---
title: Jina
description: URL scraper and web search
---

LLM-friendly URL reader and search client by [Jina AI](https://jina.ai/reader) with a basic free tier.

- package: `@agentic/jina`
- exports: `class JinaClient`, `namespace jina`
- env vars: `JINA_API_KEY`
- [source](https://github.com/transitive-bullshit/agentic/blob/main/packages/jina/src/jina-client.ts)
- [jina api docs](https://jina.ai/reader)

## Install

<CodeGroup>
```bash npm
npm install @agentic/jina
```

```bash yarn
yarn add @agentic/jina
```

```bash pnpm
pnpm add @agentic/jina
```

</CodeGroup>

## Usage

```ts
import { JinaClient } from '@agentic/jina'

const jina = new JinaClient()
const res0 = await jina.readUrl('https://example.com')
const res1 = await jina.search({ query: 'latest news', json: true })
```

## Notes

- Does not support "stream mode".
- Results default to markdown text format.
- To return JSON (especially useful for `search`), set `json: true` in the options.