Initiate a web crawl from a base URL

Retrieve initiate a web crawl from a base URL via API. Supply a URL. Sample fields include results and URLs. Use the result as input for a related analysis or application. The POST request schema also lists instructions, chunks_per_source.

Selected price
$0.008 / billing creditPublished pricing
Sellers / implementations
1 / 1
Requests · 30d
—Loading...
Success rate · 30d
—Loading...

Run sends a real API request. Charges follow the published API contract.

Request parameters
The root URL to begin the crawl.
Optional parameters (14)
Natural language instructions for the crawler. When specified, the mapping cost increases to 2 API credits per 10 successful pages instead of 1 API credit per 10 pages.
Chunks are short content snippets (about 800 characters each) pulled directly from the source. Use `chunks_per_source` to define the maximum number of relevant chunks returned per source and to control the `raw_content` length. Chunks will appear in the `raw_content` field as: `<chunk 1> [...] <chunk 2> [...] <chunk 3>`. If a page splits into no more chunks than `chunks_per_source`, its full content is returned. Available only when `instructions` are provided. Must be between 1 and 5.
Max depth of the crawl. Defines how far from the base URL the crawler can explore.
Max number of links to follow per level of the tree (i.e., per page).
Total number of links the crawler will process before stopping.
select_paths array
Regex patterns to select only URLs with specific path patterns (e.g., `/docs/.*`, `/api/v1.*`).
select_domains array
Regex patterns to select crawling to specific domains or subdomains (e.g., `^docs\.example\.com$`).
exclude_paths array
Regex patterns to exclude URLs with specific path patterns (e.g., `/private/.*`, `/admin/.*`).
exclude_domains array
Regex patterns to exclude specific domains or subdomains from crawling (e.g., `^private\.example\.com$`).
Whether to include external domain links in the final results list.
Whether to include images in the crawl results.
Advanced extraction retrieves more data, including tables and embedded content, with higher success but may increase latency. `basic` extraction costs 1 credit per 5 successful extractions, while `advanced` extraction costs 2 credits per 5 successful extractions.
The format of the extracted web page content. `markdown` returns content in markdown format. `text` returns plain text and may increase latency.
Whether to include the favicon URL for each result.

Sample response

"base_url": "docs.tavily.com"
"request_id": "123e4567-e89b-12d3-a456-426614174111"
"response_time": 1.23
results [3]
[0] {}
"favicon": "https://mintlify.s3-us-west-1.amazonaws.com/tavilyai/_generated/favicon/apple-touch-icon.png?v=3"
raw_contentString · text preview
results[0].raw_content
Welcome - Tavily Docs

[Tavily Docs home page![light logo](https://mintlify.s3.us-west-1.amazonaws.com/tavilyai/logo/light.svg)![dark logo](https://mintlify.s3.us-west-1.amazonaws.com/tavilyai/logo/dark.svg)](https://tavily.com/)

Search or ask...

Ctrl K

- [Support](mailto:[email protected])
- [Get an API key](https://app.tavily.com)
- [Get an API key](https://app.tavily.com)

Search...

Navigation

[Home](/welcome)[Documentation](/documentation/about)[SDKs](/sdk/python/quick-start)[Examples](/examples/use-cases/data-enrichment)[FAQ](/faq/faq)

Explore our docs

Your journey to state-of-the-art web search starts right here.

[## Quickstart

Start searching with Tavily in minutes](documentation/quickstart)[## API Reference

Start using Tavily's powerful APIs](documentation/api-reference/endpoint/search)[## API Credits Overview

Learn how to get and manage your Tavily API Credits](documentation/api-credits)[## Rate Limits

Learn about Tavily's API rate limits for both development and production environments](documentation/rate-limits)[## Python

Get started with our Python SDK, `tavily-python`](sdk/python/quick-start)[## Playground

Explore Tavily's APIs with our interactive playground](https://app.tavily.com/playground)
"url": "https://docs.tavily.com/welcome"
[1] {}
"favicon": "https://mintlify.s3-us-west-1.amazonaws.com/tavilyai/_generated/favicon/apple-touch-icon.png?v=3"
raw_contentString · text preview
results[1].raw_content
Credits & Pricing - Tavily Docs

[Tavily Docs home page![light logo](https://mintlify.s3.us-west-1.amazonaws.com/tavilyai/logo/light.svg)![dark logo](https://mintlify.s3.us-west-1.amazonaws.com/tavilyai/logo/dark.svg)](https://tavily.com/)

Search or ask...

Ctrl K

- [Support](mailto:[email protected])
- [Get an API key](https://app.tavily.com)
- [Get an API key](https://app.tavily.com)

Search...

