TinyFish review, pricing and verdict

TinyFish is enterprise infrastructure for AI web agents that automate business workflows across hundreds of sites, reporting a 98.7% success rate.

Best for
Enterprise data operations and engineering teams at Fortune 500 companies automating web workflows at scale
Not for
Freelance web scrapers and data resellers who need low-cost, high-volume scraping

Should you use TinyFish?

TinyFish suits enterprise teams that need AI agents to log into sites, fill forms, and pull structured data at scale instead of hand-coding scrapers. It already handles 30 million operations a month for Fortune-scale customers like Google Hotels and DoorDash, replacing bespoke scraping scripts with a managed, natural-language agent runtime.

Parallel execution at 1,000x scale with all-inclusive pricing (no separate browser/proxy/inference costs), Claude MCP integration, and natural language control—enabling non-technical teams to deploy enterprise-grade web automation in minutes, not months.

TinyFish's moat is strong: deep technical execution (82% on Mind2Web vs 43% for Operator), institutional relationships (Google, DoorDash, Fortune 500), and well-capitalized backing ($47M Series A). However, the underlying AI (vision LLMs) is not proprietary, and as frontier models improve at web understanding, competitive moats erode. Lock-in through integrations and workflows provides additional defensibility.

Also for

  • Healthcare and insurance ops leaders automating compliance and data collection across hundreds of provider/regulatory sites
  • Fortune 500 companies automating complex web workflows at scale (Google Hotels, DoorDash use cases)
Show 3 more
  • Healthcare organizations tracking prior authorizations and clinical trial data from multiple provide
  • Insurance firms monitoring regulatory filings and compliance across hundreds of government websites
  • Financial services automating data extraction from multiple banking and trading platforms

Also not for

  • Teams needing CAPTCHA solving and advanced evasion techniques

Main trade-off

CAPTCHA handling is unsupported, blocking any workflow on sites relying on image or hCaptcha verification. This is a hard technical limit that affects a significant percentage of modern web properties.

TinyFish pricing

PlanMonthly price
FreeFree
Pay-as-you-goFree
EnterpriseFree
Starter$15/mo
Pro$150/mo

Free: 500 steps, no credit card required. Pay-as-you-go: $0.015/step, 2 concurrent agents. Starter: $15/month (1,650 steps, 10 concurrent agents, $0.014 overage/step). Pro: $150/month (16,500 steps, 50 concurrent agents, $0.012 overage/step). Enterprise: Custom pricing with custom volume, concurrency, and SLA. All-inclusive: no separate charges for browsers, proxies, or LLM inference.

What each plan includes

FeatureFreePay-as-you-goEnterpriseStarterPro
Web search100 req/moUnlimitedUnlimitedUnlimitedUnlimited
Page fetch (Markdown)100 req/moPer-useUnlimitedUnlimitedUnlimited
AI browser agents5 runs/moPer-runCustom100 runs/mo1,000 runs/mo
Stealth sessions——✓—✓
MCP server✓✓✓✓✓

Before you commit

  • Step pricing opaque in production; multi-step sequences and error retries inflate costs unpredictably.
  • Enterprise deployments often require consulting, training, and custom workflows; support costs can 2x the base subscription.
  • Overage costs, though declining per tier, accumulate quickly on Starter tier if workflows become more complex.

What TinyFish does

TinyFish is enterprise infrastructure that lets organizations run autonomous AI agents across external websites: logging in, filling forms, and extracting structured data without managing browsers or proxies. It scores 82 percent on the Mind2Web benchmark, well ahead of OpenAI's Operator, and already powers production traffic for Google Hotels and DoorDash.

  • Parallel Web Automation

    Run up to 1,000 simultaneous operations across multiple websites in a single deployment, enabling massive-scale web data operations without managing infrastructure.

  • Natural Language Control

    Describe web tasks in plain English: no CSS selectors, XPath, or code required. Agents interpret goals and execute workflows autonomously.

