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: $0 per month with 100 tool calls per day and 10 new integrations per month. Premium: $50 per month with 1,000 tool calls per day and 100 new integrations per month. Business: contact for pricing with 100,000+ tool calls per day and 1,000+ new integrations per month.
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
Faster and more reliable than browser agents
Self-healing integrations that detect and repair breaks automatically
Build integrations from your coding agent with prompts
Authentication and 2FA handled automatically
No deployment or infrastructure required
Support for legacy portals and internal tools
Integration with any website type
Secure credential storage with PII redaction
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
7x faster performance than browser agents
Self-healing integrations repair automatically when websites change
No API key or credential storage required for basic use
Open source framework
Handles anti-bot measures and rate limiting automatically
Pomerado