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 responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation. Reasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the `annotation_format` parameter (pass `"point"`, `"box"`, or `"polygon"` for spatial localization on images, or `"clip"` (start/end timestamps) for temporal segments in video). Without `annotation_format`, the model returns natural-language text only.

ChatPerceptron33k tokens$0.1635 / $1.6351 · 1M

perceptron/perceptron-mk1

Context
33k tokens
Completion cap
8,192
Tools
No
JSON
Yes
Released
2026-05-12

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "perceptron/perceptron-mk1",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 responses, either structured or natural language. It excels at video understanding tasks like video QA, summarization, and event detection. On image inputs, it advances point-by-example grounding from multimodal prompts, OCR and document parsing on messy real-world inputs, open vocabulary object detection and counting, and hand pose estimation. Reasoning can be enabled per request to trade latency for deeper analysis on harder tasks. Structured annotations are emitted inline with text only when explicitly requested via the `annotation_format` parameter (pass `"point"`, `"box"`, or `"polygon"` for spatial localization on images, or `"clip"` (start/end timestamps) for temporal segments in video). Without `annotation_format`, the model returns natural-language text only. Perceptron Mk1 runs on the Geek Hub API (OpenAI-compatible). Model id: perceptron/perceptron-mk1.
Is Perceptron Mk1 free?
No. Input is $0.1635 per 1M tokens and output is $1.6351 per 1M tokens on Geek Hub (markup included).
What is the context length of Perceptron Mk1?
Perceptron Mk1 has a 33k tokens context window. It supports up to 8,192 completion tokens.
Does Perceptron Mk1 support tool calling and structured outputs?
Perceptron Mk1 does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Perceptron Mk1 released?
Perceptron Mk1 was released on 2026-05-12.