Run and fine-tune models. Deploy custom models. All with one line of code.
A private System One Decision AI that runs locally
Stage
Not given
Beta
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
usage-based
Not given
Pricing
Most models billed by time based on hardware used (CPU $0.000100/sec, T4 GPU $0.000225/sec, L40S GPU $0.000975/sec). Some models billed by input/output tokens or generated items. Private custom models billed for all uptime; fast-booting fine-tunes billed only for active processing.
Not given
Key features
Run thousands of community-contributed open-source models
Fine-tune models with custom data to create specialized versions
Deploy custom models using Cog, an open-source packaging tool
Automatic scaling based on demand
Pay only for compute time used
Image generation from text
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
One-line code interface for running models without ML expertise
Automatic infrastructure scaling without manual management
Open-source community with thousands of production-ready models
Fine-tuning capability to customize models for specific tasks