Free: 1M context tokens (one-time). Pro: $15/month for 100M tokens/month, $0.18 per extra 1M tokens. Scale: $49/month for 350M tokens/month, $0.15 per extra 1M tokens. 30% off Pro or Scale for the first year for early access teams.
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
Removes duplicate context and off-topic results
Works with any LLM provider
API and SDK integrations
Quality guard checks if kept context is sufficient
Local cleanup of tool output and JSON fields
Fallback to original context on service failure
Per-agent budgets and token limits
Savings report showing cost avoided
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
Reduces input tokens to LLMs by 56–71% on average
Optimizes in milliseconds without slowing requests
Contextwaise