Last updated 08-13-2026
Category:
Reviews:
Join thousands of AI enthusiasts in the World of AI!
TinyFish
TinyFish gives AI agents a way to use the live web through one API: search, fetch a page as clean markdown, run a real browser, and finish multi-step tasks. Search and Fetch cost zero credits on every plan. You start paying when an agent has to click, log in, or hold a session. That split is built for work that dies on dynamic pages and login walls.
Most web APIs in this category stop at search and scraping. TinyFish's own comparison pages put it next to Exa, Firecrawl, Parallel, and Tavily, then add a Web Agent that fills forms and a stealth browser for sites that block scrapers. The meter stays off until the page needs interaction, which is a different cost shape than paying per crawl.
Teams at DoorDash, Grubhub, The Zebra, and Google Hotels Japan use it for price checks, quoting, and inventory that never had a public API. If you already run Claude, Cursor, or a custom agent stack, it is one MCP config or one API key.
Web Agent hits 89.9% on Online-Mind2Web, vs 69% for Gemini 2.5 Computer Use
Fetch returns markdown, HTML, or JSON, with 93% of test pages usable
Search median latency is 556ms on their 1,200-query internal eval
Browser sessions cold-start in under 250ms and cap at 60 minutes
MCP at agent.tinyfish.ai/mcp, plus Python, TypeScript, CLI, and REST
Agent steps cost 1 credit each; failed runs are billed at $0
Search and Fetch stay at 0 credits, so grounding an agent on live pages does not burn the credit pool.
Failed Agent runs are billed at $0, which matters when a site changes mid-workflow.
One API key covers search, fetch, browser, and agent instead of stitching four vendors.
Published Mind2Web and WebVoyager scores give an accuracy bar most scraping APIs never post.
Pay as you go caps concurrent Agent runs at 2 and Browser sessions at 5.
ISO 27001, SOC 2, and on-prem are limited to the Enterprise plan.
Browser sessions cap at 60 minutes, so long portal work has to be chunked.
Agent and Browser work still consume credits at $0.015 per step or 1 credit per 4 minutes of browsing.
Does TinyFish have a free plan?
Yes. TinyFish Search and Fetch are free on every plan and use no credits. New accounts also get 500 free credits for Agent and Browser, with no card required. Paid Starter and Pro plans add monthly credit allotments on top of that.
How much does TinyFish cost?
TinyFish Starter is $15 per month for 1,650 credits, and Pro is $150 per month for 16,500 credits. Pay as you go is $0.015 per credit after 500 free starter credits. Search and Fetch stay at 0 credits. Enterprise pricing is custom.
Does TinyFish have an API?
Yes. TinyFish exposes four APIs: Search, Fetch, Agent, and Browser. Canonical endpoints include GET https://api.search.tinyfish.ai, POST https://api.fetch.tinyfish.ai, and POST https://api.browser.tinyfish.ai. SDKs cover Python and TypeScript, plus CLI and MCP.
What does TinyFish integrate with?
TinyFish connects through MCP, REST, Python and TypeScript SDKs, Claude Code, Cursor, n8n, LangChain, and Dify. The MCP server URL is https://agent.tinyfish.ai/mcp.
Can TinyFish agents log into websites?
Yes. TinyFish Web Agent handles authenticated sessions with persistent browser profiles, so it can return to vendor portals with cookies intact. The Browser API is built for login walls and anti-bot protected sites.
How accurate is the TinyFish Web Agent?
TinyFish reports 89.9% task success on Online-Mind2Web and 91.1% on WebVoyager (641 tasks across 15 live sites). Those are the figures they publish against Gemini 2.5 Computer Use, OpenAI Operator, and BrowserUse.
Is TinyFish a web scraping API?
TinyFish Fetch is a web scraping API that turns a URL into markdown, HTML, or JSON at 0 credits. Search is also free. Agent and Browser are the paid layer for pages that need clicks, forms, or a login.