Side-by-side comparison
Sonar vs Perceptron Mk1
| Sonar | Perceptron Mk1 | |
|---|---|---|
| Provider | Perplexity | Perceptron |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 127,072 | 32,768 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision | vision |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 1.0000 | 0.1500 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 1.0000 | 1.5000 |
Frequently asked questions
Which is cheaper, Sonar or Perceptron Mk1?
Perceptron Mk1 is cheaper than Sonar on a 50/50 input/output blend by about $0.175 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Sonar or Perceptron Mk1?
Sonar has the larger context window at 127k tokens versus 33k tokens for Perceptron Mk1. That means Sonar can ingest about 3.9x as much text per request.
What is the difference between Sonar and Perceptron Mk1?
Sonar comes from Perplexity; Perceptron Mk1 comes from Perceptron. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.