Skip to main content
ComfyUI Partner Nodes give you access to hosted large language models (LLMs) from providers such as Anthropic, Google, OpenAI, and OpenRouter. These nodes take text and images as input and return text, so you can use them for prompt writing, image captioning, and conversation alongside your generation nodes. This page helps you pick the right model for each task.

​
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.