perplexity/sonar
127,072 context · $1.00/M input tokens · $1.00/M output tokens
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Bayar sesuai pemakaian
Tanpa biaya di muka, bayar hanya sesuai penggunaan
Gunakan contoh kode berikut untuk integrasi dengan API kami:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="perplexity/sonar",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)perplexity sonar
| Specification | Value |
|---|---|
| Provider | Perplexity |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 127072 tokens |
| Max Output | 4096 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $1.1 |
| Output | $1.1 |
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: perplexity/sonar
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="perplexity/sonar",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "perplexity/sonar",
"messages": [{"role": "user", "content": "Hello!"}]
}'perplexity/sonar
Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...
Input
$1 /M
Output
$1 /M
Konteks
127K
Output Maks.
4K
Vision
Didukung
Akses Sonar melalui API terpadu kami — kompatibel dengan OpenAI, tanpa cold start, harga transparan.
Harga di WaveSpeedAI: $1.00 per juta token input dan $1.00 per juta token output. Prompt caching dan batch processing ditagih terpisah dan mengurangi biaya efektif pada beban kerja yang panjang dan berulang.
Sonar mendukung hingga 127K token konteks dengan hingga 4K token output per permintaan.
Ya. WaveSpeedAI menyediakan Sonar melalui endpoint yang kompatibel dengan OpenAI di https://llm.wavespeed.ai/v1. Arahkan OpenAI SDK resmi ke base URL ini dengan API key WaveSpeedAI Anda — tanpa perubahan kode lainnya.
Masuk ke WaveSpeedAI, buat API key di Access Keys, lalu kirim permintaan ke https://llm.wavespeed.ai/v1/chat/completions dengan model id seperti ditampilkan di atas. Akun baru menerima kredit gratis untuk menguji Sonar.