Perplexity answer to a prompt, live
dataforseo.x.ai-optimization-perplexity-llm-responses-liveLive Perplexity LLM Responses endpoint allows you to retrieve structured responses from a specific Perplexity AI model, based on the input parameters.
- Price
- $0.005861/callAu prix du fournisseur
- Success rate
- 100 %Last 30 days · 63 380 calls
- Latency p50
- 3.9 sp95 6.9 s
- Last verified
- 28 juil. 2026Verified working
POSThttps://toolswitch.dev/v1/tools/dataforseo.x.ai-optimization-perplexity-llm-responses-live?bodyType=jsonPreview- Uses platform quota
- Synchronous response
- Reads public data
Paramètres
POST body is a JSON array that must contain exactly one task object (Live endpoints do not support multi-task arrays). Extra elements return per-task status 40000 "You can set only one task at a time" ($0 on the rejected tasks) while HTTP stays 200 — one prompt per call.
Cet outil n’a pas de paramètres. Voir la doc du fournisseur ↗
Exemples de code
Remplacez $TOOLSWITCH_KEY par la clé créée dans la console.
curl -X POST 'https://toolswitch.dev/v1/tools/dataforseo.x.ai-optimization-perplexity-llm-responses-live?bodyType=json' \
-H "X-Toolswitch-Key: $TOOLSWITCH_KEY" \
-H "Content-Type: application/json" \
--data-raw '[{"top_p":0.5,"model_name":"sonar","temperature":0.3,"user_prompt":"provide information on how relevant the amusement park business is in France now","message_chain":[{"role":"user","message":"Hello, what’s up?"},{"role":"ai","message":"Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?"}],"system_message":"communicate as if we are in a business meeting","max_output_tokens":200,"web_search_country_iso_code":"FR"}]'import os
import json
import requests
response = requests.request(
"POST",
"https://toolswitch.dev/v1/tools/dataforseo.x.ai-optimization-perplexity-llm-responses-live?bodyType=json",
headers={"X-Toolswitch-Key": os.environ["TOOLSWITCH_KEY"]},
json=json.loads("[{\"top_p\":0.5,\"model_name\":\"sonar\",\"temperature\":0.3,\"user_prompt\":\"provide information on how relevant the amusement park business is in France now\",\"message_chain\":[{\"role\":\"user\",\"message\":\"Hello, what’s up?\"},{\"role\":\"ai\",\"message\":\"Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?\"}],\"system_message\":\"communicate as if we are in a business meeting\",\"max_output_tokens\":200,\"web_search_country_iso_code\":\"FR\"}]"),
)
response.raise_for_status()
print(response.text)const response = await fetch("https://toolswitch.dev/v1/tools/dataforseo.x.ai-optimization-perplexity-llm-responses-live?bodyType=json", {
method: "POST",
headers: {
"X-Toolswitch-Key": process.env.TOOLSWITCH_KEY ?? "",
"Content-Type": "application/json",
},
body: JSON.stringify(JSON.parse("[{\"top_p\":0.5,\"model_name\":\"sonar\",\"temperature\":0.3,\"user_prompt\":\"provide information on how relevant the amusement park business is in France now\",\"message_chain\":[{\"role\":\"user\",\"message\":\"Hello, what’s up?\"},{\"role\":\"ai\",\"message\":\"Hello! I’m doing well, thank you. How can I assist you today? Are there any specific topics or projects you’d like to discuss in our meeting?\"}],\"system_message\":\"communicate as if we are in a business meeting\",\"max_output_tokens\":200,\"web_search_country_iso_code\":\"FR\"}]")),
});
if (!response.ok) throw new Error(`Request failed: ${response.status}`);
console.log(await response.text());Cette API de passerelle est en préversion ; son URL et son authentification peuvent changer. Les paramètres de l’exemple sont des données fictives. Les appels sont facturés à $0.005861/call, frais de service inclus.