Nexra
All connectors
Implemented
AI, documents, knowledge & search
Azure OpenAI logo

Azure OpenAI

Run chat completions, Responses and embeddings against your own Azure OpenAI deployments with the GA v1 API.

Use OpenAI models inside your Azure tenancy, region and content-safety policies from business flows.

Build a flow with Azure OpenAIProvider API documentation

Source actions

3

Destination actions

3

Data types

4

Validation status

Implemented · fixture tested.

Implementation is checked against provider-shaped fixtures for every action, authentication failures, rate limits, pagination and duplicate safety. Provider sandbox and authorised account validation are recorded separately when credential-backed runs are completed.

What you can map

chat completions
  • Generate chat completion
    Destination
    Not retried automatically

    Chat completion from a deployment. Supply a JSON schema for Structured Outputs.

embeddings
  • Create embeddings
    Destination
    Not retried automatically

    Embeds up to 2,048 texts with an embedding deployment; one record per text.

models
  • Get model
    Source

    One model available to the resource.

  • List models
    Source

    Models available to the resource (GA v1 API).

responses
  • Generate response (Responses API)
    Destination
    Not retried automatically

    Generates a reply with the Responses API, which Microsoft recommends for Azure OpenAI models.

  • Get response
    Source

    Reads a stored response by ID.

Authentication

Azure OpenAI resource key (api-key header)

Plans and access

An Azure subscription with an Azure OpenAI or Microsoft Foundry resource and model deployments. Calls use deployment names, not model names. Quota is assigned per deployment in tokens per minute.

Test environment

Use a low-quota deployment in a non-production resource for testing.

Rate limits

Tokens-per-minute and requests-per-minute quota per deployment; HTTP 429 with Retry-After when exceeded.

Provider events

Azure OpenAI inference does not deliver webhooks. Nexra event triggers are not yet available; flows run on demand or on a schedule.

Before you build a flow

  • Deployments cannot be listed with a resource key; that requires the Azure Resource Manager API and Microsoft Entra ID. Enter deployment names directly.
  • The v1 models list returns models available to the resource, not deployments.
  • Streaming, tools, images, audio, Assistants, files, batches and fine-tuning are not exposed.
  • Microsoft Entra ID tokens are not supported; use a resource key.
  • Generation and embeddings are billed; they must be enabled per connection and are never retried automatically.