  • Authentication and Dynamic Sites

    Navigate password-protected sites, handle multi-factor authentication, interact with form-based systems, and extract data from JavaScript-rendered content at production speed.

  • Claude MCP Integration

    Connect TinyFish directly to Claude Desktop via Model Context Protocol, enabling AI assistants to run web automation with real-time progress streaming.

Show all 6 features
  • AgentQL Query Language

    Extract structured data and automate workflows using AgentQL, a specialized query language with Python and JavaScript SDKs, REST API, and browser debugger.

  • All-Inclusive Pricing

    No hidden charges for browsers, proxies, residential IP routing, or LLM inference. Step-based billing with transparent overage costs declining by tier.

Works with

  • Claude MCP (Model Context Protocol)
  • REST API
  • Python SDK
  • JavaScript SDK
  • n8n community node
  • AG2 agents
  • Playwright integrations

Missing integrations

  • No Zapier support
  • No Make (formerly Integromat) support
  • No webhook or serverless function triggers
  • No direct Slack/Teams/Discord notifications
  • No CAPTCHA solving integrations

Most users expect these and they are not currently supported.

Capabilities

  • Web automation
  • AI agent
  • Workflow automation
  • Data extraction
  • API first

Strengths and limits

Strengths

  • Benchmark performance beats OpenAI's Operator by a wide margin on the Mind2Web test, evidence of real capability on hard, real-world web tasks rather than a curated demo.
  • Already running in production at recognizable big-name customers like Google Hotels and DoorDash, proof this has moved past pilot stage into everyday reliability.
  • A free tier with no credit card required lowers the barrier for testing before committing budget.
  • Plain-English task descriptions mean non-technical teams can automate a workflow without learning CSS selectors or XPath, unlike most scraping tools.
  • All-inclusive pricing bundles browsers, proxies, and AI inference into one line item, simplifying budgeting against tools that meter each separately.

Limits

  • CAPTCHA handling still limited; automated solving is not supported, blocking workflows on sites heavy in image-based or hCaptcha verification.
  • Enterprise-only positioning with $47M in funding and a large-enterprise customer base means pricing and support are built around big companies, not individuals or small teams.
  • API and MCP documentation is thinner than mature web-scraping tools, with fewer public recipes and integration examples published so far.
  • The serverless architecture creates vendor lock-in: migrating a large workflow to a competitor or a self-hosted alternative would take real engineering effort.
Show 2 more
  • Step-based billing can be hard to predict since complex, multi-step sequences may cost more than a simple task estimate suggests.
  • Success-rate, latency, and uptime SLAs are not published; enterprise buyers must request the details directly.

How Hokai rates it

  • Ease of use7.0 / 10
  • Features8.0 / 10
  • Value for money8.0 / 10
  • Support6.5 / 10

TinyFish alternatives

ToolPrice fromFree planRuns onRating
TinyFish This page$15/moYesWeb3.7
ExaExa is enough on its own for clean, AI-native web search results; TinyFish is the one to reach for once the workflow needs a full agent that can log in, fill out forms, and pull structured data from behind an auth wall.$49/moYesWeb4.0
LangChainHand-building a custom agent pipeline with any tool is what LangChain is for; TinyFish instead ships a managed browser-agent runtime with stealth and anti-bot handling already built in.$39/moYesWeb · Mac · Windows--
CometPerplexity's Chromium-based AI browser with a built-in assistant, free on Mac, Windows, iOS and Android, with 7 headline features.$17/moYesiOS · Android · Mac · Windows4.0

TinyFish facts

Deployment
Cloud
Works offline
No
Price band
Enterprise pricing
Languages
English
Maker founded
2023
Total funding
$47M Series A (August 2025)
Training
Documentation (docs.tinyfish.ai) · CLI reference · MCP integration guide

Data and privacy

Proprietary

Questions about TinyFish

What does TinyFish actually cost?

