Why high: an exact fingerprint shared with 2 models that declare the same family, without a second signal of a different kind yet.
Perceptron: Perceptron Mk1 is Perceptron's model. Its measured tokenizer sits with the Qwen group, which is evidence that it builds on the Qwen tokenizer. Tokenizer reuse is normal engineering, open vocabularies travel between labs, and this says nothing against Perceptron's authorship of the model itself.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Counts every one of the 50 test strings exactly like 2 other models | tk_c5c0a8ed |
| How its API is set up | A combination of settings no other listing in the catalogue uses | api_f0a7362d |
| How much it can read and write | Reads up to 32,768 tokens at once, writes up to 8,192 | its own listing |
| Whether it thinks before answering | Reasons when asked to | its own listing |
| Who served our requests | Perceptron | we measured it, 21 August 2026 |
Click a row to open the full comparison.
We sent Perceptron: Perceptron Mk1 fifty short pieces of text and recorded what each one cost it in tokens. The bars below are those costs. Two models built on the same tokenizer produce the same bars; a model built on a different one produces a different set, which is what makes this a fingerprint.
Overhead subtracted: 6 prompt tokens.
Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language queries, and produces detailed visual understanding...
Supported parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningstructured_outputstemperaturetop_ktop_p
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
