Infrastructure to build and run apps, agents, skills and services
Stage
Not given
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Paid
Free
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
CLI for local development and deployment
Apps with offline-capable records that sync across devices
Long-running agents working 24/7
Reusable skills that work across platforms
Hosted and external services integration
Free hosting
Local testing with terminus dev simulator
Background jobs, schedules and webhooks
Support for TypeScript, Rust, Python, Go, C and C++ services
Shared spaces for team collaboration
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
Lego-style composable components that connect together
Free hosting forever for all creations
Unified workflow from local development to published releases
Terminus