Agent Serve currently tracks 10 Groq models including OpenAI GPT OSS 120B, OpenAI GPT OSS 20B, OpenAI GPT OSS Safeguard 20B, Qwen 3 32B, Qwen 3 8 27B, Qwen 3 6 27B, and more.
Llama 3.3 70B Versatile is the default Groq model in Agent Serve.
Llama 3.1 8B Instant currently has the lowest listed input price at $0.05/1M tokens.
Moonshot AI Kimi K2 Instruct 0905 currently has the largest listed context window at 262k tokens.
All Groq models in Agent Serve support tool use and function calling, allowing agents to invoke external APIs, query databases, and run custom actions.
