Perplexity: Sonar
- by perplexity
- 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...
What the numbers mean
- Context window127,072 tokens
- How much the model can read in one request, counting your prompt, any files and the conversation so far. That is about 95,000 words, or 191 pages.
- Max output114,364 tokens
- The longest single reply it can write: about 86,000 words.
- Input price$1 per million tokens
- What you pay for everything the model reads. A 1,000-word prompt costs less than a cent.
- Output price$1 per million tokens
- What you pay for everything the model writes. Output usually costs more than input. A 500-word answer costs less than a cent.
- Modalitiestext, image in, text out
- The kinds of content it accepts and the kinds it produces. A model that takes images in can read a screenshot; one that only puts text out cannot draw.
Supported parameters
The settings you can pass with a request. A model that lists tools can call functions; one that lists structured_outputs can be held to a JSON schema.
frequency_penaltymax_tokenspresence_penaltytemperaturetop_ktop_pweb_search_options