RentGPU RentGPU
Find a GPU →
by Perceptron

Perceptron: Perceptron Mk1.5.

multimodal closed 37K ctx
Cheapest input
$0.15/M
on OpenRouter
Cheapest output
$1.5/M
on OpenRouter
Hosted equiv.
~$0.54/hr
@ 100 tok/s on OpenRouter

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,.

Hosted API only

No self-host path — closed weights.

Perceptron: Perceptron Mk1.5's weights aren't published. Use it via the access providers below.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
OpenRouter api aggregator $0.15 $1.5 Launch ↗
FAQ

Frequently asked.

How do I run Perceptron: Perceptron Mk1.5?
Perceptron: Perceptron Mk1.5 is a closed-source API model. The cheapest way to access it is through the API providers listed on this page (direct API, aggregators, and hosted chat UIs).
Where can I access Perceptron: Perceptron Mk1.5?
Perceptron: Perceptron Mk1.5 is available via OpenRouter. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Perceptron: Perceptron Mk1.5?
API pricing starts at $0.15/M input tokens and $1.5/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Perceptron: Perceptron Mk1.5 open-source or proprietary?
Perceptron: Perceptron Mk1.5 is a proprietary model from Perceptron. Access is API-only — there are no public weights to download.