Mk1 overview
Mk1 specs
- Model ID
perceptron/perceptron-mk1- Developer
- Perceptron
- Context window
- 32,768 tokens
- Max output
- 8,192 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Complex reasoning
Extended reasoning improves reliability on multi-step math, logic, and technical analysis.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Use cases
For manufacturing and industrial work, Mk1 is documented as suited to operational analytics and safety monitoring across factories, construction sites, and warehouses, including detecting product defects, flagging OSHA violations, reading analog instruments, and learning new defect classes from a handful of examples without fine-tuning.
For media and content workflows, Mk1 is documented as suited to semantic visual search, tagging, and policy enforcement at scale, including auto-clipping sports highlights, finding the right shot across film and TV footage, and moderating AI-generated content on social platforms.
For robotics and automation, Mk1 is documented as suited to onboard embodied reasoning for manipulation and navigation, including pointing for grasps, multi-view understanding across cameras, and success detection on task attempts, plus offline curation of teleoperation episodes into structured training data.
For geospatial and critical infrastructure work, Mk1 is documented as suited to satellite, drone, and fixed-camera analysis for utilities, construction, and insurance, including detecting vegetation encroachment on power lines, monitoring oil rig and bridge anomalies, tracking construction progress, and assessing post-disaster damage for claims.
Capabilities
- Function calling
- Reasoning
- Streaming
- Structured outputs
- Web search
Mk1 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.1587 | 1M tokens |
| Output | $1.59 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Mk1 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
| Mk1 | $0.1587 | $1.59 |
 Mk1.5 | $0.1587 | $1.59 |
 Gemini 3.1 Flash Lite Preview | $0.2645 | $1.59 |
 Muse Glimmer 30B | $0.3703 | $1.59 |
 Nemotron 3.5 Super VL | $0.2645 | $1.59 |
How to use the Mk1 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "perceptron/perceptron-mk1",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "perceptron/perceptron-mk1",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "perceptron/perceptron-mk1",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Mk1
Related articles
Mk1 FAQ
What is the context window of Mk1?
Mk1 has a 32,768 tokens context window and can return up to 8,192 tokens.
What inputs and outputs does Mk1 support?
Mk1 takes image, text as input and returns text.
What is the model ID for Mk1?
Use perceptron/perceptron-mk1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does Mk1 cost?
Mk1 costs $0.1587 input and $1.59 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Mk1 support streaming?
Yes, Mk1 can stream responses as they are generated.
Can Mk1 read images?
Yes, Mk1 accepts image input alongside text.
What kinds of tasks is Mk1 suited for?
Mk1 is a chat model that accepts text and image input, supports reasoning, tool calls, structured outputs, and web search.
Does Mk1 support reasoning?
Yes, reasoning is listed as one of Mk1's supported features and capabilities.