Structured live web search
Search returns fresh web results with titles, URLs, snippets, and metadata in a predictable response format that agents can route into research, retrieval, citations, or monitoring workflows.
TinyFish
TinyFish is a web infrastructure platform for AI agents that combines live search, page fetching, browser sessions, and multi-step automation. Search and Fetch are free, while Agent and Browser are metered against Wallet funds.
Web infrastructure for AI agents
TinyFish is a web infrastructure platform for AI agents and automated workflows. It combines search, page fetching, browser sessions, and web automation so software can work with live websites instead of static datasets.
The product is organized around four main surfaces: Search for fresh structured results, Fetch for clean page content, Agent for multi-step task execution, and Browser for cloud browser sessions. On the pricing side, Search and Fetch are free, while Agent and Browser are metered against Wallet funds with no monthly plan, no minimum, and separate enterprise options for larger teams.
Features
Browser-rendered page extraction
Fetch renders any URL in a real browser and returns clean markdown by default, with HTML and JSON options when workflows need different output shapes.
Multi-step web automation
Agent handles multi-step web tasks such as navigating pages, filling forms, and authenticating into sites, with output that can feed production workflows.
Cloud browser sessions
Browser provides cloud browser sessions for authenticated and dynamic sites, with persistent state and infrastructure for running interactive web workflows.
Wallet-based usage billing
Pricing and runtime are organized around a Wallet model: Search and Fetch stay free, while Agent and Browser are metered against account funds when they run.
Multiple access paths for teams
TinyFish exposes the same capabilities through SDKs, CLI, MCP, and direct API access, and the pricing page mentions support for teams through enterprise contracts, SSO, audit logs, VPC deployment, and uptime SLA options.
Use cases
Live web discovery
Use Search when an agent needs current sources, recent prices, or changing information from the live web, and you want structured results that can feed downstream retrieval or decision logic.
Clean page ingestion
Use Fetch when a workflow already has a URL and needs the page content stripped down to readable markdown, JSON, or HTML for summarization, storage, or analysis.
Authenticated task automation
Use Agent for multi-step website tasks that require navigation, form filling, and authentication, such as quote requests or portal workflows.
Cloud browser execution
Use Browser when a workflow depends on a real browser session for dynamic pages or login-protected sites that search alone cannot reach.
Team-scale deployment
Use the enterprise tier when a team needs account-level limits, security review, and operational controls such as SSO, audit logs, VPC deployment, or an uptime SLA.
Pros and Cons
Pros
- Search and Fetch are free at any Wallet balance, which lowers the barrier to trying the platform for live web retrieval and page extraction.
- Search returns structured, fresh results designed for agent workflows rather than general consumer search.
- Fetch renders pages in a real browser and returns cleaner output formats such as markdown, HTML, or JSON.
- The platform supports multiple access methods, including SDKs, CLI, MCP, and direct API access.
- Enterprise options are available for teams that need raised limits, SSO, audit logs, VPC deployment, and an uptime SLA.
Cons
- The source materials provide only high-level detail for some product surfaces, so deeper workflow or configuration specifics are not clearly documented here.
- Agent and Browser require Wallet funds to start, so they are not unlimited free tools.
FAQ
What is TinyFish Search used for?
TinyFish Search is for programmatic workflows that need fresh web results. It returns structured results with URLs, titles, snippets, and metadata, and it is free at any Wallet balance.
What does TinyFish Fetch return?
TinyFish Fetch is used when a workflow needs the content of a specific URL in a clean format. It renders the page in a real browser and returns markdown by default, with HTML and JSON options available.
Which parts of TinyFish are free and which are paid?
TinyFish Agent and Browser are metered against Wallet funds. Search and Fetch remain free and do not draw from the Wallet.
How can teams integrate TinyFish into their stack?
Yes. The pricing page says you can call Search from the CLI, wire it into an MCP client, or use the SDKs and API. Fetch is also available through the CLI, MCP, SDK, or API.
Can concurrency or rate limits be raised?
The pricing page lists account limits for Agent and Browser that start at 2 concurrent runs for Agent and 5 concurrent sessions for Browser, with higher limits available through sales.
Quick Facts
- Category
- Developer tool
- Primary use
- Web infrastructure for AI agents
- Core surfaces
- Search, Fetch, Agent, Browser
- Pricing model
- Search and Fetch are free; Agent and Browser are metered against Wallet funds
- Access methods
- SDKs, CLI, MCP, and API
- Website
- tinyfish.ai
Alternativas ao TinyFish
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Codex Plugins
Codex Plugins bundle reusable skills, app integrations, and MCP servers into workflows you can install in the Codex app or use from Codex CLI. They help extend Codex with connected-service tasks, reusable instructions, and shared team workflows.
hob
hob is an independent workspace for coding agents that keeps agent sessions, terminals, history, and follow-up work organized around the tools and providers you already use. It is aimed at developers who want local control over routing, history, and workspace structure rather than a bundled model stack.
Wallie
Wallie is an open-source AI streamer that watches your screen, hears chat, and generates live commentary in a configurable persona. It runs locally on your machine with your own keys and is aimed at faceless content, autonomous streams, and real-time reactions.
Manta AI
Manta AI is an autonomous web app testing tool for teams that want to map application behavior, catch regressions, and generate tests without writing scripts or maintaining selectors. It works from a URL and supports plain-English test flows, run results with screenshots, and scheduled or deployment-triggered checks.