Pay-as-you-go pricing varying by model and resolution. Example: Happyhorse 1.1 Image to Video at 480p costs 819.97 ₫ per second (special offer ending 10/17/2026); OpenAI Sora 2 Pro at 720p costs 7.950 ₫ per second; Google Veo 3.1 Lite at 720p (no audio) costs 795 ₫ per second.
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
Single gateway to all AI models
Switch models freely without vendor lock-in
App Store for product discovery and distribution
Support for 400+ models
Cost control through pay-as-you-go pricing
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 integration to access any AI model without rebuilding for provider changes
Built-in marketplace for discoverability instead of manual user acquisition
Network effects that increase value for all participants as adoption grows
Operating layer that creates value for ecosystem rather than extracting it
AVIS