perceptron
Perceptron: Perceptron Mk1.5
perceptron/perceptron-mk1.5
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog entry, Perceptron Mk1.5 (perceptron/perceptron-mk1.5) is an embodied reasoning model intended for physical agents. The catalog lists text, image, video, and audio input with text output, plus optional structured annotations such as points, boxes, polygons, and tracks, a 36,864-token context window, adjustable reasoning effort, and support for tools and structured outputs. No independent model card was available in this source pack, so these capabilities are provider-reported and unverified, with no measured performance data included.[1]
Strengths
- The catalog lists multimodal input (text, image, video, audio) with text output and optional structured spatial annotations including points, boxes, polygons, and tracks.[1]
- Reasoning effort is configurable across high, medium, low, minimal, and none levels, with a default of high, and reasoning is not mandatory.[1]
- The catalog advertises tool calling, structured outputs, and a 36,864-token context window.[1]
Limitations
- The only evidence is the OpenRouter catalog entry; an independent model card was not available in this source pack, so all capability claims are provider-reported.[1]
- No benchmark results or other measured performance data were included, so real-world quality is unknown and requires workload validation.[1]
- The knowledge cutoff is not specified and the catalog description is truncated, leaving some output details undocumented.[1]
Where to use it
- Possibly suited to robotics or embodied-agent pipelines that fuse visual and audio streams, given the listed multimodal inputs; evaluate on representative tasks first.[1]
- A candidate for visual grounding workflows needing machine-readable points, boxes, polygons, or tracks, subject to verification of annotation accuracy.[1]
- May fit agentic applications that combine tool calls with tunable reasoning effort, pending testing of latency and output reliability.[1]
Sources
- [1] OpenRouter catalog · Perceptron: Perceptron Mk1.5Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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
- Model ID
- perceptron/perceptron-mk1.5
- Canonical ID
- perceptron/perceptron-mk1.5-20260925
- Creator
- perceptron
- Added to OpenRouter
- 25.09.2026
- Context length
- 36,864
- Modality
- text+image+audio+video->text
- Input modalities
- text, image, video, audio
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.150 / out $1.5
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | reasoning: optional · default high · efforts: high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: high, medium, low, minimal, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Perceptron | 36,864 | $0.150 | $1.5 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.