Skip to content

Commit a51bbeb

Browse files
Merge pull request #275712 from mrbullwinkle/mrb_05_18_2024_gpt4o
[Azure OpenAI] Models update
2 parents daafae2 + dc28a9e commit a51bbeb

File tree

6 files changed

+84
-77
lines changed

6 files changed

+84
-77
lines changed

articles/ai-services/openai/concepts/models.md

Lines changed: 25 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -28,23 +28,15 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
2828

2929
## GPT-4o and GPT-4 Turbo
3030

31-
GPT-4o is the latest preview model from OpenAI. GPT-4o integrates text and images in a single model, enabling it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English languages and vision tasks, setting new benchmarks for AI capabilities.
31+
GPT-4o is the latest model from OpenAI. GPT-4o integrates text and images in a single model, enabling it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English languages and vision tasks, setting new benchmarks for AI capabilities.
3232

33-
### Early access playground
34-
35-
Existing Azure OpenAI customers can test out GPT-4o in the **NEW** Azure OpenAI Studio Early Access Playground (Preview).
33+
### How do I access the GPT-4o model?
3634

37-
To test the latest model:
35+
GPT-4o is available for **standard** and **global-standard** model deployment.
3836

39-
> [!NOTE]
40-
> - The GPT-4o early access playground is currently only available for resources in **West US3** and **East US**, and is limited to 10 requests every five minutes per subscription.
41-
> - Azure OpenAI service abuse monitoring is enabled for all early access playground users even if approved for modification; default content filters are enabled and cannot be modified.
42-
> - GPT-4o is an Azure OpenAI preview model and is currently not available for deployment/direct API access.
37+
You need to [create](../how-to/create-resource.md) or use an existing resource in a [supported standard](#gpt-4-and-gpt-4-turbo-model-availability) or [global standard](#global-standard-model-availability-preview) region where the model is available.
4338

44-
1. Navigate to Azure OpenAI Studio at https://oai.azure.com/ and sign-in with credentials that have access to your OpenAI resources.
45-
2. Select an Azure OpenAI resource in the **West US3** or **East US** regions. If you don't have a resource in one of these regions you will need to [create a resource](../how-to/create-resource.md).
46-
3. From the main [Azure OpenAI Studio](https://oai.azure.com/) page select the **Early Access Playground (Preview)** button from under the **Get started** section. (This button will only be available when a resource in **West US3** or **East US** is selected.)
47-
4. Now you can start asking the model questions just as you would before in the existing [chat playground](../chatgpt-quickstart.md).
39+
When your resource is created, you can [deploy](../how-to/create-resource.md#deploy-a-model) the GPT-4o model. If you are performing a programmatic deployment, the **model** name is `gpt-4o`, and the **version** is `2024-05-13`.
4840

