---
title: "Serper Pricing & Google SERP APIs (2026): Web Search Comparison, Independently Benchmarked"
description: "SERP (RapidAPI) scores 96.0% search accuracy at a recorded $3.00 per 1,000 queries. Serper’s separate service starts at $1 per 1,000 searches with a $50 prepaid pack; volume packs reach $0.30 per 1,000. Compare the best web search APIs on pricing and benchmarks: Brave, Exa, Tavily and Parallel."
url: https://openbenchmarks.com/multi-turn-company-search/serp-rapidapi-for-research-agents
---

[Openbenchmarks](https://openbenchmarks.com/) [← web search benchmark](https://openbenchmarks.com/web-search) 

[web-search](https://openbenchmarks.com/web-search) / Serper pricing & SERP API comparison 

independent benchmark · updated 21 Oct 2026 · Serper pricing checked 21 Sept 2026

# Serper Pricing & Google SERP APIs (2026): Web Search Comparison & Benchmark

SERP (RapidAPI) scores 96.0% search accuracy at a recorded $3.00 per 1,000 queries. Serper’s separate service starts at $1 per 1,000 searches with a $50 prepaid pack; volume packs reach $0.30 per 1,000\. Compare the best web search APIs on pricing and benchmarks: Brave, Exa, Tavily and Parallel.

* **SERP (RapidAPI) search accuracy:** 96.0% · $3.00 per 1,000 queries at the recorded rate. [Measured search result →](#search-accuracy)
* **Serper starting price:** $1 per 1,000 searches; $50 buys 50,000 queries.
* **Lowest published volume rate:** $0.30 per 1,000; $3,750 buys 12.5 million queries.
* **Free allowance:** 2,500 queries without a credit card. Paid credits last six months. [Official Serper pricing ↗](https://serper.dev/)

[Compare pricing and benchmarks →](#comparison) 

## Google SERP API search accuracy: measured RapidAPI result

This search accuracy result measures SERP (RapidAPI), using one query and up to 10 results. Serper’s official prices are compared below, alongside an explicitly labelled SERP (RapidAPI) proxy reference. The multi-search F1 comparison follows separately. Last measured 21 Oct 2026.

__Measured search accuracy, time and recorded query price__
| Provider / endpoint | Search accuracy | Average search time | Per 1,000 queries | Official docs |
| --- | --- | --- | --- | --- |
| SERP (RapidAPI) google-search74.p.rapidapi.com | 96.0% | 751ms | $3.00 | [Official docs ↗](https://rapidapi.com/herosAPI/api/google-search74) |

[View full search accuracy benchmark and methodology →](https://openbenchmarks.com/company-news) 

## Serper vs Brave, Exa, Tavily and Parallel: pricing comparison

Serper rows pair official pack rates with SERP (RapidAPI) as a Google SERP API proxy reference. The proxy values are measured RapidAPI results, not measurements or validated estimates of Serper performance. Other rows show each provider’s own measured results. F1 measures answer-set quality; median task time covers the full agent workflow, including searches and model generation.

