Models

The "Models" tab in your ChatNode configuration provides you with the flexibility to choose and manage the different AI models your chatbot can use. 

1. ChatGPT (OpenAI)

• GPT 4-o Mini and GPT 4-o: You can select between the smaller GPT 4-o mini model for more cost-efficient tasks or the larger GPT 4-o model for complex queries.
  
  

2. Gemini (Google)

• Gemini 1.5 Flash Latest and Gemini 1.5 Pro Latest: These are the available Google models, offering different versions for varying needs.
  
  

3. Claude (Anthropic)

• Claude 3 Haiku and Claude 3-5 Sonnet: These are models provided by Anthropic, with options for different levels of response complexity.
  
  

4. Sonar (Perplexity)

• Sonar 3.1 Small and Sonar 3.1 Large: Sonar models focus on more nuanced responses, with small and large options for varied tasks.
  
  

5. ChatGPT (Azure)

• Azure GPT 4-o Mini and Azure GPT 4-o: These models allow you to leverage Microsoft Azure's version of GPT 4. You can choose between the mini version for smaller tasks and the full version for more complex operations.
  
  

6. Enable Monthly Message Limit

• This feature allows you to set a limit on the number of messages your bot can send within a given usage period. The message count is displayed (in this case, 2115).
  
  

7. Enable Rate Limit

• This toggle allows you to control the rate of requests your bot can handle within a specified period. It's useful if you want to prevent overuse or manage resources more effectively.
  
  

Important Reminder

• After making any changes, ensure to click the Save button to apply and confirm your changes.
  
  

Conclusion: The "Models" tab provides a wide array of options to customize your chatbot's functionality by selecting different models based on your use case. You can enable credit usage preferences, and set message or rate limits to better manage performance and costs. This flexibility allows you to fine-tune the bot according to your specific needs.