Side-by-side comparison
Perceptron Mk1 vs Spotlight
| Perceptron Mk1 | Spotlight | |
|---|---|---|
| Provider | Perceptron | Arcee AI |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 32,768 | 131,072 |
| 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 → | 0.1500 | 0.1800 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 1.5000 | 0.1800 |
Frequently asked questions
Which is cheaper, Perceptron Mk1 or Spotlight?
Spotlight is cheaper than Perceptron Mk1 on a 50/50 input/output blend by about $0.645 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, Perceptron Mk1 or Spotlight?
Spotlight has the larger context window at 131k tokens versus 33k tokens for Perceptron Mk1. That means Spotlight can ingest about 4.0x as much text per request.
What is the difference between Perceptron Mk1 and Spotlight?
Perceptron Mk1 comes from Perceptron; Spotlight comes from Arcee AI. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.