Perceptron API
Access Perceptron instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "perceptron/perceptron-mk1"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "perceptron/perceptron-mk1"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Perceptron Models
Perceptron Mk1.5
perceptron/perceptron-mk1.5
Perceptron Mk1.5 is Perceptron AI's embodied-reasoning model for physical agents, accepting text, image, video, and audio input and returning text alongside points, boxes, polygons, video clips, and object tracks, all from one model with no per-platform retraining. It leads on three of four video object segmentation benchmarks (Molmo2-Track, Ref-DAVIS17, ReasonVOS) and localizes hands in first-person video 50% better than Gemini's strongest model. With tool calling and web search enabled, it improves 36.1 points on MMSearch, and it runs 2-5x faster end to end than Mk1. At $0.15 per million input tokens and $1.50 per million output tokens, Mk1.5 suits developers building drone, quadruped, smart-glasses, or robotics pipelines that need spatial outputs and native audio understanding alongside text.
ChatPerceptron Mk1
perceptron/perceptron-mk1
Perceptron Mk1 is a vision-language model from Perceptron AI designed for video and embodied reasoning, capable of processing native video at up to 2 frames per second within its 32K context window. It excels at video QA, video summarization, event detection, open-vocabulary object detection and counting, OCR on real-world documents, hand pose estimation, and point-by-example grounding from multimodal prompts. On spatial reasoning benchmarks, Mk1 scores 85.1 on EmbSpatialBench and 72.4 on RefSpatialBench, outperforming frontier models. On VSI-Bench it reaches 88.5, the highest recorded score among compared models. At $0.15 per million input tokens, Mk1 is priced 80–90% below comparable frontier vision-language models, making it a strong choice for developers building video analysis, robotics data curation, or multimodal pipelines at scale.
Frequently Asked Questions
The Perceptron API gives you access to models for AI chat. Through Puter.js, you can start using Perceptron models instantly with zero setup or configuration.
Puter.js supports a variety of Perceptron models, including Perceptron Mk1.5 and Perceptron Mk1. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the Perceptron API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.