Skip to main content

​
Overview

OpenAI Endpoint connections integrate with any OpenAI-compatible chat completions API, enabling text-based conversational testing.

​
Configuration Requirements

​
Chat Endpoint

  • Field: chat_endpoint
  • Type: String (required)
  • Purpose: URL endpoint for OpenAI-compatible chat completions API
  • Format: Valid HTTPS URL
  • Example: https://api.openai.com/v1/chat/completions

​
Authentication Token

  • Field: auth_token
  • Type: String (required)
  • Purpose: API key or authentication token for the endpoint
  • Format: String (maximum 4KB length)
  • Security: Sensitive field - stored encrypted
  • Example: sk-proj-abc123def456...

​
Model

  • Field: model
  • Type: String (optional)
  • Default: "gpt-4o"
  • Purpose: Specify which OpenAI model to use for completions
Available Models:
  • GPT-5 Series: gpt-5, gpt-5-mini, gpt-5-nano, gpt-5-chat
  • GPT-4.1 Family: gpt-4.1, gpt-4.1-mini, gpt-4.1-nano
  • Reasoning Models: o1, o1-mini, o1-pro, o3-mini, o3-pro, o3, o4-mini
  • Current Generation: gpt-4o, gpt-4o-mini, gpt-4-turbo
  • Legacy Models: gpt-4, gpt-3.5-turbo

​
Max Tokens

  • Field: max_tokens
  • Type: Number (optional)
  • Purpose: Maximum number of tokens to generate in responses
  • Range: Positive integer ≤ 100,000
  • Example: 1000

​
System Prompt

  • Field: system_prompt
  • Type: String (optional)
  • Purpose: System-level instructions defining agent behavior and constraints
  • Use Cases: Role definition, behavior guidelines, response formatting
  • Example: "You are a helpful customer service assistant. Always be polite and provide accurate information."

​
Temperature

  • Field: temperature
  • Type: Number (optional)
  • Default: 1.0
  • Purpose: Controls randomness in AI responses
  • Range: 0.0 (deterministic) to 2.0 (very random)
  • Example: 0.7

​
Setup Instructions

  1. Enter the complete URL for your OpenAI-compatible API
  2. Input valid API key from your provider
  3. Select model and configure token limits/temperature
  4. Define system prompt for agent behavior

​
Troubleshooting

Common Issues:
  • Authentication Failures: Verify API key validity and permissions
  • Invalid Endpoint: Confirm URL format and API compatibility
  • Model Not Available: Check model name and provider support
  • Rate Limit Errors: Monitor API usage and implement backoff strategies