they do not publish.

  • Monthly or one-time: eight of the ten free tiers refill each month. Serper gives 2,500 queries at sign-up, and its page does not say they refill. The Perplexity Search API states no free tier.
  • The rate limit can stop an agent before the allowance does: SerpApi's free plan allows 50 searches an hour, Firecrawl's allows 10 searches a minute, and one free tier allows 1 request at a time.
  • A search that misses costs a second search: on 824 multi-hop questions, one search answered 48.4% to 80.2% of them, depending on the API.

Which web search APIs have a free tier?

Each row comes from the vendor's own pricing page or docs, read on November 14, 2026. "Searches" is the count in the default search mode with 10 results, unless the row says otherwise.

API Free allowance Refill Searches it buys Card needed Rate limit stated
Linkup $20 of credit, for an account with a work email Topped up to $20 each month About 4,000 at $0.005 a standard search Not stated Not stated
Parallel $5 of credit, plus up to $80 at sign-up $5 monthly; the $80 one time 1,000 in the default advanced mode, 5,000 in fast Yes, a card on file for the $5 600 a minute
Exa $10 of credit, plus a one-time $10 for onboarding Resets to $10 on the 1st About 1,428 auto, 2,500 lite No 10 a second
Brave $5 of credit on the Search plan Monthly 1,000 Yes, "to prevent abuse" 50 a second
Tavily 1,000 credits Monthly 1,000 basic, 500 advanced No 100 a minute
Firecrawl 1,000 credits Monthly 500 (2 credits per 10 results) No 10 searches a minute, 2 at a time
Serper 2,500 queries At sign-up; not stated as monthly 2,500 No Not stated
SerpApi 250 searches Monthly 250 Not stated 50 an hour
cloro 500 credits Monthly 166 Google searches, or 100 with the AI Overview No 1 request at a time
Perplexity Search API None stated 0 50 a second

Three rows need a closer read. Brave's banner says "Up to $20 in free calls every month", but its Search plan carries $5 a month, which buys 1,000 searches. Parallel's FAQ says "every account gets a recurring free monthly allowance of $5", and its plan card says the $5 needs a card on file. Linkup's top-up applies to "eligible accounts"; its docs name the work email and no other condition.

The cloro row in numbers: a Google search is 3 credits and the AI Overview makes it 5, so 500 credits buy 166 or 100 searches on the async API. A synchronous request adds 2 credits, which makes it 100 or 71.

Which web search APIs work with no key at all?

Four vendors run a hosted MCP server that answers without an API key:

  • Exa: https://mcp.exa.ai/mcp. Search and fetch "at a free rate limit". It needs a direct IPv4 connection; from IPv6 or a proxy, you need a key or OAuth.
  • Tavily: send the header X-Tavily-Access-Mode: keyless to https://api.tavily.com/search, /extract, or the MCP server at https://mcp.tavily.com/mcp/. Crawl, map and research need a key.
  • Firecrawl: the hosted MCP server does search, scrape and parse "within daily limits", with no account.
  • Parallel: a free hosted Search MCP server for "personal/hobbyist use", with "variable limits".

None of the four publishes a number for its keyless limit. Keyless access is enough to wire up a prototype in Claude Code or Cursor; move to a key before the agent searches in a loop. Open-source servers such as duckduckgo-mcp-server scrape a search engine from your own machine with no key, and break when the engine changes its page.

What does each free search return?

Each free tier returns the same response as the vendor's paid plans. The source and the shape differ by vendor.

API Source One search returns
Linkup Linkup's index Results, or a sourced answer for $0.006
Parallel Parallel's index Results with excerpts from each page
Exa Exa's neural index Results with page text or highlights
Brave Brave's own index Results with snippets, as JSON
Tavily Tavily's index Results with extracted page content
Firecrawl Its own search endpoint Results; page content costs more credits per result
Serper Google The Google results page as JSON
SerpApi Google and other engines The Google results page as JSON
cloro Google The results page as JSON, with the AI Overview and People Also Ask
Perplexity Search API Perplexity's index Ranked results with snippets

Page text (Exa, Tavily, Linkup, Parallel) is what a model answers from, and it costs tokens on every call. Structured results (Brave, Serper, SerpApi) let the agent read a field, such as a rank or a URL.

How far does each free tier go for an agent that searches in a loop?

An agent seldom stops at one search. Assume a research agent that runs 5 searches per task. The table divides each monthly allowance by 5, then by 30 days.

API Searches a month Tasks a month Tasks a day
Parallel, fast mode 5,000 1,000 33
Linkup 4,000 800 26
Exa, auto 1,428 285 9
Brave 1,000 200 6
Tavily, basic 1,000 200 6
Parallel, advanced 1,000 200 6
Firecrawl 500 100 3
SerpApi 250 50 1
cloro, async 166 33 1

Serper's 2,500 queries are a one-time grant: 500 tasks in total. Two limits change these numbers in practice.

Concurrency. An agent that fires 5 searches at once waits on a tier that runs 1 request at a time, and SerpApi's 50 searches an hour cap it at 10 tasks an hour. Exa, Brave, Tavily and Parallel leave room for parallel searches.

Misses. Six web search APIs ran on the 824 multi-hop questions of the FRAMES set in November 2026, with one search of 10 results per question. The two Google SERP APIs answered 80.2% and 77.4% of them. Parallel answered 65.3%, Exa 64.0%, Brave 53.9% and Tavily 48.4%. Those four replied "not found" on 151 to 295 questions, and an agent would search again on each of them. On short factual questions the order changes: Parallel (97.8%), Exa (97.3%) and the top Google API (96.9%) are within the margin of error. The questions, settings and graded answers are in the benchmark repo.

Which free tier should you start on?

Your agent needs Free tier to start on
The most searches a month Linkup, or Parallel in fast mode with a card
No card and any email Exa, then Tavily or Firecrawl
No sign-up, for a prototype A keyless MCP server: Exa, Tavily, Firecrawl or Parallel
An index that is not Google Brave, Exa or Parallel
Google's own results page Serper for volume; SerpApi or a Google SERP API with the AI Overview for the full page

A free tier tests the response shape and the tool wiring. Past a few thousand searches a month, the paid rate and the share of searches that hold the answer decide the cost.

How this was checked

This comparison is published by cloro, which is one of the APIs in it. Every other allowance, refill rule, card rule and rate limit comes from that vendor's own pricing page or docs, read on November 14, 2026, and each one is linked in the first table. The cloro row comes from its published plans and billing docs. Serper's page does not say whether its 2,500 queries refill; third-party reviews describe them as one-time. The accuracy figures are copied from the benchmark linked above. The full comparison, with paid prices and latency for each API, is in Best Web Search API for AI Agents.

來源:DEV Community · dev.to