Call any fetchbean provider directly with POST /v1/run
Route requests to any fetchbean-supported provider and get back its native response — no per-provider SDK, account, or API key required.
POST /v1/run is the complete surface of fetchbean. It lets you reach any supported provider endpoint directly and returns the provider’s native response without any normalization or transformation. Every curated tool (Search, Read, Weather) is built on top of this same endpoint, so anything you can do with a curated tool you can also do — and more — with /v1/run.
fetchbean supports the following providers through /v1/run. Each provider has its own set of endpoints and per-call credit costs documented in the catalog.
Provider ID
Category
Description
exa
Web search
Neural web search built for retrieval across the open web.
parallel
Web search
Run multiple search queries or URL extractions in a single call.
jina
Page reading
Turns any URL into clean, LLM-ready markdown.
tikhub
Social data
Social data including public Instagram profiles.
openweather
Weather
On-demand weather data by city name or coordinates.
tavily
Web search
Agent-focused web search with optional synthesized answers.
perplexity
Web search
Web search with synthesized, cited answers.
remoteok
Jobs
Remote job listings across the web.
apprevs
App intelligence
iOS App Store search, metadata, reviews, ratings, and AI insights.
Meeting transcripts, summaries, and action items. Requires connection.
posthog
Analytics (BYOK)
Product analytics, feature flags, HogQL queries, and more. Requires connection.
linear
Issue tracking (BYOK)
Issues, projects, teams, and comments. Requires connection.
BYOK providers — Fireflies, PostHog, and Linear require you to connect your own API key before calling them. See the BYOK Connections guide for setup instructions.
Not sure which provider or endpoint to use? Call GET /discover?q=your+task to get a ranked list of provider methods that match your task description.