> ## Documentation Index
> Fetch the complete documentation index at: https://docs.perceptron.inc/llms.txt
> Use this file to discover all available pages before exploring further.

# Models

> Vision-language models from Perceptron.

Perceptron's vision-language models accept image and video input alongside natural-language queries. Pick the model that fits your latency, accuracy, and modality needs.

**Perceptron Mk1** (short for "Mark 1") is our flagship closed-source model. The **Isaac** series ships with open weights on Hugging Face for self-hosting.

| Model                  | Best for                                                | Speed    | Latest update | Details                                        |
| ---------------------- | ------------------------------------------------------- | -------- | ------------- | ---------------------------------------------- |
| `perceptron-mk1`       | Image & Video, reasoning enabled                        | Standard | 2026-05-12    | [Spec](/perceptron-mk1/models/perceptron-mk1)  |
| `isaac-0.2-2b-preview` | Image, reasoning enabled                                | Fast     | 2025-12-10    | [Spec](/isaac-0.2/models/isaac-0.2-2b-preview) |
| `isaac-0.2-1b`         | Image, reasoning enabled, low-latency / edge deployment | Fastest  | 2025-12-10    | [Spec](/isaac-0.2/models/isaac-0.2-1b)         |
| `isaac-0.1`            | Images (legacy support)                                 | Fast     | 2025-09-17    | [Spec](/isaac-0.1/models/isaac-0.1)            |