> ## Documentation Index > Fetch the complete documentation index at: https://docs.parallel.ai/llms.txt > Use this file to discover all available pages before exploring further. # Place Search API Quickstart > Find restaurants, shops, museums and other places near a location with the Parallel Place Search API For AI agents: a documentation index is available at [https://docs.parallel.ai/llms.txt](https://docs.parallel.ai/llms.txt). The full text of all docs is at [https://docs.parallel.ai/llms-full.txt](https://docs.parallel.ai/llms-full.txt). You may also fetch any page as Markdown by appending `.md` to its URL or sending `Accept: text/markdown`. For Search and Extract, use `/v1/search` and `/v1/extract` for all new integrations and agent tool calls. Use `/v1beta/search` and `/v1beta/extract` only when maintaining an existing integration that already uses them. The request bodies changed too: on `/v1/extract`, `full_content`, `fetch_policy` and `excerpt_settings` go inside `advanced_settings`, and sending the v1beta top-level `excerpts`, `full_content` and `fetch_policy` to `/v1/extract` returns a 422. Do not substitute `/v1` for the documented FindAll or Ingest endpoint paths. The **Place Search API** finds places of interest matching a query in or near a location. Results include the address, phone number, coordinates, distance from the search center, price level, weekly opening hours, and a rating tier. Use Place Search when an agent or application needs to find, compare or recommend local businesses and points of interest: "coffee near Union Square", "24 hour pharmacy in 94110", or "museums in Cambridge, UK that are open now". ## 1. Set Up Prerequisites Generate your API key on [Platform](https://platform.parallel.ai), then export it: ```bash theme={"system"} export PARALLEL_API_KEY="PARALLEL_API_KEY" ``` The Python example below uses `requests` (`pip install requests`). ## 2. Execute Your First Place Search Send what to find as `query` and where to look as `location`: one city, neighborhood, address, or postal code per request. To search around a point instead, send `latitude` and `longitude`. ### Sample Request ```bash cURL theme={"system"} curl https://api.parallel.ai/v1/places/search \ -H "Content-Type: application/json" \ -H "x-api-key: $PARALLEL_API_KEY" \ -d '{ "query": "tacos", "location": "Mission District, San Francisco", "max_results": 5 }' ``` ```python Python theme={"system"} import os import requests response = requests.post( "https://api.parallel.ai/v1/places/search", headers={"x-api-key": os.environ["PARALLEL_API_KEY"]}, json={ "query": "tacos", "location": "Mission District, San Francisco", "max_results": 5, }, timeout=60, ) response.raise_for_status() for place in response.json()["results"]: rating = f" ({place['rating']})" if "rating" in place else "" url = place.get("url", "no link") print(f"{place['name']}{rating}: {url}") if "address" in place: print(f" {place['address']}") ``` ```typescript TypeScript theme={"system"} async function main() { const response = await fetch("https://api.parallel.ai/v1/places/search", { method: "POST", headers: { "Content-Type": "application/json", "x-api-key": process.env.PARALLEL_API_KEY!, }, body: JSON.stringify({ query: "tacos", location: "Mission District, San Francisco", max_results: 5, }), }); if (!response.ok) { throw new Error(`Place Search failed: ${response.status} ${await response.text()}`); } const { results } = await response.json(); for (const place of results) { const rating = place.rating ? ` (${place.rating})` : ""; console.log(`${place.name}${rating}: ${place.url ?? "no link"}`); if (place.address) console.log(` ${place.address}`); } } main().catch(console.error); ``` > [!TIP] > > This request uses the default `advanced` mode. Add `"mode": "fast"` for the lowest latency > and cost. See [Place Search Modes](https://docs.parallel.ai/place-search/modes.md). ### Request Options * `open_now`: only places open at request time, in each place's own time zone. Places with unknown hours are left out. * `max_distance_km`: only places within this distance of the search center. * `max_results`: up to 20 (default 10). * `mode`: `advanced` (default) or `fast`. Without `max_distance_km`, the search radius fits the location, up to 25 km. See [Best Practices](https://docs.parallel.ai/place-search/best-practices.md) for every request field. ### Sample Response The API returns a JSON response with the following structure. The `results` array below is shortened to one place. Fields that are not known for a place, such as its rating, are left out. ```json theme={"system"} { "search_id": "search_e3584cbd6545a489f43cff43737d52cc", "session_id": "session_e3584cbd6545a489f43cff43737d52cc", "results": [ { "url": "https://www.laoaxaquenaca.com/", "name": "La Oaxaqueña", "address": "2128 Mission St, San Francisco, CA 94110", "phone": "(415) 714-9119", "latitude": 37.7629157, "longitude": -122.4197557, "distance_km": 0.22, "rating": "excellent", "opening_hours": { "monday": [{"opens": "11:00", "closes": "02:30"}], "tuesday": [{"opens": "11:00", "closes": "02:30"}], "wednesday": [{"opens": "11:00", "closes": "02:30"}], "thursday": [{"opens": "11:00", "closes": "02:30"}], "friday": [{"opens": "11:00", "closes": "02:30"}], "saturday": [{"opens": "11:00", "closes": "02:30"}], "sunday": [{"opens": "11:00", "closes": "02:30"}] }, "timezone": "America/Los_Angeles", "open_now": true } ], "usage": [{"name": "sku_search", "count": 1}] } ``` ## Next Steps * **[Best Practices](https://docs.parallel.ai/place-search/best-practices.md)**: every request field, and how to write queries and locations * **[Place Search Modes](https://docs.parallel.ai/place-search/modes.md)**: choose between `fast` and `advanced` * **[Pricing](https://docs.parallel.ai/getting-started/pricing.md#place-search-api)**: per-request cost for each mode * **[Rate Limits](https://docs.parallel.ai/getting-started/rate-limits.md)**: default quotas per product