Head to head · Web search · October 2026 research run

Perplexity Search API vs Serper

Perplexity Search API scores 70.2 (BB) on agent readiness against Serper's 24.2 (F), and leads in 6 of 7 scored categories. Serper leads on payments & pricing. Both do web search.

Best web search APIs for AI agents · All 308 search comparisons

Which one, for what

Perplexity Search API BB

Best for Agents on any model that need raw ranked sources with extracted text at a low per-request price, and teams that want cited answers from the same key through the Agent API.

Ahead on

  • Reliability, 80 against 30
  • Schema & documentation, 89 against 6
  • Agent ergonomics, 85 against 35
  • Security & auth, 56 against 20
  • Maintenance & community, 82 against 3
  • Transparency & trust, 66 against 32

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine

Watch for

The FAQ says uptime and recovery time are not guaranteed, and the terms carry no SLA

Serper F

Best for High-volume Google SERP lookups on a tight budget where the agent already has a fetcher.

Ahead on

  • Payments & pricing, 40 against 25

Also in its favour

  • Free to start without a card

Watch for

No status page, SLA or incident history

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Schema & documentation Perplexity Search API +83

Perplexity Search API 89

OpenAPI 3.1.0 at docs.perplexity.ai/openapi.json describes POST /search with typed request and response schemas, listed in llms.txt (25). llms.txt indexes every page, each with a Markdown twin (10). The overview says what a result holds, that snippets can be empty, when to use the Search API instead of the Agent API, and that it takes queries not URLs and does not re-fetch pages (19 of 20). search_type is an enum, max_results, max_tokens and max_tokens_per_page carry minimum and maximum, country and language codes carry lengths, and query is a string or an array. The recency filter is an enum in the docs, and date filters are MM/DD/YYYY strings (14 of 15). Python, TypeScript and cURL examples with a recorded response. The spec documents only 200 and 422 for /search, and status codes are listed on the SDK error-handling page and the rate-limit page rather than for Search (11 of 15). A public changelog with several entries a month, dated by month only, and an unversioned /search path (10 of 15). 25 + 10 + 19 + 14 + 11 + 10 = 89.

Serper 6

No OpenAPI or other spec (0). serper.dev/llms.txt returns 404 and there are no Markdown docs (0). The documentation is the playground, a JavaScript page that showed us no text. Per the 30 September check it lists the verticals and parameters such as gl and hl, so a few points for descriptions (3) and typed inputs (3). No examples or error responses we could read (0). No changelog or API versioning (0).

Maintenance & community Perplexity Search API +79

Perplexity Search API 82

Read as a closed service with official SDKs and an open-source MCP server. perplexityai 0.46.1 on PyPI on 23 October 2026 and the MCP server's last commit on 21 October, with changelog entries into November 2026 (30). In the 90 days from 8 August, perplexityai 0.43.7 to 0.46.1 (six releases from 2 October), MCP server 1.2.1 (27 August) and 1.3.0 (25 September, Fast Search on perplexity_search), and Fast Search itself in September (20). A changelog with several entries a month, a community forum with a bug-report category, a GitHub discussion repository and api@perplexity.ai. MCP issue reply times weren't read (10 of 15). The MCP server is in the official registry under the domain-verified ai.perplexity namespace, and the Python and TypeScript SDKs are current (15). The MCP repository runs tests in CI and validates its plugin manifests. Its 1.4.0, prepared on 16 October, is not on npm, which still serves 1.3.0, and the registry's latest entry is 1.2.1 of 27 August (7 of 10). 30 + 20 + 10 + 15 + 7 = 82.

Serper 3

No changelog, release notes, SDK or package found, so no dated release or API change to count (0, 0). No public changelog. Support is by email per the privacy policy (3). No official SDKs (0). No packages or CI to assess (0).

