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

The OpenRouter LLM node sends a text prompt to a curated set of popular language models available through the OpenRouter service and returns the generated text response. It supports models from providers like xAI, DeepSeek, Qwen, Mistral, Z.AI (GLM), Moonshot (Kimi), and Perplexity Sonar, and can optionally include images or videos in the request.

Inputs

ParameterData TypeRequiredRangeDescription
promptSTRINGYesN/AText input to the model.
modelSTRINGYesMultiple options available (see note below)The OpenRouter model used to generate the response.
seedINTYes0 to 2147483647Seed for sampling. Set to 0 to omit. Most models treat this as a hint only. (default: 0)
system_promptSTRINGNoN/AFoundational instructions that dictate the model’s behavior. (default: "")
Note on model parameter: The available model options are dynamically built and may include models with different capabilities. Some models support additional features like reasoning effort, web search, or image/video inputs. The node will validate that the number of images or videos provided does not exceed the model’s maximum supported count. Note on seed parameter: The seed parameter has a “control_after_generate” behavior, meaning it can be set to automatically change (e.g., randomize, increment, or fixed) after each node execution, depending on the user’s widget settings. Note on system_prompt: This parameter is optional and is marked as an advanced parameter in the user interface.

Outputs

Output NameData TypeDescription
outputSTRINGThe generated text response from the OpenRouter model.

Source fingerprint (SHA-256): 24757e36bf2356cc1805a6f071db88ca455e17944695672f19845a4cd1826c8a