Navigation

Overview

Credits & Pricing

[Home](/welcome)[Documentation](/documentation/about)[SDKs](/sdk/python/quick-start)[Examples](/examples/use-cases/data-enrichment)[FAQ](/faq/faq)

- [API Playground](https://app.tavily.com/playground)
- [Community](https://community.tavily.com)
- [Blog](https://blog.tavily.com)

##### Overview

- [About](/documentation/about)
- [Quickstart](/documentation/quickstart)
- [Credits & Pricing](/documentation/api-credits)
- [Rate Limits](/documentation/rate-limits)

##### API Reference

- [Introduction](/documentation/api-reference/introduction)
- [POST

  Tavily Search](/documentation/api-reference/endpoint/search)
- [POST

  Tavily Extract](/documentation/api-reference/endpoint/extract)
- [POST

  Tavily Crawl](/documentation/api-reference/endpoint/crawl)
- [POST

  Tavily Map](/documentation/api-reference/endpoint/map)

##### Best Practices

- [Best Practices for Search](/documentation/best-practices/best-practices-search)
- [Best Practices for Extract](/documentation/best-practices/best-practices-extract)

##### Tavily MCP Server

- [Tavily MCP Server](/documentation/mcp)

##### Integrations

- [LangChain](/documentation/integrations/langchain)
- [LlamaIndex](/documentation/integrations/llamaindex)
- [Zapier](/documentation/integrations/zapier)
- [Dify](/documentation/integrations/dify)
- [Composio](/documentation/integrations/composio)
- [Make](/documentation/integrations/make)
- [Agno](/documentation/integrations/agno)
- [Pydantic AI](/documentation/integrations/pydantic-ai)
- [FlowiseAI](/documentation/integrations/flowise)

##### Legal

- [Security & Compliance](https://trust.tavily.com)
- [Privacy Policy](https://tavily.com/privacy)

##### Help

- [Help Center](https://help.tavily.com)

##### Tavily Search Crawler

- [Tavily Search Crawler](/documentation/search-crawler)

Overview

# Credits & Pricing

Learn how to get and manage your Tavily API Credits.

## [​](#free-api-credits) Free API Credits

[## Get your free API key

You get 1,000 free API Credits every month.
**No credit card required.**](https://app.tavily.com)

## [​](#pricing-overview) Pricing Overview

Tavily operates on a simple, credit-based model:

- **Free**: 1,000 credits/month
- **Pay-as-you-go**: $0.008 per credit (allows you to be charged per credit once your plan's credit limit is reached).
- **Monthly plans**: $0.0075 - $0.005 per credit
- **Enterprise**: Custom pricing and volume

| **Plan** | **Credits per month** | **Monthly price** | **Price per credit** |
| --- | --- | --- | --- |
| **Researcher** | 1,000 | Free | - |
| **Project** | 4,000 | $30 | $0.0075 |
| **Bootstrap** | 15,000 | $100 | $0.0067 |
| **Startup** | 38,000 | $220 | $0.0058 |
| **Growth** | 100,000 | $500 | $0.005 |
| **Pay as you go** | Per usage | $0.008 / Credit | $0.008 |
| **Enterprise** | Custom | Custom | Custom |

Head to [my plan](https://app.tavily.com/account/plan) to explore our different options and manage your plan.

## [​](#api-credits-costs) API Credits Costs

### [​](#tavily-search) Tavily Search

Your [search depth](/api-reference/endpoint/search#body-search-depth) determines the cost of your request.

- **Basic Search (`basic`):**
  Each request costs **1 API credit**.
- **Advanced Search (`advanced`):**
  Each request costs **2 API credits**.

### [​](#tavily-extract) Tavily Extract

The number of successful URL extractions and your [extraction depth](/api-reference/endpoint/extract#body-extract-depth) determines the cost of your request. You never get charged if a URL extraction fails.

- **Basic Extract (`basic`):**
  Every 5 successful URL extractions cost **1 API credit**
- **Advanced Extract (`advanced`):**
  Every 5 successful URL extractions cost **2 API credits**

[Quickstart](/documentation/quickstart)[Rate Limits](/documentation/rate-limits)

[x](https://x.com/tavilyai)[github](https://github.com/tavily-ai)[linkedin](https://linkedin.com/company/tavily)[website](https://tavily.com)

[Powered by Mintlify](https://mintlify.com/preview-request?utm_campaign=poweredBy&utm_medium=docs&utm_source=docs.tavily.com)

On this page

- [Free API Credits](#free-api-credits)
- [Pricing Overview](#pricing-overview)
- [API Credits Costs](#api-credits-costs)
- [Tavily Search](#tavily-search)
- [Tavily Extract](#tavily-extract)
"url": "https://docs.tavily.com/documentation/api-credits"
[2] {}
"favicon": "https://mintlify.s3-us-west-1.amazonaws.com/tavilyai/_generated/favicon/apple-touch-icon.png?v=3"
raw_contentString · text preview
results[2].raw_content
Who are we?
-----------

We're a team of AI researchers and developers passionate about helping you build the next generation of AI assistants. Our mission is to empower individuals and organizations with accurate, unbiased, and factual information.