__Price per 1,000 queries and benchmark results — Serper rows use a labelled RapidAPI proxy__
| Provider / configuration | Per 1,000 queries | Rate basis | Quality (F1) | Median agent task time | Official docs / pricing |
| --- | --- | --- | --- | --- | --- |
| Serper · Starter Performance reference: SERP (RapidAPI) | $1.00 | $50.00 prepaid; six-month credits | 0.4% RapidAPI proxy | 31.38s RapidAPI proxy | [Serper pricing ↗](https://serper.dev/) [Proxy endpoint ↗](https://rapidapi.com/herosAPI/api/google-search74) |
| Serper · Standard Performance reference: SERP (RapidAPI) | $0.75 | $375.00 prepaid; six-month credits | 0.4% RapidAPI proxy | 31.38s RapidAPI proxy | [Serper pricing ↗](https://serper.dev/) [Proxy endpoint ↗](https://rapidapi.com/herosAPI/api/google-search74) |
| Serper · Scale Performance reference: SERP (RapidAPI) | $0.50 | $1,250.00 prepaid; six-month credits | 0.4% RapidAPI proxy | 31.38s RapidAPI proxy | [Serper pricing ↗](https://serper.dev/) [Proxy endpoint ↗](https://rapidapi.com/herosAPI/api/google-search74) |
| Serper · Ultimate Performance reference: SERP (RapidAPI) | $0.30 | $3,750.00 prepaid; six-month credits | 0.4% RapidAPI proxy | 31.38s RapidAPI proxy | [Serper pricing ↗](https://serper.dev/) [Proxy endpoint ↗](https://rapidapi.com/herosAPI/api/google-search74) |
| Parallel basic POST /v1/search mode=basic | $5.00 | Recorded rate for this configuration | 46.5% | 67.63s | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) |
| Exa deep POST /search type=deep | $12.00 | Recorded rate for this configuration | 45.4% | 89.50s | [Official docs ↗](https://docs.exa.ai/reference/search) |
| Tavily basic POST /search search\_depth=basic | $8.00 | Recorded rate for this configuration | 36.5% | 63.04s | [Official docs ↗](https://docs.tavily.com/documentation/api-reference/endpoint/search) |
| Brave Search GET /res/v1/web/search | $5.00 | Recorded rate for this configuration | 28.0% | 43.52s | [Official docs ↗](https://api-dashboard.search.brave.com/documentation/services/web-search) |
| SERP GET google-search74.p.rapidapi.com | $3.00 | Recorded rate for this configuration | 0.4% | 31.38s | [Official docs ↗](https://rapidapi.com/herosAPI/api/google-search74) |

Serper.dev, SerpAPI and SERP (RapidAPI) are separate services. The measured Google SERP row is [google-search74 on RapidAPI](https://rapidapi.com/herosAPI/api/google-search74). Serper rows use that measured endpoint as a proxy reference alongside Serper’s own pricing. The repeated proxy values come from one RapidAPI configuration; they do not measure differences between Serper plans. Compare SerpAPI’s current plans on its [official pricing page](https://serpapi.com/pricing).

## Best web search APIs for AI agents: measured comparison

Parallel basic leads at 46.5% F1\. The same agent and 45 questions are used for every configuration. This main ranking measures multiple searches. Last measured 2 Oct 2026.

