Question 1

How do I use the Azure AI Foundry API?

Accepted Answer

Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to grok-4-3. On pay-as-you-go keys, azure-ai-foundry/grok-4-3 pins every request to Azure AI Foundry; DevPass coding plans do not support provider pinning. You do not need a separate Azure AI Foundry account or SDK.

Question 2

Which Azure AI Foundry models are available?

Accepted Answer

LLM Gateway serves 3 Azure AI Foundry models: Grok 4.3, Grok 4.1 Fast Non-Reasoning, Grok 4.1 Fast Reasoning. Each model page lists per-token pricing, context window and capabilities.

Question 3

Does Azure AI Foundry train on API data?

Accepted Answer

No. Azure AI Foundry's published policy states that API traffic is not used for model training.

Question 4

Where is Azure AI Foundry based?

Accepted Answer

Azure AI Foundry is headquartered in United States. LLM Gateway shows each provider's location and data policy so you can route by compliance requirements.

Question 5

What happens if the Azure AI Foundry API is down?

Accepted Answer

When you request a model without a provider prefix, LLM Gateway retries failed requests on other providers that serve the same model, so an outage at Azure AI Foundry does not have to take your app down. Send X-No-Fallback: true with a provider-pinned model when every request must reach Azure AI Foundry.

Azure AI Foundry API

Data & Privacy

Available Models

Grok 4.3

Grok 4.1 Fast Non-Reasoning

Grok 4.1 Fast Reasoning

Azure AI Foundry API questions

Stay ahead of the curve