Cloud sandbox for AI agents with 94% lower cost than most providers
Stage
Established
Not given
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Paid
Pricing
Not given
Standard sandbox: $0.80 per vCPU, $0.70 per GB RAM, $0.09 per GB disk per 730-hour month, metered by the minute. Example: 2 vCPU 4 GB with 4 GB disk costs $4.76/month if running continuously. Idle disk alone costs $0.36/month for 4 GB. VM sandbox costs 2.5x compute rate. New accounts get $5 starter
Key features
GroqMetal: dedicated bare-metal infrastructure tuned for speed and reliability
GroqCore: production-ready inference stack with no infrastructure expertise required
GroqAssured: enterprise-grade governance, auditability, and control
256 LPUs per rack with 40 PB/s SRAM bandwidth
1,000 tokens per second per user throughput
128 GB on-chip SRAM per rack
315 PFLOPS of FP8 inference compute
13 globally distributed data centers across four continents
Per-minute billing for compute, disk storage metered monthly
Persistent file storage with automatic backups
Auto-sleep to pause compute charges when idle
Kernel-enforced isolation via gVisor
Docker container support
Outbound internet access only, firewalled per sandbox
Scheduled runs with cron
Support for multiple AI models and custom keys
Public HTTPS URLs and custom domain support
What makes it different
Fast inference at scale without sacrificing affordability
LPU pioneered technology integrated with NVIDIA GPUs
Fully integrated platform combining infrastructure, inference, and control
94% lower cost than most sandbox providers
No subscription fees, plan fees, or minimum commitments
Compute billing stops when sandbox sleeps or stops
Data never collected for training, SOC 2 Type I compliant