__Measured search APIs: ranked by F1; Serper is not included in this benchmark__
| Provider | Endpoint & configuration | Official docs | F1 | Precision | Recall | Exact set | Median time | Mean turns | Median task cost | API list price |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Parallel basic](https://parallel.ai "Open Parallel basic in a new tab") | POST /v1/search mode=basic parallel-basic | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **46.5 ± 1.9** | 88.7 ± 0.9 | 34.4 ± 2.0 | 3.7 ± 2.6 | 67.6 s | 7.4 | $1.120 $0.070 search $1.050 token cost | $0.005 / search |
| [Exa deep](https://exa.ai "Open Exa deep in a new tab") | POST /search type=deep exa-deep | [Official docs ↗](https://docs.exa.ai/reference/search) | **45.4 ± 2.0** | 83.2 ± 3.0 | 33.7 ± 1.4 | 1.5 ± 1.3 | 89.5 s | 7.4 | $0.717 $0.156 search $0.556 token cost | $0.012 / search |
| [Parallel advanced](https://parallel.ai "Open Parallel advanced in a new tab") | POST /v1/search mode=advanced parallel-advanced | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **44.2 ± 1.4** | 87.6 ± 3.4 | 32.0 ± 1.6 | 2.2 ± 0.0 | 83.4 s | 7.3 | $0.625 $0.070 search $0.565 token cost | $0.005 / search |
| [Exa instant](https://exa.ai "Open Exa instant in a new tab") | POST /search type=instant exa-instant | [Official docs ↗](https://docs.exa.ai/reference/search) | **43.3 ± 1.0** | 82.6 ± 3.8 | 32.2 ± 0.5 | 3.0 ± 1.3 | 49.8 s | 7.3 | $0.652 $0.091 search $0.559 token cost | $0.007 / search |
| [Linkup fast](https://www.linkup.so "Open Linkup fast in a new tab") | POST /v1/search depth=fast linkup-fast | [Official docs ↗](https://docs.linkup.so/pages/documentation/endpoints/search/overview) | **41.1 ± 1.7** | 82.8 ± 1.0 | 30.3 ± 1.5 | 0.7 ± 1.3 | 64.2 s | 7.4 | $0.923 $0.070 search $0.853 token cost | $0.005 / search |
| [Tavily advanced](https://tavily.com "Open Tavily advanced in a new tab") | POST /search search\_depth=advanced tavily-advanced | [Official docs ↗](https://docs.tavily.com/documentation/api-reference/endpoint/search) | **41.1 ± 2.3** | 83.7 ± 4.2 | 29.8 ± 1.7 | 2.2 ± 0.0 | 92.2 s | 7.4 | $1.029 $0.224 search $0.808 token cost | $0.016 / search |
| [Linkup standard](https://www.linkup.so "Open Linkup standard in a new tab") | POST /v1/search depth=standard linkup-standard | [Official docs ↗](https://docs.linkup.so/pages/documentation/endpoints/search/overview) | **40.6 ± 0.9** | 84.0 ± 7.9 | 29.7 ± 1.4 | 1.5 ± 2.6 | 72.3 s | 7.3 | $0.937 $0.070 search $0.867 token cost | $0.005 / search |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights | [Official docs ↗](https://docs.you.com/) | **38.6 ± 0.8** | 79.3 ± 4.9 | 28.3 ± 0.9 | 4.4 ± 0.0 | 48.2 s | 7.5 | $0.971 $0.070 search $0.901 token cost | $0.005 / search |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights · knowledge=core | [Official docs ↗](https://docs.you.com/) | **38.1 ± 0.6** | 80.9 ± 1.6 | 27.4 ± 0.9 | 3.0 ± 1.3 | 47.6 s | 7.5 | $0.895 $0.070 search $0.827 token cost | $0.005 / search |
| [Parallel fast](https://parallel.ai "Open Parallel fast in a new tab") | POST /v1/search mode=fast parallel-fast | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **38.0 ± 2.0** | 79.9 ± 4.6 | 27.5 ± 1.4 | 1.5 ± 1.3 | 53.9 s | 7.6 | $0.460 $0.014 search $0.447 token cost | $0.001 / search |
