Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

Anthropic Claude is a family of powerful AI models known for strong reasoning, safety, and long-context capabilities. ComfyUI has integrated the Anthropic Claude API through Partner Nodes, allowing you to use Claude directly in your workflows for conversational and image analysis tasks. In this guide, we will walk you through using the Anthropic Claude node in ComfyUI.
To use the API nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the API Nodes Overview section of the documentation to understand the specific requirements for using the API nodes.
Make sure your ComfyUI is updated.Workflows in this guide can be found in the Workflow Templates. If you can’t find them in the template, your ComfyUI may be outdated. (Desktop version’s update will delay sometime)If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Supported Models

ModelStrengths
Opus 4.7Anthropic’s most capable model. Step-change improvement in agentic coding, complex reasoning, and nuanced analysis. 1M context window. Knowledge cutoff: Jan 2026.
Opus 4.6Previous generation flagship with strong all-around performance. 1M context window.
Sonnet 4.6Best balance of speed and intelligence for most workloads. 1M context window. Fast latency.
Sonnet 4.5Fast and capable, good for everyday tasks. 200k context window.
Haiku 4.5Fastest and most cost-effective option for simple queries and high-throughput use cases. 200k context window.
All models support both text-only and multimodal (text + image) inputs with up to 20 images per request.

​
Anthropic Claude Chat Workflow

Run in Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Anthropic Claude” in Template Library
In the corresponding template, we have built a prompt for analyzing and generating role prompts, used to interpret your images into corresponding drawing prompts.
Refer to the numbered steps in the workflow image to complete the basic workflow execution:
  1. In the Load Image node, load the image you need AI to interpret (optional — skip for text-only queries)
  2. In the Anthropic Claude node, modify prompt to set your conversation prompt, or change model to select a different Claude model
  3. (Optional) Set the system_prompt to define the model’s behavioral instructions
  4. Click Run or press Ctrl(cmd) + Enter to execute the conversation
  5. After the API returns results, view the AI response in the Preview Any node

​
Additional Notes

  • Adjust max_tokens (up to 32000) and temperature (0.0 to 1.0) in the node’s advanced options
  • The seed parameter controls whether the node re-runs — results are non-deterministic regardless of seed value