Integrations / Azure OpenAI

Azure OpenAI

Azure OpenAI — per-request token usage pulled from the tenant's Log Analytics workspace (diagnostic settings). The only major cloud exposing provider-side per-request token logs. Spend-only connector for the AI Platform Spend Governance feature.

Service account

Spend

What Telara does

Capability matrix

Indexes No Tracks spend Yes Discovers shadow AI No Runs actions No Real-time events No

Before you connect

Prerequisites

An Azure subscription where Azure OpenAI diagnostic logs land in a Log Analytics workspace.

Permission to App registrations in Entra and to grant Log Analytics Reader on that workspace.

Vendor setup

Get the credential

Confirm diagnostics

In the Azure portal, open the Azure OpenAI resource → Diagnostic settings. A setting must send logs to a Log Analytics workspace. If that is missing, Connect will succeed and usage will stay empty.

Entra ID → App registrations → New registration. Name it for Telara. Create a client secret under Certificates & secrets. Copy the secret immediately.

Grant Log Analytics Reader

Open the Log Analytics workspace → Access control (IAM) → Add role assignment → Log Analytics Reader → select the app you just registered.

Paste in Telara

Settings → Integrations → Azure OpenAI. Enter directory (tenant) id, application (client) id, client secret, and the Log Analytics workspace id.

In Telara

Connect in Telara

Service account

Azure AD app registration (client-credentials flow) with the Log Analytics Reader role on the workspace receiving the Azure OpenAI resource's diagnostic logs. Prerequisite: enable Diagnostic Settings on each Azure OpenAI resource (RequestResponse + Trace categories — the per-request token fields) routed to that workspace. workspace_id is the Log Analytics workspace GUID.

In Telara, open Settings → Integrations, choose this connector, and complete the fields Telara shows.

Fields Telara asks for

Tenant Id
Client ID
Client secret
Workspace Id

Spend

What gets measured

Resolution: Per request.

Attribution: Matched to people by email.

How far back vendor history goes is not published uniformly for this connector.

input_tokens
tokens
output_tokens
tokens
api_requests
requests

Sync

Freshness & sync

Spend connectors refresh on the vendor pull cadence declared in the catalog. Indexing lag is not published for this connector.

Data handling

Permissions & data handling

Telara has not published a permission list for this connector yet. Treat the vendor consent screen as the source of truth until this page lists scopes.

This catalog entry does not declare extra semantic-search exclusions.

After connect

Verify it worked

This connector does not declare a credential probe yet. A saved connection means Telara stored the credential, not that the vendor accepted it.

Honesty

Known limitations

An Azure OpenAI resource key used for chat completions cannot read usage. That key is the wrong class.

This is not the Azure OpenAI SDK (direct) telemetry connector.