On-demand GPUs and AI model APIs on one prepaid balance
Stage
Established
MVP
Founded
Not given
Not given
Based in
US
Not given
Pricing model
Not given
Paid
Pricing
Not given
GPU rental: $0.15/hr (RTX 2080) to $1.79/hr (H800). Model API calls: Claude Opus 5.5 input $2.00 / output $10.00 per 1M tokens. First top-up of $10 or more earns a $5 bonus.
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 GPU billing with no subscription
OpenAI-compatible API endpoint
2-minute GPU deployment
One-click template deployment
Multiple payment methods
Access to Claude, DeepSeek, Qwen, Llama models
No egress charges
Balance never expires
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
One balance covers both GPU rental and model API calls
Unused GPU minutes return to your balance when you destroy the instance
Designed for developers worldwide without credit card or phone requirements
Consumer GPU cards like RTX 5090 cost less than US cloud providers
CloudGPU