Overview
ComfyUI Partner Nodes give you access to large language models (LLMs) from leading providers. These nodes take text and images as input and return text, which makes them useful for prompt writing, image captioning, and conversation alongside your generation nodes.Browse LLM partners
Claude
Strong reasoning and instruction following from Anthropic
Gemini
Multimodal reasoning that interprets images and returns rich text prompts
OpenAI Chat
Chat models with strong general-purpose reasoning and image understanding
OpenRouter LLM
Access many different LLM providers through a single integration
What you can do with LLMs
- Prompt writing: Generate or refine prompts for your image, video, and 3D workflows
- Image captioning & understanding: Describe images or answer questions about their content
- Conversation: Chat with a multimodal model inside your workflow
- Agentic tasks: Break down, plan, and orchestrate generation steps across nodes
Choosing a model by provider
- Claude (Anthropic) — strong reasoning and instruction following; excellent at structured prompt engineering
- Google Gemini (Google) — multimodal reasoning that interprets images and returns rich text prompts
- OpenAI Chat (OpenAI) — chat models with strong general-purpose reasoning and image understanding
- OpenRouter LLM (OpenRouter) — access many different LLM providers through a single integration
All LLM partners
See Pricing for per-model rates, and Concurrency Limits for usage caps.