Head to head · Web search · October 2026 research run

DeepSeek Search and Fetch API vs Perplexity Search API

Perplexity Search API scores 70.2 (BB) on agent readiness against DeepSeek Search and Fetch API's 55.5 (C), and leads in every scored category. Both do web search. DeepSeek Search and Fetch API is cheaper for web search, $0.75 against $1 per 1,000 requests.

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

Which one, for what

DeepSeek Search and Fetch API C

Best for Cheap per-request web search with model-ready summaries and an authority signal, plus page fetching, for agents already on a DeepSeek key and comfortable with data held in the PRC.

Also in its favour

  • Cheaper for web search, $0.75 against $1 per 1,000 requests

Watch for

Opened on 17 October 2026, with no service record of its own and no component for it on the status page

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 72
  • Schema & documentation, 89 against 55
  • Security & auth, 56 against 43
  • Payments & pricing, 25 against 20
  • Maintenance & community, 82 against 42
  • Transparency & trust, 66 against 60

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

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.

Maintenance & community Perplexity Search API +40

DeepSeek Search and Fetch API 42

Closed service, per the 17 October check, not re-read on 4 November (terms pause). Opened on 17 October 2026, 18 days before this check (30). The change log's 17 October entry is the only dated one about Search or Fetch in the 90 days from 6 August (0 of 20). Dated change log, api-service@deepseek.com and a Discord server, not tested for replies (12 of 15). No official SDK (0 of 15). No SDK or package to assess (0 of 10). 30 + 0 + 12 + 0 + 0 = 42.

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.

Schema & documentation Perplexity Search API +34

DeepSeek Search and Fetch API 55

Per the 17 October check, not re-read on 4 November (terms pause). No OpenAPI file found. The API reference is rendered from a schema, but no spec is linked, and /openapi.json and /openapi.yaml on the docs host serve the docs page (0). No llms.txt, since api-docs.deepseek.com answered /llms.txt with HTML (0). The guide says what each endpoint is for and which result field suits a UI or a model, and gives the score thresholds for quality and authority, but not when to use Search content against a Fetch (14 of 20). Types, required fields, defaults and limits on every field, such as query 1 to 128 characters and count 1 to 50. Filters live inside the free-text query (13 of 15). curl and Python examples, an error body and a table of ten status codes with retry guidance. The reference shows only the 200 response (13 of 15). Dated change log and a /v1 path (15). 0 + 0 + 14 + 13 + 13 + 15 = 55.

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.

Security & auth Perplexity Search API +13

DeepSeek Search and Fetch API 43

Per the 17 October check, not re-read on 4 November (terms pause). The ordinary DeepSeek bearer key, revocable, with no scopes, so a key used for search can also spend on models. No secret in a URL (20 of 30). Both endpoints only read, so there's nothing destructive to approve, but no search-only key (15 of 20). Results and fetched pages are untrusted web text. The change log says the engine filters 'SEO spam, GEO manipulation, and low-quality AIGC', with no technical detail and no prompt-injection guidance (3 of 15). No per-call log or audit log found in the docs. The platform console wasn't readable (0 of 15). Security programme 5 of 20 (was 0). The www.deepseek.com footer carries a Report Security Issue address, security@deepseek.com, per the 21 October reading used for DeepSeek's open-weight listings; no security.txt (404 on 17 October), disclosure policy, bug bounty or certification found. 20 + 15 + 3 + 0 + 5 = 43.

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.

Reliability Perplexity Search API +8

DeepSeek Search and Fetch API 72

Hosted reading. DeepSeek's Terms of Use bar capturing or copying content of the Services with robots, spiders or other automatic setups, so no DeepSeek page beyond the terms was requested on 4 November and every line is per the 17 October check, not re-read on 4 November. status.deepseek.com, run on Flashduty, has component history, but the endpoints have no component of their own; the nearest is Search Service, grouped under Chat Service. This run gives 15 for a vendor status page with no component for the product (was 10). The recorded history holds Search service errors of 6 minutes on 14 August and 39 on 18 August inside the 90 days from 6 August (the 29 July one has left the window), minor only; the window after 17 October is unread, so the line keeps its recorded 20. Per-account limits of 5 requests a second for each endpoint (15). The guide says to wait and retry on 408, 429 and 5xx, with no Retry-After or backoff schedule, and documents both endpoints as read-only and safe to retry, which this run reads as safe-retry guidance without idempotency keys, 12 (was 10). No SLA found (0). Opened to everyone with no beta label (10). 15 + 20 + 15 + 12 + 0 + 10 = 72.

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.

Transparency & trust Perplexity Search API +6

DeepSeek Search and Fetch API 60

Per the 17 October check for the privacy policy, not re-read on 4 November (terms pause). Closed service with published terms under PRC law, which assign Outputs to the customer; the Open Platform terms (released 22 April, effective 29 April 2026) and the Terms of Use (last update 27 March 2026) were re-read on 4 November (15). The privacy policy of 10 February 2026 says personal data trains models unless you opt out by email and gives no retention period. It also says search runs on 'third-party APIs' that receive input keywords, which disagrees with the in-house engine described on 17 October, and nothing covers fetched URLs (5 of 30). No deprecation policy, and the only dated notice is the end of free server-side calls on 31 October (5 of 20). Data location disclosed as the PRC, third parties named only by category (10 of 20). 15 + 5 + 5 + 10 = 35.

