Model provider

Groq

Low-latency inference for popular open-weight language models.

Try in Playground Provider website

Available through one endpoint

2 Groq models

API documentation →

GroqLlama 3.3 70Bllama-3.3-70b-versatile

Fast Llama inference on Groq.

128K context$0.59 / $0.79fastchatcode GroqLlama 3.1 8B Instantllama-3.1-8b-instant

Very low-latency chat and extraction.

128K context$0.05 / $0.08fastlow-cost