Supported OpenAI models for AI integration
Introduced in 2024.2
Updated in 2025
This article explains which AI models you need to configure for the AI integration in Alloy Navigator Express and what each model is used for. You select models during AI integration, when entering your API key and configuring AI features.
Alloy Navigator Express supports OpenAI API and Azure OpenAI Service AI providers. If you use Azure OpenAI Service, you first need to create a deployment for each model you want to use. Then, you specify the deployment names in the settings.
INFO: You can find a full listing of available OpenAI models here: https://platform.openai.com/docs/models/
Completion model (Chat, Text Generation model)
The completion model (also called a chat model, or a text generation model) is essential for all AI features in Alloy Navigator Express, including AI Writing Assistance and AI-Powered Insights. By default, we use gpt-4.1-mini, a chat model optimized for conversational AI. You can select from available models or enter your own, but avoid selecting reasoning models, as they do not fit into our AI-assisted workflows.
TIP: When choosing a model for text generation, consider that GPT models are fast, cost-efficient, and highly intelligent, but work best with clear, detailed instructions. Mini and nano models offer trade-offs in speed and cost, generally being faster and cheaper to use. When in doubt, gpt-4.1 offers a solid combination of intelligence, speed, and cost effectiveness.
-
OpenAI API: Use chat models such as gpt-4o-mini, gpt-3.5-turbo, etc.
-
Azure OpenAI Service: Use chat model deployments. Model type is Chat. You must create a deployment for a chat model (e.g., GPT-4 chat) in your Azure portal and then enter the deployment name
Text-to-Speech model
This model converts text into audio for AI Writing Assistance with voice output. If you don't plan to use voice features, you can disable Text-to-Speech feature. By default, we use tts-1, but you can select or enter a different model.
-
OpenAI API: Use available text-to-speech models like tts-1
-
Azure OpenAI Service: Create a deployment for a text-to-speech model in your Azure portal and specify the deployment name in Alloy Navigator Express
Transcription model
The transcription model is used for speech recognition in AI Writing Assistance, converting audio to written text. You can disable it if you don't use voice input. The default model is whisper-1.
-
OpenAI API: Use transcription models such as whisper-1
-
Azure OpenAI Service: Create a deployment for a transcription model in your Azure portal and specify the deployment name in Alloy Navigator Express
Embedding model
The embedding model generates vector representations of text for semantic search and internal knowledge access for AI-Powered Insights. The default is text-embedding-3-large.
If you decide not to use the embedding model and disable access to internal knowledge, AI-Assisted Insights will still function but provide less accurate and relevant responses because they won't be able to search your tickets or knowledge base.
-
OpenAI API: Use an embedding model like text-embedding-3-large
-
Azure OpenAI Service: Create a deployment for an mbedding model in your Azure portal and specify the deployment name in Alloy Navigator Express