| [Perplexity](https://www.perplexity.ai "Open Perplexity in a new tab") | POST /search search\_context\_size=low | [Official docs ↗](https://docs.perplexity.ai/api-reference/search-post) | **37.8 ± 2.1** | 79.3 ± 5.7 | 26.8 ± 1.4 | 2.2 ± 2.2 | 48.9 s | 7.7 | $0.334 $0.070 search $0.264 token cost | $0.005 / search |
| [Tavily basic](https://tavily.com "Open Tavily basic in a new tab") | POST /search search\_depth=basic tavily-basic | [Official docs ↗](https://docs.tavily.com/documentation/api-reference/endpoint/search) | **36.5 ± 3.2** | 82.5 ± 1.9 | 25.7 ± 2.7 | 1.5 ± 1.3 | 63.0 s | 7.7 | $0.615 $0.112 search $0.504 token cost | $0.008 / search |
| [Parallel turbo](https://parallel.ai "Open Parallel turbo in a new tab") | POST /v1/search mode=turbo parallel-turbo | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **34.7 ± 2.4** | 80.0 ± 5.2 | 24.8 ± 2.4 | 1.5 ± 1.3 | 46.4 s | 7.6 | $0.419 $0.014 search $0.405 token cost | $0.001 / search |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=standard · full\_content=false · focus=general | [Official docs ↗](https://docs.nimbleway.com/api-reference/search/search) | **30.7 ± 1.4** | 70.3 ± 3.3 | 21.3 ± 1.1 | 0.7 ± 1.3 | 53.0 s | 7.7 | $0.467 $0.070 search $0.398 token cost | $0.005 / search |
| [Firecrawl](https://firecrawl.dev "Open Firecrawl in a new tab") | POST /v2/search firecrawl | [Official docs ↗](https://docs.firecrawl.dev/api-reference/endpoint/search) | **30.4 ± 1.1** | 77.3 ± 4.4 | 20.7 ± 0.7 | 2.2 ± 0.0 | 75.0 s | 7.9 | $0.282 $0.070 search $0.212 token cost | $0.005 / search |
| [Brave Search](https://brave.com/search/api/ "Open Brave Search in a new tab") | GET /res/v1/web/search brave | [Official docs ↗](https://api-dashboard.search.brave.com/documentation/services/web-search) | **28.0 ± 1.7** | 66.9 ± 8.5 | 19.3 ± 0.5 | 0.7 ± 1.3 | 43.5 s | 8.0 | $0.268 $0.070 search $0.200 token cost | $0.005 / search |
| [TinyFish](https://www.tinyfish.ai "Open TinyFish in a new tab") | GET api.search.tinyfish.ai tinyfish | [Official docs ↗](https://docs.tinyfish.ai/search-api) | **26.6 ± 1.3** | 64.7 ± 1.5 | 17.9 ± 0.8 | 1.5 ± 1.3 | 64.2 s | 7.9 | $0.212 $0.000 search $0.212 token cost | $0 / search |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=lite · full\_content=false · focus=general | [Official docs ↗](https://docs.nimbleway.com/api-reference/search/search) | **25.3 ± 1.1** | 62.8 ± 1.9 | 17.6 ± 1.2 | 1.5 ± 1.3 | 67.9 s | 7.9 | $0.234 $0.015 search $0.220 token cost | $0.0011 / search |
| [Seltz](https://seltz.ai "Open Seltz in a new tab") | POST /v1/search scope=companies seltz-companies | [Official docs ↗](https://docs.seltz.ai/) | **14.5 ± 0.9** | 40.0 ± 3.1 | 9.4 ± 0.7 | 0.0 ± 0.0 | 55.2 s | 7.3 | $1.751 $0.070 search $1.681 token cost | $0.005 / search |
| [SERP](https://rapidapi.com/herosAPI/api/google-search74 "Open SERP in a new tab") | GET google-search74.p.rapidapi.com serp | [Official docs ↗](https://rapidapi.com/herosAPI/api/google-search74) | **0.4 ± 0.6** | 0.7 ± 1.3 | 0.3 ± 0.4 | 0.0 ± 0.0 | 31.4 s | 7.8 | $0.103 $0.036 search $0.065 token cost | $0.003 / search |

