← All models
Perplexity · Language model
Sonar
perplexity/sonar- Language
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...
Specifications
- Context window
- 127,072 tokens
- Max output
- 114,364 tokens
- Input
- text, image
- Output
- text
- Tokenizer
- Other
Supported parameters
Accepted by the model and forwarded as-is by the gateway.
- frequency_penalty
- max_tokens
- presence_penalty
- temperature
- top_k
- top_p
Use it
POST /api/v1/chat/completions · MCP chat · full reference
curl https://omnirail.org/api/v1/chat/completions \
-H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
-d '{"model":"perplexity/sonar","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'