Llama 3.1 70B (Groq LPU)

This model is not part of the weekly automatic sync. The figures below were confirmed on 2026-08-13.

Groq LPU Serving Llama 3.1 70B. Real-time latency optimization

Llama 3.1 70B (Groq LPU) — Groq. Context window 131,072 tokens. API pricing (per 1M tokens): Input $0.59, Output $0.79. License: Open-Weight.

Benchmarks · API pricing (per 1M tokens)

ProviderGroq
TierMid
Context window131,072 tokens
Max output8,192 tokens
LicenseOpen-Weight
API pricing (per 1M tokens) · Input$0.59
API pricing (per 1M tokens) · Output$0.79
Compare in the full catalog