Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.subverseai.com/llms.txt

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

Configure the AI model that powers your agent’s intelligence.

​
LLM Model

Select the language model for your agent:
  • Google [Gemini 2.5 Flash]: Fast, cost-effective, good for most use cases
  • OpenAI [GPT-4o]: Advanced reasoning, best for complex conversations
  • OpenAI [GPT-4o Mini]: Balanced performance and cost
  • Anthropic [Claude]: Excellent for nuanced conversations
Selection Criteria:
  • Speed: Gemini Flash for fastest responses
  • Quality: GPT-4o for highest quality
  • Cost: Mini models for budget-conscious deployments
  • Language Support: Check model language capabilities

​
Temperature

Controls response creativity and randomness (0.0 to 1.0). Settings:
  • 0.0 - 0.3: Deterministic, consistent responses (recommended for customer service)
  • 0.4 - 0.7: Balanced creativity and consistency (recommended for sales)
  • 0.8 - 1.0: Creative, varied responses (use with caution)
Recommended: 0.5 for most use cases
Lower temperature (0.3-0.5) is recommended for customer-facing agents to ensure consistent, reliable responses.