Chat Azure OpenAI

Give an AI node access to OpenAI models that your organisation hosts on Azure OpenAI Service.

Needs an Azure OpenAI connection — 

Pick a saved connection in the Authentication field, or create one from there.

Connect Azure OpenAI →

What it does

Chat Azure OpenAI is a model you plug into the Model slot of an AI node, such as the Tools Agent or Basic LLM Chain. It does not run on its own and has no output. When the AI node runs, it sends its messages to your Azure OpenAI resource and gets the reply back.

• Temperature is 0 when you leave it empty, so answers are focused and repeatable.
• Replies are capped at Max Tokens (4096 by default).
• A failed request is retried up to Max Retries times (2 by default). A request that gets no answer within 60 seconds fails.

When to use it

• Your company gives you access to GPT models through Azure rather than through OpenAI directly.
• Your data must stay in your organisation’s Azure region and contract.

With a personal OpenAI account, use Chat OpenAI instead.

Inputs and settings

Einstellung	Typ	Was es bewirkt
Model PFLICHT(erforderlich)	Text	The Azure OpenAI model name, e.g. gpt-4o.
Resource Name PFLICHT(erforderlich)	Text	Your Azure OpenAI resource (instance) name.
Deployment Name PFLICHT(erforderlich)	Text	The deployment name configured in your Azure OpenAI resource.
API Version	Text	The Azure OpenAI API version. Standard: 2024-10-21
Authentication PFLICHT(erforderlich)	Credential	Use your Azure OpenAI API key.
Options	Group	The options to use with the model.
Options › Temperature	Number	The temperature to use for the model.
Options › Max Retries	Number	The maximum number of retries to use for the model. Standard: 2
Options › Max Tokens	Number	The most tokens the model may generate in one reply. Defaults to 4096, which keeps providers from reserving credit for the whole output window. Standard: 4096

You find the values in the Azure portal, on your Azure OpenAI resource:

• Resource Name: the name of the resource, the first part of its endpoint. For https://my-azure-openai.openai.azure.com, it is my-azure-openai.
• Deployment Name: the name you gave the model deployment in the resource (not always the same as the model name).
• Model: the model behind that deployment, for example gpt-4o.
• API Version: leave 2024-10-21 unless your administrator tells you otherwise.

Outputs

This node has no output port. It plugs into a slot on another node instead of passing items along.

• Model slot of Tools Agent, Q&A Agent, RAG Agent, Basic LLM Chain, Indexer, Text Classifier, Sentiment Analysis, Summarization, Information Extractor, Guardrails, Auto-fixing Output Parser

The AI node you connect it to produces the output. This node only decides which model answers.

Dependencies and credentials

• Authentication (connection): required. See Connect Azure OpenAI.

In Authentication, save one of your resource’s API keys. In the Azure portal, open the Azure OpenAI resource and copy a key from Keys and Endpoint. See Create a credential.

Example workflow

1. A Context Menu trigger on selected text.
2. Information Extractor with Text {{ $input.selectionText }} and What to extract the person's name, company and email address.
3. Chat Azure OpenAI in its Model slot: Resource Name my-azure-openai, Deployment Name gpt-4o, Model gpt-4o.
4. The contact details come out in the extracted field, ready for a spreadsheet or CRM node.

Common issues

• “Resource Name parameter is required and cannot be empty” or “Deployment Name parameter is required and cannot be empty”. Fill in both fields from the Azure portal.
• “Model parameter is required and cannot be empty”. Fill in Model.
• A “DeploymentNotFound” or 404 error. Deployment Name does not match a deployment in that resource, or the deployment is still being created. Copy the exact name from the portal.
• A 401 error. The key belongs to another resource, or was regenerated. Copy a current key from Keys and Endpoint.

Related nodes

• Chat OpenAI: the same models through OpenAI directly.
• Basic LLM Chain: send one prompt and get a reply.
• Tools Agent: an agent that can use tools and memory.