TinyFish charges by step: pay-as-you-go runs $0.015 per step with 2 concurrent agents, Starter is $15 a month for 1,650 steps and 10 concurrent agents ($0.014 overage), and Pro is $150 a month for 16,500 steps and 50 concurrent agents ($0.012 overage). Enterprise pricing is custom, and every plan bundles browser, proxy, and AI-inference costs into the same per-step rate.

What do you get on TinyFish's free tier?

The free tier includes 500 steps a month with no credit card required, covering the same authentication, extraction, and MCP access as the paid plans. Once a workflow crosses 500 steps, TinyFish switches automatically to pay-as-you-go billing or a paid tier.

Which tools compete with TinyFish in 2026?

Airtop is a simpler pick for no-code, single-site browser automation, and Hexomatic or Axiom AI cost less if you only need to automate one site at a time. TinyFish is built for enterprise-scale parallel automation across hundreds of sites with native Claude integration, so it fits teams that have outgrown single-site tools.

Is TinyFish better than Airtop?

Airtop is the simpler, no-code option and works well for individual sites, but it does not offer TinyFish's parallel execution across many sites at once or the all-inclusive step-based pricing that folds browser and proxy costs into one rate. TinyFish is the stronger choice once a team needs enterprise-scale automation rather than a single workflow.

What does it take to start using TinyFish?

Sign up for the free tier (no credit card needed) and either call the REST API directly or connect through the Python or JavaScript SDK. TinyFish also ships an MCP server, so Claude Desktop users can connect and start running agents in a chat interface within minutes.

About TinyFish

TinyFish is enterprise web agent infrastructure that launched from stealth in August 2025 with $47 million in Series A funding. It was founded in 2023 by Sudheesh Nair (former Nutanix President), Shuhao Zhang (ex-Meta engineering leader), and Keith Zhai (ex-Wall Street Journal), and enables organizations to automate complex web interactions at scale without managing browsers, proxies, or infrastructure themselves.

Read the full background

The platform runs as a serverless API: it accepts a natural-language goal and a target URL, then dispatches an AI agent to navigate the site, handle logins and multi-step forms, extract structured data, and complete the transaction while streaming progress in real time. Traditional web scraping tools need CSS selectors, XPath, or custom configuration; TinyFish agents work from a plain-English task description instead, connecting to Claude Desktop through the Model Context Protocol and exposing a REST API, Python and JavaScript SDKs, and an AgentQL query language for developers who want more control.

On the Mind2Web benchmark, TinyFish scores 82 percent versus 43 percent for OpenAI's Operator, a 39-point lead the company points to as evidence of production readiness rather than a research demo.

TinyFish already runs in production at large enterprises: Google uses it to aggregate hotel inventory across Japan for Google Hotels search, DoorDash relies on it to manage web-interaction complexity, and ClassPass, Amazon, Amplemarket, NextEra, Jobright, and Healdev deploy it across healthcare prior-authorization tracking, insurance regulatory-filing monitoring, financial services, retail price monitoring, and supply-chain shipment tracking.

Sources and guides

More AI Tools on Hokai

  • DiaDia is a Chromium browser for macOS and Windows with a built-in assistant that answers from your tabs and apps like Gmail, Slack and Notion.
  • LettaOpen-source agent platform from the MemGPT team. Agents remember across chats, run in a CLI, web app or SDK, and reply on Slack, Telegram and more.
  • BardeenFind and reach leads no one else can with agentic web scraping, AI qualification, and contact enrichment.
  • Browse AIBrowse AI is a no-code web scraping and monitoring platform used by 500,000+ users, turning any website into structured data with point-and-click robot training and a free plan available.
  • MagicTripsAI itinerary generator by to1 Labs that builds full day-by-day travel plans in seconds for free, with a Pro plan at $9.99/mo.
  • DifyOpen-source LLM app builder with visual workflows, RAG and agents, run on Dify Cloud or your own Docker host. Backed by a $30M Series Pre-A round.