Parallel Search API compatible

The call, before and after

# Before
curl -X POST https://api.parallel.ai/v1/search \
  -H "x-api-key: $PARALLEL_API_KEY" -H "Content-Type: application/json" \
  -d '{"search_queries": ["Mistral AI founders"], "mode": "fast"}'

# After
curl -X POST https://api.specstream.ai/parallel/v1/search \
  -H "x-api-key: $SPECSTREAM_API_KEY" -H "Content-Type: application/json" \
  -d '{"search_queries": ["Mistral AI founders"], "mode": "fast"}'

In the parallel-web Python SDK the change is the client line. The SDK also reads PARALLEL_BASE_URL from the environment.

# Before
client = Parallel(api_key=PARALLEL_API_KEY)

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

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.

LiteLLM 1.108.4: set PARALLEL_AI_API_BASE to https://api.specstream.ai/parallel and put your SpecStream key in PARALLEL_AI_API_KEY. The call stays litellm.search(search_provider="parallel_ai").

LangChain, langchain-parallel 0.5.0: pass base_url="https://api.specstream.ai/parallel" to ParallelWebSearchTool, or set PARALLEL_BASE_URL.

OpenClaw: set plugins.entries.parallel.config.webSearch.baseUrl to https://api.specstream.ai/parallel. The plugin adds /v1/search itself.

Cherry Studio: in the Parallel provider, set API Host to https://api.specstream.ai/parallel.

Every parameter the route uses

Used in the search: search_queries (one or more), mode (turbo, fast, basic or advanced), advanced_settings.max_results, and advanced_settings.source_policy with include_domains, exclude_domains and after_date as YYYY-MM-DD.

Used to shape the reply: advanced_settings.excerpt_settings.max_chars_per_result, max_chars_total (shared out evenly so every result keeps some text) and session_id, which comes back as sent.

Refused with Parallel's 422 body: a mode outside the four, and a field Parallel does not take, at the top of the body or in advanced_settings. A call with no key gets 401.

Every field that comes back

The reply has search_id, results and session_id. Each result has url, title, publish_date when the page has a date, and excerpts, a list with the result's text. The route does not return warnings or usage.

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

$5 per 1,000 searches, in every mode

A call of up to 10 results costs $0.005 in every mode, and basic and advanced include the text of each page. Each started block of 10 more results adds $0.006: 20 results cost $0.011. 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 in fast or turbo mode 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 in basic or advanced mode 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 Parallel alternative page.

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.

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.

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.