diff --git a/packages/ai/src/providers/azure.ts b/packages/ai/src/providers/azure.ts
index 94d5edb4c85..75e89e506bc 100644
--- a/packages/ai/src/providers/azure.ts
+++ b/packages/ai/src/providers/azure.ts
@@ -90,7 +90,8 @@ function endpoint(input: Config, modelID: string | ModelID) {
   if (input.baseURL !== undefined && !new URL(input.baseURL).hostname.endsWith(".openai.azure.com")) {
     return { baseURL, query: input.queryParams }
   }
-  return { baseURL: `${baseURL}/v1`, query }
+  // Azure's v1 API serves from /openai/v1; callers may pass the base URL with or without the version segment.
+  return { baseURL: baseURL.endsWith("/v1") ? baseURL : `${baseURL}/v1`, query }
 }
 
 export const configure = (input: Config) => {
diff --git a/packages/ai/test/provider/openai-chat.test.ts b/packages/ai/test/provider/openai-chat.test.ts
index 8d1febd6b8e..ed557fe2b79 100644
--- a/packages/ai/test/provider/openai-chat.test.ts
+++ b/packages/ai/test/provider/openai-chat.test.ts
@@ -255,7 +255,7 @@ describe("OpenAI Chat route", () => {
     LLMClient.generate(
       LLMRequest.update(request, {
         model: Azure.configure({
-          baseURL: "https://opencode-test.openai.azure.com/openai/v1/",
+          baseURL: "https://opencode-test.openai.azure.com/openai/",
           apiKey: "azure-key",
           headers: { authorization: "Bearer stale" },
         }).chat("gpt-4o-mini"),
@@ -277,6 +277,29 @@ describe("OpenAI Chat route", () => {
     ),
   )
 
+  it.effect("does not duplicate /v1 for already-versioned Azure Chat base URLs", () =>
+    LLMClient.generate(
+      LLMRequest.update(request, {
+        model: Azure.configure({
+          baseURL: "https://opencode-test.openai.azure.com/openai/v1/",
+          apiKey: "azure-key",
+        }).chat("gpt-4o-mini"),
+      }),
+    ).pipe(
+      Effect.provide(
+        dynamicResponse((input) =>
+          Effect.gen(function* () {
+            const web = yield* HttpClientRequest.toWeb(input.request).pipe(Effect.orDie)
+            expect(web.url).toBe("https://opencode-test.openai.azure.com/openai/v1/chat/completions?api-version=v1")
+            return input.respond(sseEvents(deltaChunk({}, "stop")), {
+              headers: { "content-type": "text/event-stream" },
+            })
+          }),
+        ),
+      ),
+    ),
+  )
+
   it.effect("applies serializable HTTP overlays after payload lowering", () =>
     LLMClient.generate(
       LLMRequest.update(request, {