Parallel Search API
by docs.parallel.ai
AI search and web reading
Added on November 3rd, 2026
Visit docs.parallel.ai →
What it does
The Parallel Search API is web search made for AI agents: describe what you need with a few search queries and get ranked pages with the excerpts that matter, ready for a model's prompt. Requests are JSON POST calls with an x-api-key header. Free with a free API key: $5 in credits every month; paid per request after that. An official MCP server at https://mcp.parallel.ai/mcp lets AI agents search and fetch web pages, without a key at lower rate limits.
At a glance
- API key
- Needed, free · More APIs with a free key
- Pricing
- Free with a free API key: $5 in credits every month; paid per request after that.
- From the browser
- No, call it from a server
- Formats
- JSON
- Interface
- REST, MCP
- Provider
- docs.parallel.ai
More information: https://docs.parallel.ai/search/search-quickstart
Is this your service? Show that it is listed
Put this badge on your website or in your README; it links to this page. About the badge
Example request
curl
curl -X POST 'https://api.parallel.ai/v1/search' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"objective":"Current weather in London","search_queries":["London weather"]}'
JavaScript
const response = await fetch("https://api.parallel.ai/v1/search", {
method: 'POST',
headers: {
"x-api-key": "YOUR_API_KEY",
"Content-Type": "application/json",
},
body: JSON.stringify({"objective":"Current weather in London","search_queries":["London weather"]}),
});
const data = await response.json();
console.log(data);
Python
import requests
response = requests.post(
"https://api.parallel.ai/v1/search",
headers={
"x-api-key": "YOUR_API_KEY",
"Content-Type": "application/json",
},
json={
"objective": "Current weather in London",
"search_queries": [
"London weather",
],
},
timeout=30,
)
print(response.json())
Replace YOUR_API_KEY with your own key. Run the JavaScript on a server, such as Node.js 18 or newer: this API does not accept calls from web pages on other sites.