Hormouz AIHormouzSign in

Perceptron: Perceptron Mk1: AI model

Perceptron Mk1 is a vision-language model for image and video reasoning, strong at video QA, OCR and object detection. Reachable from inside Iran through Hormouz.

Context window:
32,768 tokens
Input:
$0.15/1M tokens
Output:
$1.5/1M tokens
Type:
text, image, video
  • Vision
  • Streaming

Thinking levels:

Perceptron Mk1 is Perceptron’s high-quality vision-language model for video and embodied reasoning. It accepts image and video inputs alongside natural-language queries and produces visual-understanding responses, either structured or in natural language.

The model is strong at video-understanding tasks such as video QA, summarization and event detection, and on images it handles OCR, document parsing, open-vocabulary object detection and counting, and point-based grounding. Reasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Its context window is up to 32K tokens, and access runs through Hormouz behind an OpenAI-compatible API.

Pricing is usage-based: $0.15 per million input tokens and $1.50 per million output tokens. Hormouz provides stable access to the model from inside Iran.

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...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perceptron/perceptron-mk1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorPerceptron
TypeText, Image, Video
Context window32,768 tokens
Pricing$0.15/M in · $1.50/M out
APIChat Completions
CapabilitiesStreaming · Vision

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perceptron/perceptron-mk1",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="perceptron/perceptron-mk1",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "perceptron/perceptron-mk1",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Perceptron: Perceptron Mk1 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Perceptron: Perceptron Mk1 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Perceptron Mk1 cost?
Billing is usage-based: $0.15 per million input tokens and $1.50 per million output tokens.
How do I access Perceptron Mk1 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Perceptron Mk1 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What inputs does Perceptron Mk1 accept?
It accepts image and video inputs alongside natural-language queries, and is suited to video QA, OCR, document parsing and object detection.
Does Perceptron Mk1 support reasoning?
Yes. Reasoning can be enabled per request for deeper analysis on harder tasks; its context window is up to 32K tokens.

Updated 2026-10-13