The Orchestrator › Models › Perceptron
Perceptron: Perceptron Mk1.5
Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...
Specifications
| Provider | Perceptron |
| Model ID | perceptron/perceptron-mk1.5 |
| Context window | 37K tokens (36,864) |
| Modalities | text + image + audio + video → text |
| Tokenizer | Other |
| Router sources | OpenRouter |
| Released | 2026-09-25 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Supported |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | perceptron/perceptron-mk1.5 | $0.15 | $1.50 | 37K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.15 | $1.50 | 37K |
Capabilities
Vision (image input)Audio inputVideo inputAgentic tool useStructured outputsControllable reasoning
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, reasoning_effort, structured_outputs, temperature, tool_choice, tools, top_k, top_p