OpenAI Compatible API

Selecting the Connection Type

Once you have selected your connection type, a configuration tab will appear on the next step, prompting you to input the required connection details.

Integration Setup

The integration supports two API types:

1. ​Chat Completions API - The traditional industry-standard protocol (/v1/chat/completions). It operates on a message-based array system and requires manual context management. While robust and widely used, it is now considered a legacy path and may not receive the latest agentic features or reasoning optimizations.

2. Responses API - The modern, unified protocol designed to supersede Chat Completions. It offers better performance with reasoning models (like GPT-5), native agentic loops for multi-tool calling, lower costs through improved cache utilization, and built-in stateful context management.

The setup process and requirements for both API Types are defined below.

Figure 1: OpenAI Compatible API Connection - Chat Completions API

Figure 2: OpenAI Compatible API Connection - Responses API

• URL - This is your target endpoint to which the attack messages will be sent.

• API Key - The authentication key for your target (if applicable).

• System Prompt - Your application’s system prompt. It sets the initial instructions or context for the AI model, defines the behavior, tone, and specific guidelines the AI should follow while interacting. For best practices, refer to the OpenAI documentation on prompt engineering.

• Model - The exact model name you want to use. Since this connector is not tied to a single model provider, you should look up the correct identifier on your chosen provider’s website. You can find links to the model lists from different providers on their corresponding Connections pages in the SPLX Platform documentation.

• HTTP Headers - Enter the key–value pairs required for API requests to the target.

• Extra LLM Config - Any request-body LLM configuration parameters the UI does not expose explicitly, such as temperature, top_p, or max_tokens. Leave the field blank to accept provider defaults. You can check all the optional fields in the OpenAI cookbook.

For the extra LLM config, the Add + button needs to be pressed after the Key and Value textboxes are filled.