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
Search for web pages, images, and news
Crawl pages into Markdown, HTML, links, and screenshots
Map discovery using website sitemaps
Extract structured JSON from pages
Index with scheduled refreshes and retrieval
TypeScript and Python SDKs
Model Context Protocol (MCP) integration
REST API for all capabilities
CLI for terminal and script access
Private GitHub repository indexing
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
Maintains indexed knowledge with automatic scheduled refreshes
Provides source references for verifiable answers
Supports both public and private knowledge sources
Bulkgrid