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-services/openai/concepts/models.md
+25-17Lines changed: 25 additions & 17 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -28,23 +28,15 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
28
28
29
29
## GPT-4o and GPT-4 Turbo
30
30
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.
32
32
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?
36
34
37
-
To test the latest model:
35
+
GPT-4o is available for **standard** and **global-standard**model deployment.
38
36
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.
43
38
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`.
48
40
49
41
### GPT-4 Turbo
50
42
@@ -70,8 +62,8 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope
70
62
71
63
| Model ID | Description | Max Request (tokens) | Training Data (up to) |
72
64
| --- | :--- |:--- |:---: |
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 |
75
67
|`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 |
@@ -103,7 +95,7 @@ GPT-3.5 models can understand and generate natural language or code. The most ca
103
95
| --------- |:---|:------:|:----:|
104
96
|`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 |
0 commit comments