Venice AIInstall

Overview

The node integrates with Venice AI to provide various AI-powered functionalities including chat completions, image generation and editing, audio text-to-speech conversion, embeddings creation, and model or character listing. Specifically for the Model - List operation, it fetches a list of available AI models filtered by type (e.g., text, image, embedding). This is useful when you want to dynamically retrieve and select from supported AI models in your workflows.

Practical examples:

• Automatically fetching all available text models to present options for a chat completion task.
• Listing image-related models before generating images to choose the best suited model.
• Querying embedding models to ensure compatibility before creating embeddings.

Properties

Output

The output is a JSON array containing the list of models matching the selected type filter. Each item in the array represents a model object as returned by the Venice AI API. The exact structure depends on the API response but typically includes model identifiers and metadata.

Example output JSON structure:

[
  {
    "id": "venice-uncensored",
    "type": "text",
    "name": "Venice Uncensored",
    ...
  },
  {
    "id": "llama-3.3-70b",
    "type": "text",
    "name": "LLaMA 3.3 70B",
    ...
  }
]

No binary data is produced for this operation.

Dependencies

• Requires an active connection to the Venice AI service via an API key credential configured in n8n.
• The node uses HTTP requests to Venice AI endpoints to fetch model information.
• No additional environment variables are explicitly required beyond the API authentication.

Troubleshooting

• Common issues:

  • Network connectivity problems may prevent fetching the model list.
  • Invalid or missing API credentials will cause authentication errors.
  • Selecting an unsupported model type might return empty results.

• Error messages:

  • "Unknown error": Generic catch-all; check network and API key validity.
  • Authentication failures: Verify that the API key credential is correctly set up.
  • "No binary data property ... found": Not applicable for this operation but relevant for image/audio operations.

To resolve errors, ensure the API key is valid, the Venice AI service is reachable, and the selected model type is supported.

Links and References

• Venice AI official documentation (for API details and model info)
• n8n documentation on creating custom nodes and using credentials
• Venice AI API reference for /models endpoint