# Firecrawl Web Search API

> Searches the web using a text query and returns relevant pages with their titles, descriptions, and source URLs. Supports adjusting result counts.

Source: https://www.sandbase.ai/apis/firecrawl/search
API reference: https://www.sandbase.ai/apis/firecrawl/search/docs

## Facts

- Provider: Firecrawl
- Type: Data API
- Endpoint: `POST https://api.sandbase.ai/v1/api/firecrawl/search`
- Price: $0.01 per call
- Capabilities: web search, search
- Billing: pay per use from one SandBase balance; no provider account or subscription needed

## Call it

`POST https://api.sandbase.ai/v1/api/firecrawl/search` with `Authorization: Bearer $SANDBASE_API_KEY` and the parameters as a JSON body.

| Parameter | Type | Required | Allowed values |
| --- | --- | --- | --- |
| `query` | string | yes |  |
| `limit` | integer | no |  |

## FAQ

### How do I use the Firecrawl Web Search API?

Send a POST request to https://api.sandbase.ai/v1/api/firecrawl/search with your SandBase API key in the Authorization header (Bearer) and the parameters as a JSON body. You can also try it in the Playground on this page without writing code.

### How much does the Firecrawl Web Search API cost?

$0.01 per call, billed from your SandBase balance. You are only charged for calls you make; there is no subscription.

### What parameters does the Firecrawl Web Search API accept?

Required: query (string). Optional: limit (integer). The Parameters table and the Playground on this page list every field.

### What does the Firecrawl Web Search API return?

A JSON response returned in the same HTTP request (synchronous). The README on this page includes a sample response.

### Do I need a Firecrawl developer account or API key?

No. Firecrawl Web Search runs through SandBase, so one SandBase API key covers this endpoint and every other API and model in the catalog. You do not need to apply for Firecrawl API access separately.

## README

### Firecrawl Web Search API

Look up web search results using `query`. You can optionally restrict the total number of items returned using `limit`.

#### Use cases

- Retrieve relevant web page URLs and snippets for research queries.
- Gather search results to feed context into automated LLM pipelines.
- Find source URLs and page metadata for specific search terms.

#### Request

```bash
curl -X POST "https://api.sandbase.ai/v1/api/firecrawl/search" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"query": "OpenAI"}'
```

#### Parameters

| Name | Type | Required | Description |
|---|---|---|---|
| `query` | string | Yes | The search query. |
| `limit` | integer | No | Maximum number of results to return. |

#### Example response

Real response for the request above, trimmed to the main fields. User names and long IDs are masked.

```json
{
  "web": [
    {
      "description": "OpenAI | Research & Deployment  ## Latest research [An OpenAI model proposes a solution t…",
      "title": "OpenAI | Research & Deployment",
      "url": "https://openai.com/"
    }
  ]
}
```

#### Notes

- Specify `query` to set the search terms.
- Use `limit` to configure the maximum number of results to return.