Call LLM and VLM from ComfyUI using the OpenAI API standard. Compatible with custom inference servers like Ollama, vLLM or TGI thru their support of their OpenAI API implementation.
https://github.com/hekmon/comfyui-openai-api
git clone https://github.com/hekmon/comfyui-openai-api
comfy node install openai-api