Perceptron Mk1 vs Perceptron Mk1.5
Perceptron Mk1 (Perceptron) and Perceptron Mk1.5 (Perceptron) have the same list price: $0.15 per 1M input tokens and $1.50 per 1M output tokens. Perceptron Mk1.5 has the larger context window, 36,864 tokens against 32,768 for Perceptron Mk1. Only Perceptron Mk1.5 supports tool calling. Perceptron Mk1 accepts text, images and video and produces text; Perceptron Mk1.5 accepts text, images, audio and video and produces text.
Perceptron Mk1 and Perceptron Mk1.5 both accept text, images, and video, produce text, and support reasoning and structured outputs. Mk1.5 also accepts audio and supports tools; their context lengths are 36,864 and 32,768 tokens, respectively.
Compared from catalog data checked
Side by side
0.00 the better figure in a row| Specification | Perceptron Mk1 | Perceptron Mk1.5 |
|---|---|---|
| Maker | Perceptron | Perceptron |
| Added to catalog | 12 May 2026 | 25 Sep 2026 |
| Input, per 1M tokens | $0.15 | $0.15 |
| Output, per 1M tokens | $1.50 | $1.50 |
| Context windowTokens | 32,768 | 36,864 |
| Max outputTokens | 8,192 | 8,192 |
| Accepts | image, text, video | audio, image, text, video |
| Produces | text | text |
| Tool calling | No | Yes |
| Structured outputs | Yes | Yes |
| Reasoning effort control | No | Yes |
List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.
What the same task costs
List price for one request, from the token counts shown. The same four tasks are priced on every model page.
| Task | Perceptron Mk1 | Perceptron Mk1.5 |
|---|---|---|
| Answer a short question500 in / 300 out | $0.0005 | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0050 | $0.0050 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0075 | $0.0075 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.025 | $0.025 |
Which to choose
Choose Perceptron Mk1 if
No row of the table favours Perceptron Mk1. The difference, if there is one, is in the answers it writes: try it on your own task.
Perceptron Mk1 detailsChoose Perceptron Mk1.5 if
- You need the larger context window: 36,864 tokens against 32,768
- It has to read audio, which the other model does not
- You need tool calling
- You want to set how much it reasons before it answers
Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.