Exa vs Perplexity Search API in 2026

Both calls, one key

You do not have to choose an API or rewrite one. Exa's call and the Perplexity Search API's call both run on SpecStream, each on its own path and in its own JSON. The address changes, and the key.

# Exa: before
curl -X POST https://api.exa.ai/search \
  -H "x-api-key: $EXA_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "open source vector databases", "numResults": 10}'

# Exa: after
curl -X POST https://api.specstream.ai/exa/search \
  -H "x-api-key: $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "open source vector databases", "numResults": 10}'

# Perplexity: before
curl -X POST https://api.perplexity.ai/search \
  -H "Authorization: Bearer $PERPLEXITY_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?", "max_results": 5}'

# Perplexity: after
curl -X POST https://api.specstream.ai/perplexity/search \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"query": "Who founded Mistral AI and when?", "max_results": 5}'

In the official SDKs it is one argument: Exa(api_key=SPECSTREAM_API_KEY, base_url="https://api.specstream.ai/exa") and Perplexity(api_key=SPECSTREAM_API_KEY, base_url="https://api.specstream.ai/perplexity"). Exa's MCP server takes EXA_API_BASE_URL, and Perplexity's takes PERPLEXITY_BASE_URL.

What stays the same

The Exa route reads query, numResults (1 to 100), includeDomains, excludeDomains, includeText, excludeText, startPublishedDate, endPublishedDate, contents.text and contents.highlights, and returns results[] with id, url, title, publishedDate and text, plus costDollars.total, the price of the call. It does not return score, summary, image or favicon. The Exa migration guide lists every parameter and field.

The Perplexity route reads query, max_results (1 to 20, or up to 50 with search_type people), search_domain_filter, search_recency_filter, the date filters and max_tokens_per_page, and returns results[] with title, url, snippet and date. It takes one query a call, and last_updated is always null. The Perplexity migration guide lists every parameter and field.

One price for every call, page text included

On SpecStream a search of up to 10 results costs $0.005 on either route, whether it asks for page text or not, and each started block of 10 more results adds $0.006: 100 results cost $0.059. 100,000 searches cost $500, from credit that never expires and with no monthly plan. A busy call answers 429 with Retry-After and is not charged.

The most accurate web search API in the world, in about one second

The SpecStream Search API scores a 97.9 F-score on all 1,000 official SimpleQA Verified questions, with 978 correct. On WideSearch it scores 64.0 item F1 and 43.4 row F1 on all 200 official tasks, and the Extract API scores 0.908 F1 on WCXB. The scores and the method are at specstream.ai/benchmarks.

A call of up to 10 results without page text runs the fast search. On November 9, 2026 production answered 718 of 720 fast searches: the median was 0.82 s at 1 search a second and 1.07 s at 20 a second, and the 95th percentile stayed between 1.09 and 1.73 s. There is no limit per key and no daily limit.

Zero retention on any key

Create the key with zero_retention and a search made with it keeps no request text and no answer after the reply. spend_cap_cents is the most the key can spend.

curl -X POST https://api.specstream.ai/v1/account/keys \
  -H "Authorization: Bearer $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"name": "production", "scopes": ["account:read", "finds:spend"], "spend_cap_cents": 500000, "zero_retention": true}'

Search, pages and rows on one key

The same key reads up to 20 pages or documents a call with the Extract API at $0.80 per 1,000 pages, and a page with no text is not charged. Exa Contents calls answer on the Exa route. Deep Search takes a request in plain words and returns every match on the live web as structured rows at 5¢, 15¢ or $1 a row. The most a run can cost is approved before it starts.

Tavily

$0.008 a credit pay as you go, 1 credit a basic search and 2 an advanced one. SpecStream answers Tavily's POST /search at https://api.specstream.ai/tavily, in Tavily's JSON, with the same key that answers Exa and Perplexity.

Brave Search API

$5 per 1,000 requests, with $5 in free credits every month and 50 queries a second. SpecStream answers Brave's GET /res/v1/web/search in Brave's JSON on the same key.

Parallel Search API

From $1 per 1,000 requests. SpecStream answers Parallel's POST /v1/search at https://api.specstream.ai/parallel, in Parallel's JSON, on the same key and balance.

Linkup

Search at $0.005 to $0.006 a request, and Research at $0.25 to $2.50. SpecStream answers Linkup's search at https://api.specstream.ai/linkup/v1, with searchResults and sourcedAnswer, on the same key.