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.
Developer plan is free for solo users with up to 5k base traces per month, then pay-as-you-go. Plus plan costs $39/seat/month with 10k base traces included. Enterprise plan offers custom pricing with advanced options.
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
Agent observability with step-by-step tracing
Agent evaluation and scoring
Agent deployment infrastructure
Production monitoring with online evaluations
Autonomous agent improvement with Engine
Secure sandbox execution for agent-generated code
LLM Gateway for model call control
No-code agent builder Fleet
Open source frameworks for agent development
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
Comprehensive platform covering the entire agent development lifecycle from building to monitoring
Open source frameworks with options from quick-start to low-level control
Built-in observability and evaluation capabilities integrated into the platform
Support for long-running autonomous agents with Deep Agents framework