Parallel / parallel/search

Parallel Search - access through LLMTR

Parallel Search is web search for agents and applications. Call it with `POST /v1/search`: it returns ranked URLs and excerpts and generates no answer. The price is per request rather than per token and depends on the chosen mode. Modes: turbo, fast, basic, advanced (default).

Technical specifications

Canonical IDparallel/search
ProviderParallel
Context windowNot available
OperationsWEB_SEARCH
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
WEB_SEARCHREQUESTPER_CALL$0.001000
WEB_SEARCHREQUESTPER_CALL$0.001000
WEB_SEARCHREQUESTPER_CALL$0.001000
WEB_SEARCHREQUESTPER_CALL$0.005000
WEB_SEARCHREQUESTPER_CALL$0.005000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions   -H "Authorization: Bearer llmtr-your_key"   -H "Content-Type: application/json"   -d '{"model":"parallel/search","messages":[{"role":"user","content":"Hello"}]}'

Related models