Perceptron Mk1.5
Perceptron Mk1.5 is a large language model made by Perceptron, added to the catalog on 25 Sep 2026. It has a context window of 36,864 tokens and costs $0.15 per 1M input tokens and $1.50 per 1M output tokens. It accepts text, images, audio and video and produces text. Typical uses: reasoning over multimodal inputs, interpreting image and video material and producing points, boxes, polygons, and tracks.
Price checked · source: OpenRouter
What Perceptron Mk1.5 is
Perceptron Mk1.5 is Perceptron’s embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and produces text. Its responses can also include optional structured annotations such as points, boxes, polygons, and tracks. Listed capabilities include reasoning, tool use, and structured outputs, so the model can be used in workflows that combine these features with multimodal input and text responses.
The model has a context window of 36,864 tokens and a maximum output of 8,192 tokens. This provides room to include substantial instructions or input material in a request, while keeping the generated response within the stated output limit. The context length may suit tasks involving several related pieces of text or mixed media, although the catalog does not specify how each modality is represented within that limit.
Its supported inputs make it relevant to tasks that combine language with visual or audio material, while optional points, boxes, polygons, and tracks provide structured ways to express spatial or temporal annotations. Tool support can be used in workflows that call tools, and structured-output support is available when responses need an organized format. These capabilities describe the model’s listed interface; the catalog does not specify domain accuracy or particular physical actions.
Key features
- Accepts text, image, video, and audio input
- Produces text with optional structured annotations
- Supports reasoning, tools, and structured outputs
- Has a context window of 36,864 tokens
- Supports outputs of up to 8,192 tokens
Typical uses
- Reasoning over multimodal inputs
- Interpreting image and video material
- Producing points, boxes, polygons, and tracks
- Tool-enabled reasoning workflows
Perceptron Mk1.5 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $0.15 |
| Output, per 1M tokens | $1.50 |
No price change since it was added on 25 Sep 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0050 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0075 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.025 |
Perceptron Mk1.5 specifications
| Model id | perceptron/perceptron-mk1.5 |
|---|---|
| Version | perceptron-mk1.5-20260925 |
| Context window | 36,864 tokensAbout 27,648 English words |
| Max output | 8,192 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 25 Sep 2026 |
| Input types | text, image, video, audio |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Perceptron Mk1.5 yet.
Compare Perceptron Mk1.5
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.