Get an API key

Sonar

perplexity/sonar

A chat model with a 127K-token context window, at $0.2625 per million input tokens and $2.625 per million output tokens.

Details

Maker
perplexity
Kind
Chat
Context window
127,000 tokens
Max output
8,000 tokens
Input
$0.2625 per million tokens
Cache write
$0.065625 per million tokens
Output
$2.625 per million tokens
Capabilities
Reasoning, vision, web search
Takes
Text, image
Returns
Text
Zero data retention
Not on every provider
No training on requests
Yes, on every provider
Released
2025-02-19

Description

Perplexity's lightweight offering with search grounding, quicker and cheaper than Sonar Pro.

Call it

curl
curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perplexity/sonar",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a keyCompare with another model