From a28fb8295389efb6381141c601643366799c97f4 Mon Sep 17 00:00:00 2001 From: Stephen Smith Date: Tue, 18 Aug 2026 16:28:27 -0700 Subject: [PATCH 1/2] Add Azure model and region IDs --- fern/providers/model/azure-openai.mdx | 34 +++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/fern/providers/model/azure-openai.mdx b/fern/providers/model/azure-openai.mdx index 926e24f6f..c565c973d 100644 --- a/fern/providers/model/azure-openai.mdx +++ b/fern/providers/model/azure-openai.mdx @@ -82,6 +82,40 @@ Vapi currently accepts the following Azure OpenAI deployment names. Your Azure d Check [Azure OpenAI model availability](https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure) and the [model retirement schedule](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/model-retirement-schedule) before creating a deployment. Availability depends on the Azure region and deployment type. +### Regional model routing + +To route an assistant's model requests to a specific Azure region, set `model.provider` to `openai` and set `model.model` to one of the region-qualified model IDs below. The value after the colon is the Azure region. These are assistant model IDs, not Azure deployment names. + +When the request uses an Azure OpenAI credential configured for the selected region, Vapi routes through that credential. Otherwise, Vapi uses its managed Azure deployment in that region. Vapi does not send a region-pinned request through an out-of-region fallback. + +```bash +curl -X PATCH "https://api.vapi.ai/assistant/ASSISTANT_ID" \ + -H "Authorization: Bearer $VAPI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": { + "provider": "openai", + "model": "gpt-5.4:eastus2" + } + }' +``` + +Vapi currently supports these region-qualified model IDs: + +| Model | Region-qualified model IDs | +| --- | --- | +| GPT 5.6 Sol | `gpt-5.6-sol:westus3` | +| GPT 5.6 Terra | `gpt-5.6-terra:westus3` | +| GPT 5.6 Luna | `gpt-5.6-luna:westus3` | +| GPT 5.4 | `gpt-5.4:eastus2`
`gpt-5.4:swedencentral` | +| GPT 5.4 Mini | `gpt-5.4-mini:australiaeast`
`gpt-5.4-mini:eastus2`
`gpt-5.4-mini:swedencentral` | +| GPT 5.4 Nano | `gpt-5.4-nano:eastus2`
`gpt-5.4-nano:swedencentral` | +| GPT 5.2 | `gpt-5.2:eastus2`
`gpt-5.2:swedencentral` | +| GPT 5.1 | `gpt-5.1:eastus2`
`gpt-5.1:swedencentral` | +| GPT 5 | `gpt-5:canadaeast`
`gpt-5:eastus`
`gpt-5:eastus2`
`gpt-5:germanywestcentral`
`gpt-5:polandcentral`
`gpt-5:spaincentral`
`gpt-5:swedencentral`
`gpt-5:westeurope` | +| GPT 5 Mini | `gpt-5-mini:eastus2`
`gpt-5-mini:germanywestcentral`
`gpt-5-mini:polandcentral`
`gpt-5-mini:spaincentral`
`gpt-5-mini:swedencentral`
`gpt-5-mini:westeurope` | +| GPT 5 Nano | `gpt-5-nano:eastus2`
`gpt-5-nano:swedencentral` | + ### Supported Regions Vapi supports these Azure regions for OpenAI deployments: From 0ada14aa4072f123c9b162f3b22989873984ead6 Mon Sep 17 00:00:00 2001 From: Stephen Smith Date: Wed, 19 Aug 2026 09:55:52 -0700 Subject: [PATCH 2/2] Rewrite Azure deployment name note --- fern/providers/model/azure-openai.mdx | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/fern/providers/model/azure-openai.mdx b/fern/providers/model/azure-openai.mdx index c565c973d..4536eb61d 100644 --- a/fern/providers/model/azure-openai.mdx +++ b/fern/providers/model/azure-openai.mdx @@ -55,9 +55,7 @@ You can configure your Azure OpenAI credentials in the "Model Providers" section ### Model and Deployment Names - -**Critical Requirement**: Your Azure deployment name **must exactly match** one of Vapi's supported model names. Custom deployment names are not supported. - +Your Azure deployment name must match one of Vapi's supported model IDs. Custom deployment names are not supported. For example, if you want to use GPT-4o, your Azure deployment must be named exactly `gpt-4o-2024-11-20` (or another supported variant), not a custom name like `my-custom-gpt4`.