> ## Documentation Index
> Fetch the complete documentation index at: https://context7.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Search API

> Search all Context7 documentation with one request

The Search API is the simplest way to use Context7. You send a question, and Context7 picks the relevant libraries, searches them, and returns the best snippets in one request. No library ID is needed.

It is a plain GET request, so you can try it in your browser:

[https://context7.com/api/v3/search?query=what+is+nextjs](https://context7.com/api/v3/search?query=what+is+nextjs)

<Note>
  Requests without an API key are for testing only and are rate-limited by IP address. For real use, send your [API key](/docs/howto/api-keys) as a bearer token.
</Note>

## Send a question

<CodeGroup>
  ```bash curl theme={null}
  curl -G "https://context7.com/api/v3/search" \
    -H "Authorization: Bearer CONTEXT7_API_KEY" \
    --data-urlencode "query=How do I stream an OpenAI response from a Next.js route?"
  ```

  ```typescript TypeScript SDK theme={null}
  import { Context7 } from "@upstash/context7-sdk";

  const client = new Context7({ apiKey: process.env.CONTEXT7_API_KEY });

  const result = await client.search(
    "How do I stream an OpenAI response from a Next.js route?"
  );

  for (const snippet of result.codeSnippets) {
    console.log(snippet.libraryId, snippet.codeTitle);
  }
  ```

  ```python Python theme={null}
  import os
  import requests

  response = requests.get(
      "https://context7.com/api/v3/search",
      headers={"Authorization": f"Bearer {os.environ['CONTEXT7_API_KEY']}"},
      params={"query": "How do I stream an OpenAI response from a Next.js route?", "type": "json"},
  )
  response.raise_for_status()

  for snippet in response.json()["codeSnippets"]:
      print(snippet["libraryId"], snippet["codeTitle"])
  ```
</CodeGroup>

The REST endpoint returns plain text by default, ready to add to a prompt. Set `type=json` for structured results. The TypeScript SDK returns JSON by default.

Every snippet includes the library it came from and a link to the source page.

## Add hints

A query is all you need. If you know the library, version, or language, add them to narrow the results:

```bash theme={null}
curl -G "https://context7.com/api/v3/search" \
  -H "Authorization: Bearer CONTEXT7_API_KEY" \
  --data-urlencode "query=How do I stream an OpenAI response from a route handler?" \
  --data-urlencode "library=Next.js" \
  --data-urlencode "library=OpenAI" \
  --data-urlencode "language=TypeScript" \
  --data-urlencode "type=json"
```

| Parameter  | Description                                                                                                                     |
| ---------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `query`    | The question or task. Required.                                                                                                 |
| `library`  | A library name (`next.js`) or Context7 ID (`/vercel/next.js`). Repeat for up to four hints.                                     |
| `version`  | A version such as `15.4.0`. Requires at least one `library`. Strict with one library, a preference with several.                |
| `language` | A programming language to prefer, such as `TypeScript`. It is a preference, so language-neutral documentation can still appear. |
| `type`     | `txt` (default) or `json`.                                                                                                      |

If nothing matches, the API returns `404 no_documentation_found`. Treat it as an empty result.

## Pricing

Search API calls count as regular Context7 API calls. There is no separate price:

* **Free:** 1,000 calls per month.
* **Pro:** 5,000 calls per month per seat, then \$10 per 1,000 calls.

See [Plans & Pricing](/docs/plans-pricing) for details.

## Search API or Context API?

Use the **Search API** for a quick answer: one request, and Context7 picks the libraries and snippets for you. It is the easiest way to integrate Context7 into an agent, for example as a grounding step before the agent writes code.

Use the **Context API** ([Search Library](/docs/api-reference/search/search-for-libraries) and [Get Context](/docs/api-reference/context/get-documentation-context)) when you know exactly which library you want, or when you need to go deep: choose the library, ask follow-up questions, and combine results from several libraries yourself.

## Next steps

* [Search Documentation reference](/docs/api-reference/search/search-documentation) for all parameters and the response schema
* [TypeScript SDK](/docs/sdks/ts/commands/search) for the `search()` method
* [API guide](/docs/api-guide) for authentication, rate limits, and caching