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.
Free plan with 3 included agent seats. Team plan: $9.99 per agent per month (monthly) or $7.99 per agent per month (annual billing) for seats 4-50. Enterprise: Custom pricing for more than 50 agent seats.
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
Shared Knowledge - manage and route shared guidance to agents
Governed Skills - publish reusable workflows that agents can use
Portable Memory - carry decisions and context across sessions
Versioned Artifacts - save briefs, files, and deliverables as packages
Agent Monitoring - audit conversations and their context
Agent Messages - pass work and artifacts between agents
Multi-vendor support - manage context across different AI providers
Version control and audit history
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
63% fewer tokens with managed context through selective context and summaries
75% less privacy leakage with governed context governance
Agent-agnostic platform works with ChatGPT, Claude, GitHub Copilot and custom agents
15% higher worker productivity with company-specific context