TinyFish

TinyFish Developer Documentation

Choose the right TinyFish API, authenticate quickly, and start integrating faster

TinyFish gives you six public API surfaces: Agent, Research, Search, Fetch, Browser, and Monitor. 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.

Search and Fetch are free within a daily allowance; beyond it they draw from your wallet. Research runs, Agent and Browser draw from your wallet.

Start Here

[card] Quick Start

Run your first integration in minutes

[card] Authentication

Set up API keys and MCP auth

[card] For Coding Agents

Single-page context for Claude, Codex, and Cursor

[card] Error Codes

Debug auth, rate limits, and run failures

Choose the Right API

[card] TinyAgent

Use natural-language goals to automate workflows on real sites

[card] Research API

Produce source-backed reports with configurable depth and live progress

[card] Search API

Get structured ranked web results for a query

[card] Fetch API

Fetch URLs and extract clean page content

[card] Browser API

Create a remote browser session for direct Playwright/CDP control

Canonical Endpoints

Product	Canonical endpoint
Agent	https://agent.tinyfish.ai/v1/automation/...
Research	POST https://agent.tinyfish.ai/v1/automation/run-research
Search	GET https://api.search.tinyfish.ai
Fetch	POST https://api.fetch.tinyfish.ai
Browser	POST https://api.browser.tinyfish.ai

Learn the Basics

[card] TinyAgent Endpoints

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

[card] Runs

Understand lifecycle, polling, and statuses

[card] Goals

Write instructions that produce reliable results

[card] Browser Context Profiles

Keep logged-in state across runs

[card] Browser Profiles

Choose lite vs stealth

[card] Proxies

Route runs through supported countries

[card] MCP Integration

Connect TinyFish to Claude and other assistants

This documentation is built and hosted on Mintlify, a developer documentation platform.