A private System One Decision AI that runs locally
Stage
Not given
Beta
Founded
Not given
Not given
Based in
US
Not given
Pricing model
usage-based
Not given
Pricing
Starter plan is free with $30/month compute credits. Team plan is $250/month plus compute. Enterprise plan is custom. Compute is billed per second for CPU, GPU, and memory with no charges for idle time.
Not given
Key features
Serve LLMs, image, video, and audio models
Isolated environments for coding agents and RL rollouts
Fine-tune and train models on GPUs
Autoscale compute from zero to thousands of GPUs
Distributed storage for models and weights
Global capacity across 20+ clouds
Serverless functions with HTTPS endpoints
Out-of-the-box observability and logs
Non-autoregressive with no free text generation
Multi-question call support in a single forward pass
Bounded output within supplied candidate set
Calibrated probabilities without temperature fitting
Local inference as a Rust binary executable
Deterministic inference with reproducible results
Support for choice, score, and yes-no decision types
CPU, Apple Metal, and CUDA hardware support
Trainable on your own decisions locally
What makes it different
Custom infrastructure built for AI including container runtime, storage, and scheduler
Sub-second container startup times for GPU workloads
Pay only by the second with no idle charges
Programmatically create millions of concurrent sandboxes