LiteLLM / LiteLLM

LiteLLM Azure OpenAI Authentication Broken in v1.84.0 with enable_azure_ad_token_refresh

Fix LiteLLM Azure OAI authentication error after upgrading to 1.84.0 when using enable_azure_ad_token_refresh Includes evidence for LiteLLM troubleshooting demand.

Source-backed Last updated May 14, 2026 1 source Needs local verification

Category: LiteLLM
Error signature: LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable
Quick fix: Verify the account session, API key, provider settings, and environment where the failing tool is running.
Updated: May 14, 2026
Verification status: Source-backed
Evidence: 1 public source URL

Before you change production

This page includes public source URLs in the imported troubleshooting record. Compare those references with your version and environment before applying changes.

Reproduce the smallest failing action and save non-secret logs before changing configuration.
Check versions for LiteLLM, related SDKs, package managers, CI runners, and hosting providers.
Change one setting or dependency at a time, then rerun the same failing command or request.
Avoid destructive commands, credential rotation, billing changes, or security relaxations without a rollback plan.

What this error means

LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable is a LiteLLM failure pattern reported for developers trying to fix litellm azure oai authentication error after upgrading to 1.84.0 when using enable_azure_ad_token_refresh. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Issue #27945 on BerriAI/litellm: regression in v1.84.0 breaks Azure AD token refresh. Logs show AuthenticationError despite enable_azure_ad_token_refresh=true. Worked in 1.84.0rc1. Affects production deployments using Azure OpenAI with AD auth.

Common causes

Upgrading LiteLLM from 1.84.0rc1 to 1.84.0 breaks Azure AD token refresh for Azure OpenAI models. The error indicates api_key is missing even though Azure AD token provider is configured. This is a regression in a paid proxy service used in production environments.
Issue #27945 on BerriAI/litellm: regression in v1.84.0 breaks Azure AD token refresh. Logs show AuthenticationError despite enable_azure_ad_token_refresh=true. Worked in 1.84.0rc1. Affects production deployments using Azure OpenAI with AD auth.

Quick fixes

Confirm the exact error signature matches LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable.
Check the LiteLLM account, local tool state, and provider configuration involved in the failing workflow.
Verify the account session, API key, provider settings, and environment where the failing tool is running.

Platform/tool-specific checks

Verify the command, editor, extension, or API client that produced the error.
Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

Capture the exact error message and the command, editor action, or request that triggered it.
Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
Review the source evidence below and compare it with your environment.
Apply one change at a time and rerun the smallest failing action.
Keep the working fix documented for the team or deployment environment.

How to prevent it

Keep provider/tool configuration documented.
Record non-secret diagnostics such as tool version, provider name, model name, and command path.
Add a lightweight check before CI or production workflows depend on the tool.

Diagnostic flow for this page

Match LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable exactly before applying the quick fix.
Compare the failing environment with LiteLLM versions, account scope, provider settings, and deployment context.
Check the listed common causes in order, starting with the cause that best matches your logs.
Use the evidence status below to decide whether to confirm against public sources or official documentation.
Apply one reversible change, rerun the smallest failing action, and keep rollback notes.

FAQ

What does LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable mean in LiteLLM?

LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable indicates the workflow described by "LiteLLM Azure OpenAI Authentication Broken in v1.84.0 with enable_azure_ad_token_refresh" failed in a LiteLLM context. Start by confirming the exact signature and the component that emitted it.

What should I check first for LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable?

Check whether this cause matches your environment: Upgrading LiteLLM from 1.84.0rc1 to 1.84.0 breaks Azure AD token refresh for Azure OpenAI models. The error indicates api_key is missing even though Azure AD token provider is configured. This is a regression in a paid proxy service used in production environments.

Is the LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable guidance source-backed?

The "LiteLLM Azure OpenAI Authentication Broken in v1.84.0 with enable_azure_ad_token_refresh" page is labeled source-backed. It has 1 public source URL from github.com, so use that evidence status when deciding how much additional verification you need.

When should I avoid the quick fix for LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable?

For "LiteLLM Azure OpenAI Authentication Broken in v1.84.0 with enable_azure_ad_token_refresh", avoid applying "Verify the account session, API key, provider settings, and environment where the failing tool is running." when the error text differs, the affected version or provider is different, or the change would touch credentials, billing, DNS, production deploy settings, or irreversible data.

What should I collect before debugging LiteLLM AuthenticationError: AzureException AuthenticationError - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable?

For "LiteLLM Azure OpenAI Authentication Broken in v1.84.0 with enable_azure_ad_token_refresh", collect the failing LiteLLM command or request, non-secret configuration, versions, timestamps, request IDs when available, and the smallest reproduction that still triggers the signature.