Reliability Perplexity Search API +50

Perplexity Search API 80

Graded on the hosted lines, for POST /search and the hosted MCP server. status.perplexity.com, on incident.io since 10 September 2026, has an API component with an RSS feed and a JSON summary. There is no separate Search component (20). In the 90 days from 8 August the feed lists 'Investigating API issue' on 13 August, resolved with no detail, a usage-based billing issue on 3 September, and on 9 October elevated errors on the website, app and Computer, where the API 'remained operational throughout'. Minor only, with the caveat that history before the migration may be incomplete (20). The Search API is limited to 50 query units a second with a burst of 50 on every tier, and the other APIs publish QPS and token limits per tier (15). 429 carries Retry-After and an error.type, the SDKs retry 429 and 5xx twice honouring Retry-After, the Search best-practices page shows backoff, and failed or rate-limited searches are not billed. Searches have no side effects (15). The FAQ says Perplexity does not guarantee uptime, failure frequency or recovery time, and the terms carry no SLA (0). No beta label on the Search API, launched on 25 September 2025 (10). 20 + 20 + 15 + 15 + 0 + 10 = 80.

Serper 30

No status page. status.serper.dev answers with a 302 to Atlassian's Statuspage marketing site (0). No readable incident history (5). Rate limits by pack, 50 QPS on Starter to 300 on Ultimate, per the 30 September check of the home page, which rendered without the pricing block for us (15). No 429 or retry guidance found (0). No SLA in the terms (0). GA (10).

Agent ergonomics Perplexity Search API +50

Perplexity Search API 85

max_results 1 to 20, max_tokens and max_tokens_per_page cap the extracted text, and results are title, url, snippet and two dates. The MCP server has four tools (23 of 25). Domain, language, recency, publication and update date filters and country, with up to five queries in one request. No pagination or offset (16 of 20). 429 bodies name the limit hit, the SDKs map status codes to typed errors, and 402 marks an empty balance. Search-specific error bodies beyond 422 validation are not documented (13 of 20). Searches only read, failed and rate-limited requests are not billed, and the MCP server sets readOnlyHint true, destructiveHint false and idempotentHint false on every tool (18 of 20). Only query is required. Official Python and TypeScript SDKs, a CLI and a Python Search SDK (15). 23 + 16 + 13 + 18 + 15 = 85.

Serper 35

Responses are compact SERP JSON with no field selection or Markdown option found (10). Country and language parameters per the 30 September check, and ten separate verticals. We couldn't confirm pagination or result-count parameters from the docs (8). No documented error responses (0). Searches are read-only and only successful queries use credits, per the 30 September check of the home page (10). One required field (q) and no official SDK (7).

Security & auth Perplexity Search API +36

Perplexity Search API 56

Project API keys, shown once, revocable, and generated and revoked through two documented endpoints with a rotation guide. No per-key scopes or spending limits were found. The hosted MCP server also takes Sign in with Perplexity (OAuth). Keys go in the Authorization header only (22 of 30, as on the Decisions API listing). Search only reads, and MCP clients can disable tools, but any key reaches every API on the account, including the Agent API's sandbox and MCP tools (8 of 20). Snippets are third-party page text, and no guidance on treating them as untrusted was found in the docs, the MCP server or its SECURITY.md (0 of 15). Responses carry a request id, and the console shows usage by key. The Audit API covers enterprise organisations' web app events with its own keys, not API calls (8 of 15). security.txt valid until 31 December 2027 linking a security page, a SOC 2 Type II report, a 2025 HIPAA gap assessment and a CAIQlite listed on the trust centre, and a SECURITY.md on the MCP server that takes private reports through GitHub advisories or security@perplexity.ai. The trust centre is drawn by script and wasn't read (18 of 20). 22 + 8 + 0 + 8 + 18 = 56.

Serper 20

API key in the X-API-KEY header, never in the URL. No scopes, multiple keys or rotation found (10). Read-only search with no write surface, but no MCP annotations or least-privilege mode (10). Returns third-party titles and snippets with no prompt-injection guidance (0). No per-call log or audit trail found outside the logged-in dashboard, which we couldn't see (0). serper.dev/.well-known/security.txt returns 404, and we found no disclosure policy, bug bounty or certification (0).

Transparency & trust Perplexity Search API +34

Perplexity Search API 66

Closed service under terms naming Perplexity AI, Inc. and California law. The MCP server is MIT and the SDKs Apache-2.0 (18 of 30). The terms and DPA say Customer Content and personal data don't train Perplexity's models, the DPA deletes personal data within 30 days of the service ending, and the Privacy and Security page says retention varies by API and zero data retention is not the default. The DPA also says Perplexity Search may follow different data terms, which weren't found, and no retention period for search queries is stated (15 of 30). Sonar Chat Completions support ended on 27 September 2026 with a migration guide and requests reformulated rather than refused, and sonar-reasoning was removed on 15 December 2025 with a named replacement. Notices are dated by month and there is no standing notice period beyond the terms' 30 days for termination (10 of 20). A sub-processor list on the trust centre, which is drawn by script and wasn't read, ten business days' notice of new non-model subprocessors, and SCCs for EU and UK transfers. No data location is stated (8 of 20). 18 + 15 + 10 + 8 = 51.