F1, precision, recall, and exact-set accuracy are percentages reported as mean ± sample SD across three independent runs; each run aggregates all 45 questions. SD is measured in percentage points. Median time is the median end-to-end time across all runs for each vendor. Median task cost is the median of LLM $ plus search API $ per agent run. API list price is the PAYG unit rate of the search endpoint the harness calls.

[View full multi-search benchmark →](https://openbenchmarks.com/multi-turn-company-search) 

Additional benchmark: search and scrape

The same questions with a page-scraping tool enabled. Compare within this mode separately.

__Search and scrape: measured configurations ranked by F1__
| Provider | Endpoint & configuration | Official docs | F1 | Precision | Recall | Exact set | Median time | Mean turns | Median task cost | API list price |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Exa deep](https://exa.ai "Open Exa deep in a new tab") | POST /search type=deep exa-deep | [Official docs ↗](https://docs.exa.ai/reference/search) | **48.2 ± 2.1** | 89.4 ± 1.2 | 36.0 ± 2.2 | 2.2 ± 2.2 | 95.8 s | 7.5 | $0.683 $0.156 search+scrape $0.526 token cost | $0.012 / search $0.001 / scrape |
| [Perplexity](https://www.perplexity.ai "Open Perplexity in a new tab") | POST /search search\_context\_size=high | [Official docs ↗](https://docs.perplexity.ai/api-reference/search-post) | **46.6 ± 2.0** | 87.7 ± 5.9 | 34.7 ± 1.1 | 2.2 ± 2.2 | 53.9 s | 7.5 | $0.504 $0.070 search+scrape $0.441 token cost | $0.005 / search |
| [Exa instant](https://exa.ai "Open Exa instant in a new tab") | POST /search type=instant exa-instant | [Official docs ↗](https://docs.exa.ai/reference/search) | **44.9 ± 0.9** | 85.9 ± 2.5 | 33.5 ± 0.9 | 5.2 ± 1.3 | 52.5 s | 7.5 | $0.653 $0.091 search+scrape $0.557 token cost | $0.007 / search $0.001 / scrape |
| [Parallel basic](https://parallel.ai "Open Parallel basic in a new tab") | POST /v1/search mode=basic parallel-basic | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **42.3 ± 1.1** | 81.3 ± 2.8 | 31.3 ± 1.1 | 3.0 ± 1.3 | 68.6 s | 7.5 | $1.089 $0.061 search+scrape $1.033 token cost | $0.005 / search $0.001 / scrape |
| [Parallel advanced](https://parallel.ai "Open Parallel advanced in a new tab") | POST /v1/search mode=advanced parallel-advanced | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **42.2 ± 1.1** | 87.6 ± 0.3 | 30.1 ± 1.1 | 2.2 ± 0.0 | 80.9 s | 7.4 | $0.599 $0.061 search+scrape $0.538 token cost | $0.005 / search $0.001 / scrape |
| [Linkup standard](https://www.linkup.so "Open Linkup standard in a new tab") | POST /v1/search depth=standard linkup-standard | [Official docs ↗](https://docs.linkup.so/pages/documentation/endpoints/search/overview) | **42.0 ± 1.8** | 90.7 ± 2.0 | 30.5 ± 2.0 | 3.0 ± 3.4 | 81.0 s | 7.5 | $0.911 $0.070 search+scrape $0.848 token cost | $0.005 / search $0.001 / scrape |
| [Tavily advanced](https://tavily.com "Open Tavily advanced in a new tab") | POST /search search\_depth=advanced tavily-advanced | [Official docs ↗](https://docs.tavily.com/documentation/api-reference/endpoint/search) | **41.0 ± 1.3** | 89.4 ± 6.0 | 29.1 ± 0.7 | 2.2 ± 0.0 | 92.6 s | 7.3 | $0.898 $0.195 search+scrape $0.685 token cost | $0.016 / search $0.0032 / scrape |
| [Linkup fast](https://www.linkup.so "Open Linkup fast in a new tab") | POST /v1/search depth=fast linkup-fast | [Official docs ↗](https://docs.linkup.so/pages/documentation/endpoints/search/overview) | **39.9 ± 1.3** | 85.3 ± 3.6 | 28.6 ± 1.3 | 0.7 ± 1.3 | 68.0 s | 7.3 | $0.903 $0.061 search+scrape $0.837 token cost | $0.005 / search $0.001 / scrape |