What is the Tavily Search Engine?
---------------------------------

Building an AI agent that leverages realtime online information is not a simple task. Scraping doesn't scale and requires expertise to refine, current search engine APIs don't provide explicit information to queries but simply potential related articles (which are not always related), and are not very customziable for AI agent needs. This is why we're excited to introduce the first search engine for AI agents - [Tavily](https://app.tavily.com/).

Tavily is a search engine optimized for LLMs, aimed at efficient, quick and persistent search results. Unlike other search APIs such as Serp or Google, Tavily focuses on optimizing search for AI developers and autonomous AI agents. We take care of all the burden of searching, scraping, filtering and extracting the most relevant information from online sources. All in a single API call!

To try the API in action, you can now use our hosted version on our [API Playground](https://app.tavily.com/playground).

Why choose Tavily?
------------------

Tavily shines where others fail, with a Search API optimized for LLMs.

How does the Search API work?
-----------------------------

Traditional search APIs such as Google, Serp and Bing retrieve search results based on a user query. However, the results are sometimes irrelevant to the goal of the search, and return simple URLs and snippets of content which are not always relevant. Because of this, any developer would need to then scrape the sites to extract relevant content, filter irrelevant information, optimize the content to fit LLM context limits, and more. This task is a burden and requires a lot of time and effort to complete. The Tavily Search API takes care of all of this for you in a single API call.

The Tavily Search API aggregates up to 20 sites per a single API call, and uses proprietary AI to score, filter and rank the top most relevant sources and content to your task, query or goal. In addition, Tavily allows developers to add custom fields such as context and limit response tokens to enable the optimal search experience for LLMs.

Tavily can also help your AI agent make better decisions by including a short answer for cross-agent communication.

Getting started
---------------

[Sign up](https://app.tavily.com/) for Tavily to get your API key. You get **1,000 free API Credits every month**. No credit card required.

[Get your free API key --------------------- You get 1,000 free API Credits every month. **No credit card required.**](https://app.tavily.com/)Head to our [API Playground](https://app.tavily.com/playground) to familiarize yourself with our API.

To get started with Tavily's APIs and SDKs using code, head to our [Quickstart Guide](https://docs.tavily.com/guides/quickstart) and follow the steps.
"url": "https://docs.tavily.com/documentation/about"
"usage": {
  "credits": 1
}

Response result

Response structure

Inferred from examples
  • base_urlstring
  • request_idstring
  • response_timenumber
  • resultsobject[]
    • faviconstring
    • raw_contentstring
    • urlstring
  • usageobject
    • creditsinteger

Common questions

Do I need a separate key for every provider?

Use your OpenAny API key for standard API access. Read it from OPENANY_API_KEY in your environment and keep it out of prompts, source code and logs.

Are these providers interchangeable?

No. Each offering has its own inputs, pricing and response contract. Selecting a catalog offering does not establish automatic routing or fallback. Confirm the service contract before calling.

How is this API billed?

API-key calls use your shared balance at the selected implementation's published rate. Check the billing unit and request-specific pricing rules before making a paid call. Recorded usage determines the final charge under that contract.

Where do the price and contract come from?

The selected implementation publishes its provider, request contract, revision and billing rules through OpenAny's public API catalog. A revision number identifies a contract version, not a price update date. A price update timestamp is not supplied; do not treat a page date as one.

How do OpenAny Balance and x402 differ?

OpenAny Balance uses an API key and one shared balance. Card, USDC and x402 top-ups, card auto top-up and USDC subscriptions fund that balance; available routes appear on the Credits page. Direct x402 is a separate pay-per-request flow, available only on listings that show it and requiring an authorized payment client.

Does Playground send a paid request?

Yes. After you sign in, Run sends a real API request using an active OpenAny API key. Charges follow the published API contract and use your shared balance. Selecting an implementation, editing inputs and viewing sample responses do not send requests.

Use Initiate a web crawl from a base URL with your agent

Inspect endpoint contracts and confirm availability and pricing before a paid call.