← All models
Perplexity: Perplexity Sonar
perplexity/sonarsearch
Perplexity model with native web search — answers from fresh internet data with citations.
Price in / out
Context / Max output
127K / 114K
Released
Jan 27, 2025
Additional rates
Search · every request
Parameters
messagesrequiredmax_tokensoptional · alias max_completion_tokensstreamtrue · falseproviderrouting: order · only · ignore · sortstream_options{"include_usage": true}Fine-tuning · 5
temperature0–2top_p0–1top_koptionalfrequency_penalty−2…2presence_penalty−2…2How to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
model="perplexity/sonar",
messages=[{"role": "user", "content": "Привет"}],
temperature=0.7,
max_tokens=1024,
stream=False,
)
print(resp.choices[0].message.content)
# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
model="perplexity/sonar",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)