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 optimized for speed.

ChatPerplexity127k tokens$1.0901 / $1.0901 · 1M

perplexity/sonar

Context
127k tokens
Completion cap
—
Tools
No
JSON
No
Released
2025-01-27

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/sonar",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 optimized for speed. Sonar runs on the Geek Hub API (OpenAI-compatible). Model id: perplexity/sonar.
Is Sonar free?
No. Input is $1.0901 per 1M tokens and output is $1.0901 per 1M tokens on Geek Hub (markup included).
What is the context length of Sonar?
Sonar has a 127k tokens context window.
Does Sonar support tool calling and structured outputs?
Sonar does not advertise tool calling on this endpoint. Structured outputs are not listed for this endpoint.
When was Sonar released?
Sonar was released on 2025-01-27.

More models from Perplexity