Specialist hardware
Groq
/groq · Mountain View, USA · est. 2016
Data: highVisit provider ↗
Key facts
- Groq is a specialist hardware headquartered in Mountain View, USA, founded 2016.
- Exposes an OpenAI-compatible API, so existing OpenAI SDK code can target it by changing the base URL.
- Blended reference price is $0.69 per 1M tokens (in $0.59 / out $0.79).
- Reference latency 120 ms TTFT at 480 tok/s throughput, with 99.6% reference uptime.
- Editorial reputation index 87/100 from 470 weighted signals; 90-day trend improving.
Specification
- Category
- Specialist hardware
- Headquarters
- Mountain View, USA
- Founded
- 2016
- Model access
- Open weights
- Flagship / served
- LPU-served open models
- Reference open model
- Llama 3.3 70B
- OpenAI-compatible API
- Yes
- Blended $/1M
- $0.69 medium
Strengths & trade-offs
Strength
Category-leading tokens/sec thanks to custom LPU silicon.
Trade-off
Curated, smaller model selection; capacity-gated at peaks.
Profile reviewed 2026-07-10. Confidence for this listing:high — Figure confirmed against the provider's public pricing/docs page on the last_reviewed date.Not affiliated with Groq. ← Back to directory