Starter plan free with $10 credits monthly, 1 GB processed data, 10k scores, 14-day retention. Pro plan $249/month with $100 credits, 5 GB processed data, 50k scores, 30-day retention. Enterprise with custom pricing. Overage charges at $4/GB for Starter and $3/GB for Pro on processed data.
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
Real-time trace inspection
LLM scoring and evaluation
Production monitoring dashboards
Automated pattern detection
Dataset versioning and management
Prompt optimization with Loop agent
Natural language trace investigation
Custom annotation interfaces
Gateway API for unified access
Brainstore database for AI data
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
Built specifically for agents which fail differently than normal software
Automatic pattern discovery from production data
Framework agnostic with no vendor lock-in
Enterprise security with SOC 2 Type II and HIPAA compliance
Brainstore query engine for faster production debugging