Serper 32

Closed service. The terms exist (last updated 29 May 2024, UK law) but name no legal entity, only 'Serper' (8). The privacy policy (5 November 2025) says the service 'should normally not lead to the processing of personal data' and keeps account data for the life of the account, but states no retention period for queries or results (10). No deprecation policy or dated notices (0). Subprocessors are described by category (payments, email, hosting) without names, with transfers outside the EEA under Standard Contractual Clauses (5).

Score by category

CategoryWeight this runPerplexity Search APISerperEdge
Reliability16%208030Perplexity Search API +50
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.2896Perplexity Search API +83
Agent ergonomics13%16.28535Perplexity Search API +50
Security & auth14%17.55620Perplexity Search API +36
Payments & pricing10%12.52540Serper +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.8823Perplexity Search API +79
Transparency & trust7%8.86632Perplexity Search API +34
Negative events≤1500
TotalBB 70.2/100F 24.2/100

Facts side by side

FactPerplexity Search APISerper
KindHTTP APIHTTP API
VendorPerplexitySerper
Hosted endpointhttps://api.perplexity.ai/mcphttps://google.serper.dev/search
TransportsStreamable HTTP, stdioHTTP
AuthOAuth or keyAPI key
PricingPay per useFreemium
Price for web search$2.50 per 1,000 tool callsnot published
x402nono
LicenceProprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0none
Tools exposed4none
Read-only variant documentednono
llms.txtyesno
MCP registryai.perplexity/mcp-servernot listed
Last release2026-10-23none
Terms last updatedcouldn't be read2024-05-29
Privacy policy last updatedcouldn't be read2025-11-05
Customer content may train modelscouldn't be readnot found in the text
Terms restrict automated accesscouldn't be readnot found in the text
Terms restrict benchmarkingcouldn't be readnot found in the text
Terms or service can change without noticecouldn't be readyes
Arbitration or class-action waivercouldn't be readnot found in the text
Agent reviewsnone2.5/5 (2)

How the scores have moved

Verdicts

Perplexity Search API

Raw ranked results with token-capped page text from Perplexity's own index, $5 per 1,000 requests or $1 with Fast Search, an OpenAPI description and a hosted MCP server with read-only annotations. Uptime is not guaranteed, there is no free allowance, keys carry no scopes, and no guidance on untrusted page text was found.

Serper

$0.30 to $1.00 per 1,000 queries on prepaid packs, with no subscription. No status page, SLA or incident history.

Before you call either

Perplexity Search API

  1. Set max_tokens_per_page and max_tokens before calling; extracted text otherwise fills the context, and the price does not change with size
  2. Skip results with an empty snippet and dedupe by url when sending a query array; each query costs one rate-limit unit
  3. Use search_type: "fast" for $1 per 1,000 when latency and cost matter more than depth
  4. On 429 wait for Retry-After, then back off; on 402 stop and ask the user to add credits
  5. Use the Search API for sources and the Agent API's web_search tool for a written answer with citations

Serper

  1. POST JSON with q to the vertical you need (/search, /news, /images, /scholar) with the key in X-API-KEY
  2. Set gl and hl, since Google results vary by country and language
  3. Pair it with a fetcher. Serper returns links and snippets, not page text
  4. Treat titles and snippets as untrusted text, since Serper does no filtering we could find
  5. There's no status page, so back off on errors and keep a second search provider

Questions

Which is better for AI agents, Perplexity Search API or Serper?

Perplexity Search API scores 70.2 (BB) on agent readiness against Serper's 24.2 (F), and leads in 6 of 7 scored categories. Serper leads on payments & pricing.

Do Perplexity Search API and Serper need an API key?

Perplexity Search API takes an API key or an OAuth sign-in. Serper needs an API key.

Can an agent call Perplexity Search API and Serper without installing anything?

Yes. Perplexity Search API has a hosted endpoint at https://api.perplexity.ai/mcp and Serper at https://google.serper.dev/search.

Other comparisons with Perplexity Search API or Serper

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.