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.
$0.075
$0.075
$0.75
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
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.
On NagaAI, Perceptron Mk1 costs $0.075 per 1M input tokens and $0.75 per 1M output tokens. You pay only for what you use, with no subscription.
Perceptron Mk1 reads up to 32.8k tokens in one request, counting the prompt and the answer together.
Perceptron Mk1 can answer in a JSON schema you give it. Tool calling is not available for it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Not enough throughput data
Not enough TTFT data
Not enough activity data to display a chart
