Sold by: Perceptron
One OpenAI-compatible endpoint for Perceptron's full suite: our flagship Mk1 model for video and embodied reasoning, open-weight Isaac models for the edge, and agentic vision APIs. Mk1 matches or exceeds flagship models from other frontier labs.
Overview
One API for Perceptron's Full Model Suite
The Perceptron API serves all of Perceptron's vision-language models through a single OpenAI-compatible interface. One integration covers video understanding, embodied reasoning for robotics, agentic object detection, OCR, multimodal search, and low-latency perception at the edge.
Credits will be allocated to your Perceptron account and can be used across all models available on the Perceptron Platform.
For any questions, please contact: support@perceptron.inc
Core Model Categories
PERCEPTRON MODELS
Perceptron Mk1: Perceptron's highest-quality vision-language model for video and embodied reasoning. It matches or exceeds the performance of flagship models from other frontier labs at an order of magnitude lower cost per token.
- Accepts image and video inputs paired with natural language queries and produces detailed visual understanding responses in either structured or natural language.
- Excels at video QA, summarization, event detection, and video clipping with start/end timestamps.
- On images: 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 when explicitly requested.
- In-context learning: teach new visual concepts with a handful of annotated image or video examples, without fine-tuning.
ISAAC MODELS (OPEN WEIGHTS)
Isaac 0.2 (2B): Best-in-class open-weight 2B vision-language model with reasoning. Sub-200 ms time-to-first-token for fast image understanding.
Isaac 0.2 (1B): Compact 1B vision-language model with reasoning, optimized for edge and low-latency deployments.
Isaac 0.1: Original 2B vision-language model, fully supported for existing integrations.
AGENTIC APIs
Perceptron Agentic Detection: Frontier performance on dense, ambiguous detection tasks.
Describe your detection classes in plain language or with visual examples. An agent coordinates multiple Mk1 calls, zooming in to resolve the small, dense, and ambiguous details that one-shot detectors miss at full-image resolution.
One detection API that generalizes across satellite, drone, robot, vehicle, and wearable imagery.
Perceptron Egocentric Annotation: State-of-the-art, temporally-aligned annotation of human and teleop videos for robot policy training.
Turns raw robot and egocentric video into structured, policy-trainable supervision.
Pass in a video of any task and the agent returns sub-task labels, per-hand action labels, and pose estimation of 21 joints in each hand.
MULTIMODAL PRODUCTS
Multimodal Search: Search image and video libraries with natural language or a reference example.
Every model is served through the same OpenAI-compatible API, with structured outputs (JSON Schema, Pydantic, or regex) and a Python SDK with grounded perception primitives (points, boxes, polygons, and clips).
Perceptron models are used in physical AI applications, including robotics, manufacturing, logistics, retail, security, media, and geospatial.
Resources: https://docs.perceptron.inc
Highlights
- Embodied Reasoning: Enables robotic task planning and robotic data annotation, exceeding the performance of other frontier embodied reasoning models.
- Video & Image Understanding: Long- and short-form video analysis, summarization, and clipping, plus dense open-vocabulary detection of long-tail classes and OCR on messy real-world text, used in manufacturing, logistics, retail, geospatial, and sports.
- One API, Full Suite: A single OpenAI-compatible integration serves every Perceptron product: the flagship Mk1, the open-weight Isaac models for edge deployment, agentic detection, and multimodal search, with structured outputs and in-context learning without fine-tuning.
Details
Sold by
Delivery method
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Pricing is based on the duration and terms of your contract with the vendor. This entitles you to a specified quantity of use for the contract duration. If you choose not to renew or replace your contract before it ends, access to these entitlements will expire.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/month |
|---|---|---|
$100 Credits | $100 worth of tokens for access to all APIs and models on Perceptron Platform, with no expiration date - valid until fully consumed. | $100.00 |
$1,000 Credits | $1,000 worth of tokens for access to all APIs and models on Perceptron Platform, with no expiration date - valid until fully consumed. | $1,000.00 |
$10,000 Credits | $10,000 worth of tokens for access to all APIs and models on Perceptron Platform, with no expiration date - valid until fully consumed. | $10,000.00 |
Dimensions summary
You buy prepaid credits in three fixed amounts: $100, $1,000, or $10,000. Each option works the same way. You purchase a block of credits, then draw down against it as you use the APIs and models on the Perceptron Platform. Credits are consumed as tokens based on your usage. The dimensions differ only in the credit amount you commit upfront, not in what they unlock — each gives access to all APIs and models. Credits carry no expiration date and stay valid until you fully consume them. Larger blocks suit higher expected usage.
Top-of-mind questions for buyers
Credits are drawn down as tokens. Each API request counts input tokens (your prompt, image, or video) and output tokens (the model's response). Both are metered separately at different rates. Your credit balance drops by the token cost of each call until fully consumed.
Two token types combine on each call: input tokens and output tokens. Output tokens carry a higher per-token rate than input tokens. Tasks that generate long responses, like detailed reasoning or captioning, consume credits faster than short detection queries with brief outputs.
Each credit block gives access to all APIs and models on the Perceptron Platform. This includes image, video, and edge-focused models. You are not locked to one model. You draw from the same balance regardless of which model you call.
docs.perceptron.inc
Helpful?
Vendor refund policy
Contact our support team for refund information. (support@perceptron.inc )
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Resources
Vendor resources
Support
Vendor support
We have around the clock support and you can write an email to our support team (support@perceptron.inc ).
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
A multi-layer feedforward artificial neural network
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.