RentGPU RentGPU
Trouver un GPU →
by Perceptron

Perceptron: Perceptron Mk1.

multimodal open weights 33K ctx
Cheapest input
$0.15/M
on OpenRouter
Cheapest output
$1.5/M
on OpenRouter
Fastest
36 tok/s
on OpenRouter
Hosted equiv.
~$0.54/hr
@ 100 tok/s on OpenRouter

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 und

Where to use it

Cheapest hosted endpoints.

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

Speed across providers.

Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.

Provider Tokens/sec TTFT Total
OpenRouter 36.0 1094 ms 3698 ms
FAQ

Frequently asked.

How do I run Perceptron: Perceptron Mk1?
Perceptron: Perceptron Mk1 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Perceptron: Perceptron Mk1?
Perceptron: Perceptron Mk1 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?
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 open-source or proprietary?
Perceptron: Perceptron Mk1 is open-weight under the license. You can download and self-host it.