Skip to content

Chat Azure OpenAI

Use OpenAI models hosted on Azure OpenAI Service.

Provides access to OpenAI models deployed on your own Azure OpenAI resource for AI agent nodes.

Connect this to AI agents when your organization runs OpenAI models through an Azure OpenAI Service resource instead of the public OpenAI API, for example to meet data residency or enterprise compliance requirements.

SettingNotes
ModelThe Azure OpenAI model name, e.g. gpt-4o. Placeholder: gpt-4o.
Resource NameYour Azure OpenAI resource (instance) name. Placeholder: my-azure-openai.
Deployment NameThe deployment name configured in your Azure OpenAI resource. Placeholder: gpt-4o.
API VersionThe Azure OpenAI API version. Defaults to 2024-10-21. Placeholder: 2024-10-21.
AuthenticationCredential used to authenticate: “Use your Azure OpenAI API key.”
Options → TemperatureThe temperature to use for the model.
Options → Max RetriesThe maximum number of retries to use for the model. Defaults to 2.

Returns a chat model dependency that can be connected to AI agent nodes.

  • Requires an Authentication credential holding your Azure OpenAI API key.
  • Also requires the Resource Name and Deployment Name of your Azure OpenAI resource; the node throws an error if Model, Resource Name, or Deployment Name are empty.

Connect Chat Azure OpenAI to an AI agent or dependency input that accepts this dependency type, set the Model, Resource Name, and Deployment Name to match your Azure OpenAI resource, attach your API key credential, then run the agent with data from previous nodes.

  • Ensure Model, Resource Name, and Deployment Name are all filled in — the node rejects empty values for these fields.
  • Verify the API Version is supported by your Azure OpenAI resource if requests fail.
  • If it calls an external service, verify credentials, permissions, and rate limits.
  • No dedicated source test was found next to this node; verify behavior manually when changing this page.