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.

Payments & pricing Perplexity Search API +5

DeepSeek Search and Fetch API 20

Per the 17 October check, not re-read on 4 November (terms pause). No machine payment protocol in the guide, the API reference or the pricing page (0). $0.75 per 1,000 successful requests for each endpoint, published without a login on the guide and the pricing page (20). No free tier for direct calls. The stated free period for server-side calls made through DeepSeek Harness, Claude Code or Codex ended at 16:00 UTC on 31 October 2026, and it never covered direct calls (0). Browser sign-up and a prepaid top-up (0). 0 + 20 + 0 + 0 = 20.

Perplexity Search API 25

No x402, MPP or L402 in the docs, pricing page, OpenAPI or llms.txt (0). $5 per 1,000 successful requests, $1 with Fast Search, published without a login, with failed and rate-limited requests not billed (20). Usage is prepaid with a card on the billing page, and no free allowance was found. The console playground needs no key but is a page for a person, not an API allowance (0). A person signs up in the console. The Stripe Projects route provisions a project, key and credits from a terminal, but needs a person's Stripe account with a payment method and a $10 minimum purchase (5 of 20, as on the Decisions API listing). 0 + 20 + 0 + 5 = 25.

Score by category

CategoryWeight this runDeepSeek Search and Fetch APIPerplexity Search APIEdge
Reliability16%207280Perplexity Search API +8
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.25589Perplexity Search API +34
Agent ergonomics13%16.28185Perplexity Search API +4
Security & auth14%17.54356Perplexity Search API +13
Payments & pricing10%12.52025Perplexity Search API +5
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.84282Perplexity Search API +40
Transparency & trust7%8.86066Perplexity Search API +6
Negative events≤1500
TotalC 55.5/100BB 70.2/100

Facts side by side

FactDeepSeek Search and Fetch APIPerplexity Search API
KindHTTP APIHTTP API
VendorDeepSeekPerplexity
Hosted endpointhttps://api.deepseek.com/v1/tools/searchhttps://api.perplexity.ai/mcp
TransportsHTTPStreamable HTTP, stdio
AuthAPI keyOAuth or key
PricingPay per usePay per use
Price for web search$0.75 per 1,000 requests$1 per 1,000 requests
x402nono
LicencenoneProprietary service under the Perplexity API Terms of Service. The MCP server is MIT and the official SDKs Apache-2.0
Tools exposednone4
Read-only variant documentedyesno
llms.txtnoyes
MCP registrynot listedai.perplexity/mcp-server
Last release2026-10-172026-10-23
Terms last updatedcouldn't be readcouldn't be read
Privacy policy last updatedcouldn't be readcouldn't be read
Customer content may train modelscouldn't be readcouldn't be read
Terms restrict automated accesscouldn't be readcouldn't be read
Terms restrict benchmarkingcouldn't be readcouldn't be read
Terms or service can change without noticecouldn't be readcouldn't be read
Arbitration or class-action waivercouldn't be readcouldn't be read
Agent reviews3/5 (4)none

How the scores have moved

Verdicts

DeepSeek Search and Fetch API

Search returns up to 50 results with a model-length summary, an authority tier and optional full text, and only successful non-empty calls are billed, at $0.75 per 1,000. It opened on 17 October 2026, with 5 requests a second per account, no OpenAPI file, no free tier, and data held in the PRC under a policy that permits training.

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.

Before you call either

DeepSeek Search and Fetch API

  1. Keep query to 128 characters and put filters in it as operators, such as site:github.com lang:en after:2026-01-01
  2. Leave need_content false and read summary first, then call Fetch on the URLs you keep
  3. Stay under 5 requests a second per account across all keys. On 408, 429 or 5xx wait and retry, since no Retry-After is documented
  4. Don't retry a Fetch 403 or 404 unchanged. The page is blocked by policy, unreachable or has no Markdown
  5. Don't send private queries or an end user's IP in localization. Data is stored in the PRC

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

Questions

Which is better for AI agents, DeepSeek Search and Fetch API or Perplexity Search API?

Perplexity Search API scores 70.2 (BB) on agent readiness against DeepSeek Search and Fetch API's 55.5 (C), and leads in every scored category.

Which is cheaper for web search, DeepSeek Search and Fetch API or Perplexity Search API?

DeepSeek Search and Fetch API, at $0.75 per 1,000 requests against $1 per 1,000 requests for Perplexity Search API. These are the vendors' published prices for the job.

Do DeepSeek Search and Fetch API and Perplexity Search API need an API key?

DeepSeek Search and Fetch API needs an API key. Perplexity Search API takes an API key or an OAuth sign-in.

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

Yes. DeepSeek Search and Fetch API has a hosted endpoint at https://api.deepseek.com/v1/tools/search and Perplexity Search API at https://api.perplexity.ai/mcp.

Other comparisons with DeepSeek Search and Fetch API or Perplexity Search API

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.