Skip to main content
TinyFish gives you four public API surfaces: Agent, Search, Fetch, and Browser. This docs site is organized to help you pick the right one quickly, authenticate once, and move straight to the examples or reference you need. Free Search and Fetch. Credits are used only by Agent and Browser.

​
Start Here

Quick Start

Run your first integration in minutes

Authentication

Set up API keys and MCP auth

For Coding Agents

Single-page context for Claude, Codex, and Cursor

Error Codes

Debug auth, rate limits, and run failures

​
Choose the Right API

Agent API

Use natural-language goals to automate workflows on real sites

Search API

Get structured ranked web results for a query

Fetch API

Render URLs in a real browser and extract clean page content

Browser API

Create a remote browser session for direct Playwright/CDP control

​
Canonical Endpoints

ProductCanonical endpoint
Agenthttps://agent.tinyfish.ai/v1/automation/...
SearchGET https://api.search.tinyfish.ai
FetchPOST https://api.fetch.tinyfish.ai
BrowserPOST https://api.browser.tinyfish.ai

​
Learn the Basics

Agent Endpoints

Pick /run, /run-async, or /run-sse

Runs

Understand lifecycle, polling, and statuses

Goals

Write instructions that produce reliable results

BBU Profiles

Keep logged-in state across runs

Browser Profiles

Choose lite vs stealth

Proxies

Route runs through supported countries

MCP Integration

Connect TinyFish to Claude and other assistants