You have an Azure subscription that contains an Azure OpenAl resource.

Scenario Recap:

You have an Azure OpenAI resource with multiple deployed models.

You are using the Chat playground to build a chatbot.

Requirements:

Generate text in concise, formal business language.

Reduce cost of running the model.

Maintain the size of the chatbot history window (i.e., context length).

Step 1: Ensuring concise, formal business language

In the Chat playground setup panel, you can configure System message instructions.

Example:

You are an AI assistant that responds in concise formal business language.

This controls tone, style, and response behavior.

So one setting is: System message / Instructions.

Step 2: Reducing cost while maintaining chat history window

Costs in Azure OpenAI are tied to:

The model used (larger models = more expensive).

The context window size (token usage).

Since we must maintain the size of the chat history window, we cannot shrink context length.

Therefore, to reduce cost: select a smaller/cheaper deployed model (e.g., GPT-3.5 instead of GPT-4).

So the second setting is: Deployment (model selection).

✅ Final Answer:

Configure Deployment → choose a smaller/cheaper model.

Configure System message instructions → specify “concise formal business language.”

Microsoft References:

Azure OpenAI Chat playground

Best practices for reducing token cost