Pay as you go from $10. Monthly subscriptions: Run $19/month, Run Plus $99/month (5× allowance), Run Max $199/month (10× allowance). Model pricing per million tokens varies: qwen3.8-max $2.00 input/$6.00 output, claude-haiku-5-5 $0.10 input/$0.50 output, claude-sonnet-5 $2.00 input/$10.00 output, cl
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
Zero-retention guarantees with signed cryptographic receipts for every API call
OpenAI-compatible API endpoint
Web-based chat interface with encrypted conversations
Access to 15+ frontier models including Claude, Gemini, Qwen, DeepSeek
Python SDK and R package support
Receipts show token usage, cost, model, provider and retention basis
No data storage on offrec infrastructure
Models run on managed third-party providers
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
Every call returns a cryptographically signed receipt proving zero retention
No need to negotiate zero-retention terms with each provider individually
Unified access to frontier models from multiple labs via single API key
Offrec owns no infrastructure; models run on managed providers
Verifiable accountability through transparent receipt system
offrec