Side-by-side comparison
Spotlight vs Sonar
| Spotlight | Sonar | |
|---|---|---|
| Provider | Arcee AI | Perplexity |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 131,072 | 127,072 |
| 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 → | 0.1800 | 1.0000 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 0.1800 | 1.0000 |
Frequently asked questions
Which is cheaper, Spotlight or Sonar?
Spotlight is cheaper than Sonar on a 50/50 input/output blend by about $0.82 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, Spotlight or Sonar?
Spotlight has the larger context window at 131k tokens versus 127k tokens for Sonar. That means Spotlight can ingest about 1.0x as much text per request.
What is the difference between Spotlight and Sonar?
Spotlight comes from Arcee AI; Sonar comes from Perplexity. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.