Author's Description
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...
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Perceptron Mk1 demonstrates competitive response times, performing among the fastest models with a 50th percentile speed ranking across seven benchmarks. It also offers cost-effective solutions, ranking in the 68th percentile for price. A standout feature is its exceptional reliability, boasting a 99% success rate, indicating minimal technical failures and consistent evaluable responses. In terms of specific performance, Perceptron Mk1 excels in Instruction Following, achieving 87.1% accuracy and ranking #1 in speed for this category. It also performs strongly in Email Classification (97.8% accuracy). However, the model shows notable weaknesses in General Knowledge (84.3% accuracy, 22nd percentile) and Coding (76.0% accuracy, 31st percentile). Its ability to acknowledge uncertainty in the Hallucinations benchmark is moderate at 87.8% accuracy. While its Reasoning accuracy is average (69.8%), its Ethics performance, at 96.7% accuracy, is solid despite a lower percentile ranking.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.15 |
| Completion | $1.5 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Perceptron
|
Perceptron | perceptron/perceptron-mk1-20260512 | 32K | $0.15 / 1M tokens | $1.5 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by perceptron
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Perceptron: Perceptron Mk1 | May 12, 2026 | — | 32K |
Image input
Text input
Video input
Text output
|
★★★ | ★★★ | $$$ |