Connect to Modular Cloud and self-hosted MAX for high-performance LLM inference.
Overview
Modular provides high-performance LLM inference through Modular Cloud and the self-hosted MAX platform. The StackAI Modular integration lets your workflows connect to Modular's OpenAI-compatible API with a single API key, whether you use hosted models on Modular Cloud, a dedicated endpoint, or your own MAX deployment. Connect once and any agent or workflow can call Modular for text generation.