| [Parallel fast](https://parallel.ai "Open Parallel fast in a new tab") | POST /v1/search mode=fast parallel-fast | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **39.3 ± 3.3** | 82.3 ± 6.6 | 28.2 ± 2.0 | 2.2 ± 0.0 | 55.1 s | 7.6 | $0.441 $0.014 search+scrape $0.427 token cost | $0.001 / search $0.001 / scrape |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights | [Official docs ↗](https://docs.you.com/) | **38.5 ± 1.6** | 85.2 ± 2.7 | 26.9 ± 1.7 | 0.7 ± 1.3 | 45.6 s | 7.4 | $0.864 $0.065 search+scrape $0.795 token cost | $0.005 / search $0.001 / scrape |
| [You](https://you.com "Open You in a new tab") | POST /v1/search extraction\_mode=highlights · knowledge=core | [Official docs ↗](https://docs.you.com/) | **38.5 ± 2.4** | 78.2 ± 2.5 | 28.3 ± 3.0 | 3.7 ± 1.3 | 48.5 s | 7.4 | $0.894 $0.065 search+scrape $0.830 token cost | $0.005 / search $0.001 / scrape |
| [Tavily basic](https://tavily.com "Open Tavily basic in a new tab") | POST /search search\_depth=basic tavily-basic | [Official docs ↗](https://docs.tavily.com/documentation/api-reference/endpoint/search) | **38.1 ± 1.4** | 81.2 ± 5.9 | 27.8 ± 0.7 | 2.2 ± 0.0 | 62.0 s | 7.8 | $0.610 $0.112 search+scrape $0.507 token cost | $0.008 / search $0.0032 / scrape |
| [Parallel turbo](https://parallel.ai "Open Parallel turbo in a new tab") | POST /v1/search mode=turbo parallel-turbo | [Official docs ↗](https://docs.parallel.ai/api-reference/search/search) | **36.0 ± 3.5** | 83.6 ± 4.0 | 25.0 ± 2.6 | 0.0 ± 0.0 | 48.1 s | 7.7 | $0.414 $0.013 search+scrape $0.400 token cost | $0.001 / search $0.001 / scrape |
| [Firecrawl](https://firecrawl.dev "Open Firecrawl in a new tab") | POST /v2/search firecrawl | [Official docs ↗](https://docs.firecrawl.dev/api-reference/endpoint/search) | **33.2 ± 2.1** | 83.3 ± 0.8 | 22.7 ± 1.8 | 1.5 ± 1.3 | 82.1 s | 7.9 | $0.295 $0.063 search+scrape $0.230 token cost | $0.005 / search $0.0025 / scrape |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=standard · full\_content=false · focus=general · extract formats=\[markdown\] | [Official docs ↗](https://docs.nimbleway.com/api-reference/search/search) | **31.3 ± 1.8** | 73.2 ± 1.9 | 21.7 ± 1.6 | 1.5 ± 1.3 | 59.2 s | 7.9 | $0.424 $0.424 token cost | $0.005 / search |
| [TinyFish](https://www.tinyfish.ai "Open TinyFish in a new tab") | GET api.search.tinyfish.ai tinyfish | [Official docs ↗](https://docs.tinyfish.ai/search-api) | **30.2 ± 3.5** | 70.9 ± 11.3 | 20.9 ± 2.5 | 0.0 ± 0.0 | 63.4 s | 7.9 | $0.219 $0.000 search+scrape $0.219 token cost | $0 / search $0 / scrape |
| [Brave Search](https://brave.com/search/api/ "Open Brave Search in a new tab") | GET /res/v1/web/search brave | [Official docs ↗](https://api-dashboard.search.brave.com/documentation/services/web-search) | **29.4 ± 1.6** | 73.5 ± 5.8 | 20.4 ± 0.9 | 1.5 ± 1.3 | 45.1 s | 8.0 | $0.285 $0.060 search+scrape $0.222 token cost | $0.005 / search |
| [Nimble](https://www.nimbleway.com "Open Nimble in a new tab") | POST /v2/search search\_depth=lite · full\_content=false · focus=general · extract formats=\[markdown\] | [Official docs ↗](https://docs.nimbleway.com/api-reference/search/search) | **27.1 ± 1.5** | 68.5 ± 4.4 | 18.7 ± 0.9 | 2.2 ± 0.0 | 72.0 s | 8.0 | $0.237 $0.237 token cost | $0.0011 / search |
| [Seltz](https://seltz.ai "Open Seltz in a new tab") | POST /v1/search scope=companies seltz-companies | [Official docs ↗](https://docs.seltz.ai/) | **16.3 ± 1.5** | 49.5 ± 2.4 | 10.2 ± 1.2 | 0.0 ± 0.0 | 60.1 s | 7.5 | $1.741 $0.070 search+scrape $1.671 token cost | $0.005 / search |
| [SERP](https://rapidapi.com/herosAPI/api/google-search74 "Open SERP in a new tab") | GET google-search74.p.rapidapi.com serp | [Official docs ↗](https://rapidapi.com/herosAPI/api/google-search74) | **0.0 ± 0.0** | 0.0 ± 0.0 | 0.0 ± 0.0 | 0.0 ± 0.0 | 33.4 s | 7.8 | $0.102 $0.039 search+scrape $0.066 token cost | $0.003 / search |

