Groq

🌍 International

Groq is known for its custom LPU inference chip, offering the fastest AI inference. Free API supports multiple open-source models, several times faster than GPU solutions.

🎁 Free Tier

Daily Limit: 14400 tokens/min

ModelContextLimitNotes
Llama 3.3 70B 128k 30 RPM Ultra-fast inference, free to use
Mixtral 8x7B 32k 30 RPM MoE architecture, cost-effective

πŸ”‘ API Info

Free Credits: Free tier

Rate Limit: 30 RPM

Free API, fastest inference in the industry (LPU chip)

Visit Website β†’