Perceptron: Perceptron Mk1
by PerceptronPerceptron: Perceptron Mk1 is a large language model from Perceptron. It costs $0.150 per million input tokens and $1.50 per million output tokens. Its context window is 33K tokens.
- Input / 1M tokens
- $0.150
- Output / 1M tokens
- $1.50
- Cached input / 1M
- -
- Context window
- 33K
Not supported
tokens
Who serves it cheapest
1 hosts serve Perceptron Mk1. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| PerceptronCheapest | $0.150 | $1.50 | 33K | - | 100.0% |
About Perceptron Mk1
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...
Specifications
| Model ID | perceptron/perceptron-mk1 |
|---|---|
| Provider | Perceptron |
| Context window | 33K tokens |
| Max output | 8K tokens |
| Input modalities | text, image, video |
| Output modalities | text |
| Knowledge cutoff | - |
| Open weights | No |
| Released | May 12, 2026 |
Cheaper alternatives
Models that cost less than Perceptron Mk1 while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does Perceptron: Perceptron Mk1 cost?
$0.150 per million input tokens and $1.50 per million output tokens.
What is the context window of Perceptron: Perceptron Mk1?
33K tokens, with up to 8K tokens of output per request.