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/perceptron-mk1
- Contexto
- 33k tokens
- Máx. completion
- 8,192
- Tools
- No
- JSON
- Sí
- Lanzamiento
- 2026-05-12
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
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"}]
}'Preguntas frecuentes
- ¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: perceptron/perceptron-mk1.
- ¿Perceptron Mk1 es gratis?
- No. El input cuesta $0.1635 / 1M tokens y el output $1.6351 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Perceptron Mk1?
- Perceptron Mk1 tiene una ventana de 33k tokens. Soporta hasta 8,192 tokens de completion.
- ¿Perceptron Mk1 soporta tool calling y structured outputs?
- Perceptron Mk1 no publica tool calling en este endpoint. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Perceptron Mk1?
- Perceptron Mk1 se lanzó el 12 de mayo de 2026.