Azure OpenAI: get an API key and write fiction with it on your phone
For users who already live in Azure or have enterprise credits: the same GPT models, delivered through Microsoft's regional and compliance machinery. Newcomers should start with a direct provider — this onboarding is simply long. This page is the BYOK quick answer for Azure OpenAI: key steps, direct console and pricing links, and the app-side notes that matter. Verified 2026-07-18.
Two links up front: get your key at the official console and check rates on the official pricing page. Prices and free quotas move; the official pages are authoritative.
What does it power inside Foreverse?
The factory preset declares 2 modality flags for Azure OpenAI. The models actually available come from the live catalog fetched in-app — catalogs move fast, and the flag only means the protocol wiring is ready.
| Modality | Used for |
|---|
| Text | Continuation · roleplay chat · agent |
| Vision | Image understanding in chat |
How do I get a Azure OpenAI API key?
- Have an Azure account with a subscription (portal.azure.com, card required). If you have no Microsoft cloud footprint, plain OpenAI is a much shorter path.
- Create an Azure OpenAI resource in the portal (now under the Microsoft Foundry umbrella), in a region that carries your target model.
- Deploy a model to the resource in the Foundry portal (ai.azure.com) and note the deployment name — that string is the "model ID" you'll enter in the app.
- Copy the API key and endpoint domain from the resource's Keys and Endpoint page.
- In the app, set the host to https://<resource>.openai.azure.com/openai/v1 (the full path), then add a model whose ID equals your deployment name.
Key in hand: three steps to connect
- Open the app's Settings → AI models & services and find Azure OpenAI in the list (one of 62 presets, with logo and search).
- Paste the key and tap the connectivity test — it fires one real request to verify key and network, and pulls back the model list while it's at it.
- Enable the models you want, then set per-modality defaults (text, image, speech, and video each get their own); continuation, chat, and listening route through them from then on.
The one universal host pitfall: the API host must include its full version prefix (this provider's exact form is in the notes below) — the app never appends /v1 for you.
Azure OpenAI-specific notes
You must use Azure's v1 endpoint shape: a host ending in /openai/v1. The app sends the key as a Bearer header (which the v1 endpoint accepts, with no api-version parameter needed); the legacy /openai/deployments/…?api-version=… shape is not supported. Paste the full path — entering just the domain makes the app append a generic /v1, which is wrong here. Model ID = your deployment name, not the catalog model name. The connectivity test button reports unsupported for Azure; verify by sending an actual message.