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.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

​
Overview

Generate text responses from an Anthropic Claude model. This node sends a text prompt and optional images to a Claude model and returns the generated text response.

​
Inputs

ParameterData TypeRequiredRangeDescription
promptSTRINGYesN/AText input to the model. (default: empty string)
modelCOMBOYes"Opus 4.7"
"Opus 4.6"
"Sonnet 4.6"
"Sonnet 4.5"
"Haiku 4.5"		The Claude model used to generate the response.
seedINTYes0 to 2147483647Seed controls whether the node should re-run; results are non-deterministic regardless of seed. (default: 0)
imagesIMAGENo0 to 20 imagesOptional image(s) to use as context for the model. Up to 20 images.
system_promptSTRINGNoN/AFoundational instructions that dictate the model’s behavior. (default: empty string)

​
Parameter Constraints

  • Image Limit: A maximum of 20 images can be provided per request.
  • Temperature Handling: When thinking is enabled or when using the “Opus 4.7” model, the temperature parameter is automatically unset (defaults to 1.0) as required by the Anthropic API. For other models, temperature can be set via the model configuration.
  • Thinking/Reasoning: The model configuration includes a reasoning_effort setting that controls whether thinking is enabled. When enabled, the node automatically configures the appropriate thinking mode (adaptive or budget-based) depending on the selected model.

​
Outputs

Output NameData TypeDescription
outputSTRINGThe generated text response from the Claude model. Returns “Empty response from Claude model.” if no text is generated.
Source fingerprint (SHA-256): e3bab004535d4d406582aa42f28bb64a2988f8331788d51ec1fa4e943d8d4382