You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/how-to/reproducible-output.md
+1-15Lines changed: 1 addition & 15 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ services: cognitive-services
6
6
manager: nitinme
7
7
ms.service: azure-ai-openai
8
8
ms.topic: how-to
9
-
ms.date: 07/02/2025
9
+
ms.date: 08/11/2025
10
10
author: mrbullwinkle
11
11
ms.author: mbullwin
12
12
recommendations: false
@@ -19,20 +19,6 @@ By default if you ask an Azure OpenAI Chat Completion model the same question mu
19
19
20
20
## Reproducible output support
21
21
22
-
Reproducible output is only currently supported with the following:
23
-
24
-
### Supported models
25
-
26
-
*`gpt-35-turbo` (1106)
27
-
*`gpt-35-turbo` (0125)
28
-
*`gpt-4` (1106-Preview)
29
-
*`gpt-4` (0125-Preview)
30
-
*`gpt-4` (turbo-2024-04-09)
31
-
*`gpt-4o-mini` (2024-07-18)
32
-
*`gpt-4o` (2024-05-13)
33
-
34
-
Consult the [models page](../concepts/models.md) for the latest information on model regional availability.
35
-
36
22
### API Version
37
23
38
24
Support for reproducible output was first added in API version [`2023-12-01-preview`](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/inference/preview/2023-12-01-preview/inference.json)
0 commit comments