F1, precision, recall, and exact-set accuracy are percentages reported as mean ± sample SD across three independent runs; each run aggregates all 45 questions. SD is measured in percentage points. Median time is the median end-to-end time across all runs for each vendor. Median task cost is the median of LLM $ plus search/scrape API $ per agent run. API list price is the PAYG unit rate of the search (and scrape) endpoint the harness calls.

## How pricing and benchmark results are compared

Serper prices come from its official plans. Benchmark scores come from the named search endpoints using the same agent, prompt and turn budget on company-discovery questions with several constraints. Precision, recall and F1 compare the returned set with a human-reviewed answer set across three runs. Median task cost includes model and search spend; list price per 1,000 queries covers the API calls.

[Open benchmark code ↗](https://github.com/openbenchmarks-labs/multi-turn-company-search) · [Public dataset sample ↗](https://huggingface.co/datasets/openbenchmarks/OB-Company-Websearch) 

## Serper pricing and Google SERP APIs: FAQ

### What is the measured search accuracy of SERP (RapidAPI)?

SERP (RapidAPI), measured at google-search74.p.rapidapi.com, scores 96.0% search accuracy. This result uses one query and up to 10 results on the company-news benchmark. The multi-search table below reports F1 for a different workflow. Serper and SerpAPI are separate services and have no measured accuracy in this comparison.

### How much does Serper cost per 1,000 searches in 2026?

Serper’s Starter pack costs $50 for 50,000 queries, or $1 per 1,000\. Standard is $0.75 per 1,000 with a $375 purchase; Scale is $0.50 with $1,250; Ultimate is $0.30 with $3,750\. Prices exclude sales tax, VAT and GST. Credits are valid for six months. Official prices checked 21 September 2026.

### Does Serper have a free tier or monthly subscription?

Serper offers 2,500 free queries without a credit card. Paid usage uses prepaid credit packs rather than a monthly subscription. The lowest paid pack is $50; its $1 per 1,000 rate describes the query allowance, not a $1 minimum purchase.

### Serper vs Brave, Exa and Tavily: which search API is cheapest?

Compare the Serper pack rates with the recorded per-query rates for the tested alternatives in the pricing table. Serper’s paid rate ranges from $1 to $0.30 per 1,000 queries depending on the pack. Minimum purchase, credit expiration, result limits, scrape calls and LLM tokens all affect the bill. Use the linked official terms for your chosen endpoint.

### Are Serper, SerpAPI and SERP via RapidAPI the same API?

They are separate services. Serper.dev and SerpAPI provide Google search APIs; the SERP (RapidAPI) benchmark row here measures google-search74.p.rapidapi.com. This page compares Serper’s official prices with other providers and labels the RapidAPI F1 and task time shown alongside them as a proxy reference. Those values measure RapidAPI, not Serper. Every measured score stays attached to its named provider and endpoint.

### Which is the best web search API for AI agents in this comparison?

Parallel basic leads the measured multi-search ranking at 46.5% F1\. F1 combines precision and recall for an agent collecting answers across several searches. Compare quality with search price and total agent cost, then use the linked general search and developer benchmarks for those workflows.

### What did the Google SERP API via RapidAPI score?

The tested SERP (RapidAPI) configuration scored 0.4% F1 with 31.38s median agent task time. The endpoint was GET google-search74.p.rapidapi.com. Its scores describe that service and configuration. Serper pricing rows repeat these values as an explicitly labelled proxy reference, not measured Serper performance.

### How much do 100,000 Serper searches cost?

At the Starter rate, 100,000 queries use $100 of credits. A $50 Starter pack includes 50,000 queries, so two packs supply that allowance. At the Standard rate the same usage consumes $75 of credits, but purchasing that pack requires $375 upfront for 500,000 queries. Choose the pack for your expected six-month usage.

## More web search API comparisons

[Cheapest search APIs per 1,000 queries](https://openbenchmarks.com/web-search/cheapest-search-api) · [Best web search APIs for AI](https://openbenchmarks.com/web-search/best-web-search-api-for-ai) · [Best web search APIs for developers](https://openbenchmarks.com/web-search/best-web-search-api-for-developers) · [Best web search APIs for LLM apps](https://openbenchmarks.com/web-search/best-web-search-api-for-llm-apps) · [Brave Search API comparison](https://openbenchmarks.com/multi-turn-company-search/brave-search-for-research-agents)