/updates / Update
Apr 1, 2026 · Llama 3.3 70B on Groq

Llama 3.3 70B free on Groq at ~275 tok/sec. The 1K-request-a-day ceiling stops you running a SaaS on it, but for agent loops, evals, and weekend builds, it's the fastest free 70B on the planet. Go.

Related deal

Llama 3.3 70B
Groq
Free tier: 30 RPM, 1K requests/day, 100K tokens/day
[PERMANENT] [API]
FOREVER

Provider

Groq
Provider
Ultra-fast inference on custom LPU hardware. Runs open-weight models at hundreds of tokens per second.