2 Services from groq.mpp.paywithlocus.com

Returns the full list of available AI models on Groq's fast-inference platform, including metadata like context window size, ownership, and active status

Runs ultra-fast LLM chat completions using Groq-hosted models including Llama 3.3, DeepSeek R1, Gemma 2, and Qwen via an OpenAI-compatible API