Skip to content

Commit 86b07c9

Browse files
Merge pull request #2622 from mrbullwinkle/mrb_01_29_2025_inference_API_update
[Azure OpenAI] API update
2 parents 6813e08 + c3b4531 commit 86b07c9

File tree

5 files changed

+16
-14
lines changed

5 files changed

+16
-14
lines changed

articles/ai-services/openai/api-version-deprecation.md

Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ services: cognitive-services
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: conceptual
8-
ms.date: 01/10/2024
8+
ms.date: 01/29/2025
99
author: mrbullwinkle
1010
ms.author: mbullwin
1111
recommendations: false
@@ -24,14 +24,12 @@ This article is to help you understand the support lifecycle for the Azure OpenA
2424

2525
Azure OpenAI API latest release:
2626

27-
- Inference: [2024-12-01-preview](reference-preview.md)
28-
- Authoring: [2024-10-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2024-10-01-preview/azureopenai.json)
29-
30-
> [!IMPORTANT]
31-
> For features that are part of the dataplane authoring API such as batch, fine-tuning, and assistants files, continue to use API version `2024-10-01-preview` to take advantage of the latest preview features.
27+
- Inference: [2025-01-01-preview](reference-preview.md)
28+
- Authoring: [2025-01-01-preview](https://github.com/Azure/azure-rest-api-specs/blob/main/specification/cognitiveservices/data-plane/AzureOpenAI/authoring/preview/2025-01-01-preview/azureopenai.json)
3229

3330
This version contains support for the latest Azure OpenAI features including:
3431

32+
- [Predicted Outputs](./how-to/predicted-outputs.md) [**Added in 2025-01-01-preview**]
3533
- [Reasoning models](./how-to/reasoning.md) [**Added in 2024-12-01-preview**]
3634
- [Stored completions/distillation](./how-to/stored-completions.md) [**Added in 2024-12-01-preview**]
3735
- Assistants V2 [**Added in 2024-05-01-preview**]
@@ -44,6 +42,11 @@ This version contains support for the latest Azure OpenAI features including:
4442
- [Function calling](./how-to/function-calling.md) [**Added in 2023-07-01-preview**]
4543
- [Retrieval augmented generation with your data feature](./use-your-data-quickstart.md). [**Added in 2023-06-01-preview**]
4644

45+
## Changes between 2025-01-01-preview and 2024-12_01_preview
46+
47+
- `prediction` parameter added for [predicted outputs](./how-to/predicted-outputs.md) support.
48+
- `gpt-4o-audio-preview` [model support](./audio-completions-quickstart.md).
49+
4750
## Changes between 2024-12-01-preview and 2024-10-01-preview
4851

4952
- `store`, and `metadata` parameters added for [stored completions support](./how-to/stored-completions.md).

articles/ai-services/openai/how-to/predicted-outputs.md

Lines changed: 0 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,6 @@ Predicted outputs can improve model response latency for chat completions calls
1919
## Model support
2020

2121
- `gpt-4o-mini` version: `2024-07-18`
22-
- `gpt-4o` version: `2024-05-13`
2322
- `gpt-4o` version: `2024-08-06`
2423
- `gpt-4o` version: `2024-11-20`
2524

articles/ai-services/openai/includes/api-versions/latest-inference-preview.md

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -6292,7 +6292,7 @@ Represents an `assistant` that can call the model and use tools.
62926292
| created_at | integer | The Unix timestamp (in seconds) for when the assistant was created. | Yes | |
62936293
| name | string | The name of the assistant. The maximum length is 256 characters.<br> | Yes | |
62946294
| description | string | The description of the assistant. The maximum length is 512 characters.<br> | Yes | |
6295-
| model | string | ID of the model to use. You can use the List models API to see all of your available models, or see our [Model overview](/docs/models/overview) for descriptions of them.<br> | Yes | |
6295+
| model | string | ID of the model to use. You can use the List models API to see all of your available models, or see our [Model overview](../../concepts/models.md) for descriptions of them.<br> | Yes | |
62966296
| instructions | string | The system instructions that the assistant uses. The maximum length is 256,000 characters.<br> | Yes | |
62976297
| tools | array | A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`.<br> | Yes | [] |
62986298
| tool_resources | object | A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs.<br> | No | |
@@ -7343,7 +7343,7 @@ Represents a step in execution of a run.
73437343
| Name | Type | Description | Required | Default |
73447344
|------|------|-------------|----------|---------|
73457345
| id | string | The identifier of the run step, which can be referenced in API endpoints. | Yes | |
7346-
| object | string | The object type, which is always `assistant.run.step``. | Yes | |
7346+
| object | string | The object type, which is always `assistant.run.step`. | Yes | |
73477347
| created_at | integer | The Unix timestamp (in seconds) for when the run step was created. | Yes | |
73487348
| assistant_id | string | The ID of the assistant associated with the run step. | Yes | |
73497349
| thread_id | string | The ID of the thread that was run. | Yes | |
@@ -7451,7 +7451,7 @@ Details of the message creation by the run step.
74517451

74527452
| Name | Type | Description | Required | Default |
74537453
|------|------|-------------|----------|---------|
7454-
| type | string | Always `message_creation``. | Yes | |
7454+
| type | string | Always `message_creation`. | Yes | |
74557455
| message_creation | object | | Yes | |
74567456

74577457

@@ -7785,7 +7785,7 @@ A result instance of the file search.
77857785

77867786
| Name | Type | Description | Default |
77877787
|------|------|-------------|--------|
7788-
| output | string | The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. | |
7788+
| output | string | The output of the function. This will be `null` if the outputs have not been submitted yet. | |
77897789

77907790

77917791

articles/ai-services/openai/includes/language-overview/javascript.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -17,7 +17,7 @@ Feature availability in Azure OpenAI is dependent on what version of the REST AP
1717

1818
| Latest GA API | Latest Preview API|
1919
|:-----|:------|
20-
|`2024-10-21` |`2024-10-01-preview`|
20+
|`2024-10-21` |`2025-01-01-preview`|
2121

2222
## Installation
2323

articles/ai-services/openai/includes/language-overview/python.md

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ Feature availability in Azure OpenAI is dependent on what version of the REST AP
1919

2020
| Latest GA API | Latest Preview API|
2121
|:-----|:------|
22-
|`2024-10-21` |`2024-10-01-preview`|
22+
|`2024-10-21` |`2025-01-01-preview`|
2323

2424
## Installation
2525

@@ -616,7 +616,7 @@ except openai.APIStatusError as e:
616616

617617
### Request IDs
618618

619-
To retrieve the ID of your request you can use the `_request_id` property which corresponds to the `x-request-id` responde header.
619+
To retrieve the ID of your request you can use the `_request_id` property which corresponds to the `x-request-id` response header.
620620

621621
```python
622622
print(completion._request_id)

0 commit comments

Comments
 (0)