4941
### GPT-4 Turbo
5042

@@ -70,8 +62,8 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope
7062

7163
| Model ID | Description | Max Request (tokens) | Training Data (up to) |
7264
| --- | :--- |:--- |:---: |
73-
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni) Preview** | **Latest preview model** <br> - Text, image processing <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks <br> - [Currently only available via early access playground](#early-access-playground) <br> - Currently no deployment/API access|Input: 128,000 <br> Output: 4,096| Oct 2023 |
74-
| `gpt-4` (turbo-2024-04-09) <br>**GPT-4 Turbo with Vision** | **Latest GA model** <br> - Replacement for all previous GPT-4 preview models (`vision-preview`, `1106-Preview`, `0125-Preview`). <br> - [**Feature availability**](#gpt-4o-and-gpt-4-turbo) is currently different depending on method of input, and deployment type. <br> - Does **not support** enhancements. | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
65+
|`gpt-4o` (2024-05-13) <br> **GPT-4o (Omni)** | **Latest GA model** <br> - Text, image processing <br> - JSON Mode <br> - parallel function calling <br> - Enhanced accuracy and responsiveness <br> - Parity with English text and coding tasks compared to GPT-4 Turbo with Vision <br> - Superior performance in non-English languages and in vision tasks <br> - **Does not support enhancements** |Input: 128,000 <br> Output: 4,096| Oct 2023 |
66+
| `gpt-4` (turbo-2024-04-09) <br>**GPT-4 Turbo with Vision** | **New GA model** <br> - Replacement for all previous GPT-4 preview models (`vision-preview`, `1106-Preview`, `0125-Preview`). <br> - [**Feature availability**](#gpt-4o-and-gpt-4-turbo) is currently different depending on method of input, and deployment type. <br> - **Does not support enhancements**. | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
7567
| `gpt-4` (0125-Preview)*<br>**GPT-4 Turbo Preview** | **Preview Model** <br> -Replaces 1106-Preview <br>- Better code generation performance <br> - Reduces cases where the model doesn't complete a task <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 128,000 <br> Output: 4,096 | Dec 2023 |
7668
| `gpt-4` (vision-preview)<br>**GPT-4 Turbo with Vision Preview** | **Preview model** <br> - Accepts text and image input. <br> - Supports enhancements <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 128,000 <br> Output: 4,096 | Apr 2023 |
7769
| `gpt-4` (1106-Preview)<br>**GPT-4 Turbo Preview** | **Preview Model** <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 128,000 <br> Output: 4,096 | Apr 2023 |
@@ -103,7 +95,7 @@ GPT-3.5 models can understand and generate natural language or code. The most ca
10395
| --------- |:---|:------:|:----:|
10496
| `gpt-35-turbo` (0125) **NEW** | **Latest GA Model** <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) <br> - Higher accuracy at responding in requested formats. <br> - Fix for a bug which caused a text encoding issue for non-English language function calls. | Input: 16,385<br> Output: 4,096 | Sep 2021 |
10597
| `gpt-35-turbo` (1106) | **Older GA Model** <br> - JSON Mode <br> - parallel function calling <br> - reproducible output (preview) | Input: 16,385<br> Output: 4,096 | Sep 2021|
106-
| `gpt-35-turbo-instruct` (0914) | **Completions endpoint only** | 4,097 |Sep 2021 |
98+
| `gpt-35-turbo-instruct` (0914) | **Completions endpoint only** <br> - Replacement for [legacy completions models](./legacy-models.md) | 4,097 |Sep 2021 |
10799
| `gpt-35-turbo-16k` (0613) | **Older GA Model** <br> - Basic function calling with tools | 16,384 | Sep 2021 |
108100
| `gpt-35-turbo` (0613) | **Older GA Model** <br> - Basic function calling with tools | 4,096 | Sep 2021 |
109101
| `gpt-35-turbo`**<sup>1</sup>** (0301) | **Older GA Model** <br> - [Retirement information](./model-retirements.md#current-models) | 4,096 | Sep 2021 |
@@ -175,6 +167,21 @@ You need to speak with your Microsoft sales/account team to acquire provisioned
175167

176168
For more information on Provisioned deployments, see our [Provisioned guidance](./provisioned-throughput.md).
177169

170+
### Global standard model availability (preview)
171+
172+
**Supported models:**
173+
174+
- `gpt-4o` **Version:** `2024-05-13`
175+
176+
**Supported regions:**
177+
178+
- eastus
179+
- eastus2
180+
- northcentralus
181+
- southcentralus
182+
- westus
183+
- westus3
184+
178185
### GPT-4 and GPT-4 Turbo model availability
179186

180187
#### Public cloud regions
@@ -303,8 +310,9 @@ For Assistants you need a combination of a supported model, and a supported regi
303310
| Sweden Central ||||| |
304311
| UK South ||||| |
305312

313+
### Early access playground
306314

307-
315+
The GPT-4o model is now [GA and available for regular model deployment](#gpt-4o-and-gpt-4-turbo).
308316

309317
## Next steps
310318

articles/ai-services/openai/includes/model-matrix/provisioned-models.md

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@ description: PTU-managed model availability by region.
55
manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: include
8-
ms.date: 05/06/2024
8+
ms.date: 05/18/2024
99
---
1010

1111
| **Region** | **gpt-4**, **0613** | **gpt-4**, **1106-Preview** | **gpt-4**, **0125-Preview** | **gpt-4**, **turbo-2024-04-09** | **gpt-4-32k**, **0613** | **gpt-35-turbo**, **1106** | **gpt-35-turbo**, **0125** |
@@ -14,21 +14,21 @@ ms.date: 05/06/2024
1414
| brazilsouth ||| - | - ||| - |
1515
| canadacentral || - | - | - || - ||
1616
| canadaeast ||| - | - | - || - |
17-
| eastus |||| - ||||
18-
| eastus2 |||| - ||||
17+
| eastus |||| ||||
18+
| eastus2 |||| ||||
1919
| francecentral |||| - || - ||
2020
| germanywestcentral |||| - ||| - |
21-
| japaneast | - ||| - | - | - ||
21+
| japaneast | - ||| | - | - ||
2222
| koreacentral || - | - | - ||| - |
23-
| northcentralus |||| - ||||
23+
| northcentralus |||| ||||
2424
| norwayeast || - || - || - | - |
2525
| polandcentral |||| - ||||
2626
| southafricanorth ||| - | - ||| - |
27-
| southcentralus |||| - ||||
27+
| southcentralus |||| ||||
2828
| southindia |||| - ||||
2929
| swedencentral ||||||||
3030
| switzerlandnorth |||| - ||||
3131
| switzerlandwest | - | - | - | - | - | - ||
32-
| uksouth |||| - ||||
33-
| westus |||| - ||||
32+
| uksouth |||| ||||
33+
| westus |||| ||||
3434
| westus3 ||||||||

0 commit comments

Comments
 (0)