80trust / 100
Llm Perplexity
by x402engine.app in Search & web
x402 APIPassing, checked 1 h ago
Search-augmented LLM — answers grounded in real-time web search with citations
POST
https://x402engine.app/api/llm/perplexity- Price
- $0.045
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 294 ms
- 536 ms slowest 5%
- Last check
- Passed
- 1 h ago, next any minute now
Reliability
All checks passedSome failedAll failedNot checked
Status and outage history · Atom feed · Watch with other listings
How to call it
POST https://x402engine.app/api/llm/perplexity
Each call costs $0.045331 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
POST https://x402engine.app/api/llm/perplexity
content-type: application/json
{
"max_tokens": 1024,
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
frequency_penalty | number | No | Model-supported frequency_penalty; see /docs/llm-capabilities.md. |
max_completion_tokens | integer | No | Alias for total output budget; bounded by model maxOutputTokens. |
max_tokens | integer | No | Total output budget, including reasoning. Use this or max_completion_tokens. |
messages | array of object | Yes | Text or model-supported multimodal messages; assistant tool calls may have null content |
presence_penalty | number | No | Model-supported presence_penalty; see /docs/llm-capabilities.md. |
stream | boolean | No | Return live OpenAI-compatible SSE after payment settlement. |
stream_options | object | No | Optional include_usage boolean; usage is always requested upstream. |
temperature | number | No | Model-supported temperature; see /docs/llm-capabilities.md. |
top_k | integer | No | Model-supported top_k; see /docs/llm-capabilities.md. |
top_p | number | No | Model-supported top_p; see /docs/llm-capabilities.md. |
Example response
The listing has no example response.
Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.045331.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://x402engine.app/api/llm/perplexity' \
-H 'content-type: application/json' \
--data-raw '{"max_tokens":1024,"messages":[{"content":"Hello","role":"user"}]}'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://x402engine.app/api/llm/perplexity' \
-H 'content-type: application/json' \
--data-raw '{"max_tokens":1024,"messages":[{"content":"Hello","role":"user"}]}' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.045331 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.045331" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.045331 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402engine.app%2Fapi%2Fllm%2Fperplexity&method=POST
const res = await pay("https://x402engine.app/api/llm/perplexity", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"max_tokens": 1024,
"messages": [
{
"content": "Hello",
"role": "user"
}
]
}),
});
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.045331 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.045331"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.post(
"https://x402engine.app/api/llm/perplexity",
json={
"max_tokens": 1024,
"messages": [
{
"content": "Hello",
"role": "user",
},
],
},
)
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 1 h ago | Passed | 402 | 328 ms | $0.045 |
| 6 h ago | Passed | 402 | 275 ms | $0.045 |
| 10 h ago | Passed | 402 | 294 ms | $0.045 |
| 14 h ago | Passed | 402 | 293 ms | $0.045 |
| 18 h ago | Passed | 402 | 317 ms | $0.045 |
Show 10 older checks
| 23 h ago | Passed | 402 | 417 ms | $0.045 |
| 27 h ago | Passed | 402 | 523 ms | $0.045 |
| 31 h ago | Passed | 402 | 367 ms | $0.045 |
| 35 h ago | Passed | 402 | 306 ms | $0.045 |
| 40 h ago | Passed | 402 | 404 ms | $0.045 |
| 44 h ago | Passed | 402 | 242 ms | $0.045 |
| 2 days ago | Passed | 402 | 378 ms | $0.045 |
| 2 days ago | Passed | 402 | 330 ms | $0.045 |
| 2 days ago | Passed | 402 | 337 ms | $0.045 |
| 2 days ago | Passed | 402 | 288 ms | $0.045 |