Tavily API
Official vendor OpenAPI document · agent-readyAI/MLEmbeddings SearchapiKey2 EndpointsREST
For Agents
Programmatically search the web, extract content from urls. Covers 2 operations with apiKey authentication.
Use for: I need to the web, I want to extract content from urls, Get the current status of Tavily API resources, List all records from Tavily API
Not supported: Does not handle payments, communications, or crm - use for ai and machine learning only.
Tavily is a search API built for AI agents and LLMs. It provides fast, accurate, and real-time search results optimized for AI-powered applications. The API exposes 2 endpoints secured with apiKey authentication.
Install Jentic One Beta
Connect the Tavily API to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Tavily API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ftavily.com%2Ftavily" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Ftavily.com%2Ftavily" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with Tavily API.
Search the web
Extract content from URLs
Integrate Tavily API into automated workflows
Query and filter Tavily API records by parameters
Monitor Tavily API operational status and events
Use Cases
Patterns agents use Tavily API for, with concrete tasks.
★ AI and Machine Learning Operations
Use the Tavily API to perform ai ml operations programmatically. The API provides 2 endpoints covering core functionality including search the web, extract content from urls.
Call POST /search to search the web
Data Retrieval and Monitoring
Query Tavily API resources on a schedule to track changes, generate alerts, or feed downstream dashboards. Agents poll relevant endpoints, compare against previous state, and trigger actions when thresholds are crossed.
Poll the primary Tavily API endpoint, compare response to last known state, and alert if changed
AI Agent Integration via Jentic
AI agents discover and call Tavily API endpoints through Jentic without managing credentials directly. An agent searches for the required operation by intent, receives the matching endpoint schema, and executes the call with Jentic-managed authentication. This eliminates the need to read API documentation or handle apiKey tokens manually.
Search Jentic for 'search the web', load the operation schema, and execute with Jentic-managed credentials
Key Endpoints
2 endpoints — tavily is a search api built for ai agents and llms.
METHOD
PATH
DESCRIPTION
POST
/search
Search the web
POST
/extract
Extract content from URLs
POST
/search
Search the web
POST
/extract
Extract content from URLs
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Tavily API by hand means formatting your key as a Bearer value in the Authorization header, targeting the api.tavily.com host, and building your own retry handling on search and extract calls. Through Jentic you install once, import the Tavily API from the API Directory, store the API key once, and your agent calls it.
Permission scoping
The Tavily API takes its target in the request body of the search and extract endpoints, so limit the agent to the operations it needs, such as web search. You choose which of the two operations it may call, so extract is not included unless you add it.
Credential isolation
Your Tavily API key is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'search the web' or 'extract content from a URL', and Jentic returns the matching Tavily API operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using Tavily API through Jentic.
What authentication does the Tavily API use?
The Tavily API uses an API key passed in the `Authorization` header. Through Jentic, these credentials are stored encrypted in your Jentic One instance and injected at execution time, so raw secrets never enter the agent context.
Can I search the web with the Tavily API?
Yes. Use the POST /search endpoint. The API returns structured JSON responses that agents can parse and act on directly.
What are the rate limits for the Tavily API?
Rate limits are not specified in the OpenAPI spec. Check the vendor documentation for current limits. Through Jentic, rate limiting is handled automatically with retry logic built into the execution layer.
How do I search the web through Jentic?
Install the Jentic SDK with pip install jentic, authenticate through Jentic One, the self-hosted execution layer, then search for 'search the web'. Jentic returns the matching Tavily API operation with its input schema. Load the schema and execute the call - credentials are injected automatically.
How many endpoints does the Tavily API have?
The Tavily API exposes 2 endpoints covering extract, search operations.
Can I limit what my agent is allowed to do with the Tavily API?
Yes. Because you run Jentic One yourself, your own rules decide which of the Tavily API's two operations the agent may call and which credentials it can use. The Tavily API exposes only POST /search for web search and POST /extract for pulling content from URLs, so you can allow the agent to search the web while withholding extract until you choose to add it. Your API key is injected only for the operations you have permitted, so the agent never reaches endpoints you have not scoped it to.
GET STARTED