Perplexity Search API compatible

The call, before and after

# 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}'

# 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 perplexityai Python SDK the change is the client line. The SDK also reads PERPLEXITY_BASE_URL from the environment.

# Before
client = Perplexity(api_key=PERPLEXITY_API_KEY)

# After
client = Perplexity(api_key=SPECSTREAM_API_KEY, base_url="https://api.specstream.ai/perplexity")

Every parameter and field on this page is in the pass table, measured on production on November 10, 2026.

Apps and SDKs that take the address as a setting

Each line was run on production on November 10, 2026 through that client's own request and reply code. Put your SpecStream key wherever the client takes its key.

Open WebUI: choose the web search engine perplexity_search and set Perplexity Search API URL (PERPLEXITY_SEARCH_API_URL) to the whole address, https://api.specstream.ai/perplexity/search, with your SpecStream key in the engine's key field.

LiteLLM 1.108.4: set PERPLEXITY_API_BASE to https://api.specstream.ai/perplexity and put your SpecStream key in PERPLEXITYAI_API_KEY. The call stays litellm.search(search_provider="perplexity").

LangChain, langchain-perplexity 1.4.2: PerplexitySearchRetriever has no address argument, so set PERPLEXITY_BASE_URL to https://api.specstream.ai/perplexity in the environment.

Perplexity's MCP server: set PERPLEXITY_BASE_URL to https://api.specstream.ai/perplexity, with your SpecStream key where the Perplexity key went.

Every parameter the route uses

Used in the search: query (a string, or a list of one), max_results (1 to 20, or up to 50 with search_type people), search_type people, search_domain_filter with or without a - before a domain, search_recency_filter (hour, day, week, month, year), search_after_date_filter and search_before_date_filter.

Used to shape the reply: max_tokens_per_page and max_tokens (each token is 4 characters of page text, and a budget for all results is shared out evenly), and display_server_time.

Refused with Perplexity's 422: a query list of two or more queries, a max_results over 20 on a web search, and a date filter that is not MM/DD/YYYY. A call with no key gets 401.

Every field that comes back

The reply has id, results and server_time, which holds the time when you send display_server_time and is null otherwise. Each result has title, url, snippet, date when the page has a date, and last_updated, which is always null.

One field is added: specstream, with what the Search API returns beyond Perplexity's fields, including the call's price_usd. A parser that reads Perplexity's fields never sees it.

$5 per 1,000 searches, page text included

A call of up to 10 results costs $0.005, with or without a page text budget. Each started block of 10 more results adds $0.006: 20 results cost $0.011 and a people search of 50 costs $0.029. A call stopped by a 429 charges nothing, and credit you buy never expires.

The most accurate web search API, in about one second

On SimpleQA Verified the SpecStream Search API scores 97.9 F-score on all 1,000 official questions, 978 of them correct. On WideSearch it scores 64.0 item F1 and 43.4 row F1 on all 200 official tasks. The Extract API scores 0.908 F1 on WCXB. Every score and its method is on the benchmarks page.

A call with no max_tokens or max_tokens_per_page runs the fast search. Measured on production on November 9, 2026, its median was 0.82 s at 1 search a second and 1.07 s at 20 a second, the 95th percentile stayed between 1.09 and 1.73 s, and it answered 718 of 720. It takes up to 8,800 searches a minute on one account. A call with a page text budget runs the default search, which reads the pages, at the same price.

You decide what is kept, on each key

Create the key with zero_retention and a search made with it keeps no request text and no answer after the reply: it is not in the history, its answer is not reused for another call, and its log lines carry neither. 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. Deep Search returns every match for a request in plain words as structured rows, at 5¢, 15¢ or $1 a row, with a source URL on every value. The most a run can cost is approved before it starts. The full comparison is on the Perplexity alternative page.

Tavily

A search API sold in credits at $0.008 each pay as you go: a basic search takes 1 credit and an advanced search 2. SpecStream answers Tavily's POST /search at https://api.specstream.ai/tavily for $0.005, basic or advanced.

Exa

A search API on Exa's own index, at $7 per 1,000 requests on auto and $4 on lite for up to 10 results, with its own request and reply. SpecStream answers Exa's call as well, at https://api.specstream.ai/exa, for $0.005 a search.

Brave Search API

A search API on Brave's own index at $5 per 1,000 requests, with $5 in free credits every month and 50 queries per second. SpecStream answers Brave's call at https://api.specstream.ai/res/v1/web/search at the same price per call and takes up to 8,800 searches a minute on one account.