Skip to content

Commit 0601790

Browse files
PMEds28PMEds28
authored
Merge pull request #269026 from mrbullwinkle/mrb_03_13_2024_quota
[Azure OpenAI] Model matrix update
2 parents 4083cf1 + 6698b65 commit 0601790

File tree

7 files changed

+183
-45
lines changed

7 files changed

+183
-45
lines changed

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

Lines changed: 40 additions & 23 deletions
Original file line numberDiff line numberDiff line change
@@ -85,6 +85,17 @@ You can also use the OpenAI text to speech voices via Azure AI Speech. To learn
8585

8686
## Model summary table and region availability
8787

88+
> [!NOTE]
89+
> This article only covers model/region availability that applies to all Azure OpenAI customers with deployment types of **Standard**. Some select customers have access to model/region combinations that are not listed in the unified table below. These tables also do not apply to customers using only **Provisioned** deployment types which have their own unique model/region availability matrix. For more information on **Provisioned** deployments refer to our [Provisioned guidance](./provisioned-throughput.md).
90+
91+
### Standard deployment model availability
92+
93+
[!INCLUDE [Standard Models](../includes/model-matrix/standard-models.md)]
94+
95+
### Standard deployment model quota
96+
97+
[!INCLUDE [Quota](../includes/model-matrix/quota.md)]
98+
8899
### GPT-4 and GPT-4 Turbo Preview models
89100

90101
GPT-4, GPT-4-32k, and GPT-4 Turbo with Vision are now available to all Azure OpenAI Service customers. Availability varies by region. If you don't see GPT-4 in your region, please check back later.
@@ -128,13 +139,16 @@ GPT-4 version 0125-preview is an updated version of the GPT-4 Turbo preview prev
128139

129140
#### Public cloud regions
130141

131-
| Model | Regions where model is available to all subscriptions with Azure OpenAI access | Regions where model is available only to subscriptions with previous access to that model/region |
132-
|---|:---|:---|
133-
| gpt-4 (0314) | | East US <br> France Central <br> South Central US <br> UK South |
134-
| gpt-4 (0613) | Australia East <br> Canada East <br> France Central <br> Sweden Central <br> Switzerland North | East US <br> East US 2 <br> Japan East <br> UK South |
135-
| gpt-4 (1106-Preview) | Australia East <br> Canada East <br> East US 2 <br> France Central <br> Norway East <br> South India <br> Sweden Central <br> UK South <br> West US | |
136-
| gpt-4 (0125-Preview) | East US <br> North Central US <br> South Central US <br> |
137-
| gpt-4 (vision-preview) | Sweden Central <br> West US <br> Japan East <br> Switzerland North <br> Australia East| |
142+
[!INCLUDE [GPT-4](../includes/model-matrix/standard-gpt-4.md)]
143+
144+
#### Select customer access
145+
146+
In addition to the regions above which are available to all Azure OpenAI customers, some select pre-existing customers have been granted access to versions of GPT-4 in additional regions:
147+
148+
| Model | Region |
149+
|---|:---|
150+
| `gpt-4` (0314) | East US <br> France Central <br> South Central US <br> UK South |
151+
| `gpt-4` (0613) | East US <br> East US 2 <br> Japan East <br> UK South |
138152

139153
#### Azure Government regions
140154

@@ -144,7 +158,6 @@ The following GPT-4 models are available with [Azure Government](/azure/azure-go
144158
|--|--|
145159
| `gpt-4` (1106-Preview) | US Gov Virginia<br>US Gov Arizona |
146160

147-
148161
### GPT-3.5 models
149162

150163
> [!IMPORTANT]
@@ -159,19 +172,20 @@ See [model versions](../concepts/model-versions.md) to learn about how Azure Ope
159172
> [!NOTE]
160173
> Version `0613` of `gpt-35-turbo` and `gpt-35-turbo-16k` will be retired no earlier than June 13, 2024. Version `0301` of `gpt-35-turbo` will be retired no earlier than July 5, 2024. See [model updates](../how-to/working-with-models.md#model-updates) for model upgrade behavior.
161174
162-
### GPT-3.5-Turbo model availability
175+
| Model ID | Max Request (tokens) | Training Data (up to) |
176+
| --------- |:------:|:----:|
177+
| `gpt-35-turbo`**<sup>1</sup>** (0301) | 4,096 | Sep 2021 |
178+
| `gpt-35-turbo` (0613) | 4,096 | Sep 2021 |
179+
| `gpt-35-turbo-16k` (0613) | 16,384 | Sep 2021 |
180+
| `gpt-35-turbo-instruct` (0914) | 4,097 |Sep 2021 |
181+
| `gpt-35-turbo` (1106) | Input: 16,385<br> Output: 4,096 | Sep 2021|
182+
| `gpt-35-turbo` (0125) **NEW** | 16,385 | Sep 2021 |
163183

184+
### GPT-3.5-Turbo model availability
164185

165186
#### Public cloud regions
166187

167-
| Model ID | Model Availability | Max Request (tokens) | Training Data (up to) |
168-
| --------- | -------------------- |:------:|:----:|
169-
| `gpt-35-turbo`**<sup>1</sup>** (0301) | East US <br> France Central <br> South Central US <br> UK South <br> West Europe | 4,096 | Sep 2021 |
170-
| `gpt-35-turbo` (0613) | Australia East <br> Canada East <br> East US <br> East US 2 <br> France Central <br> Japan East <br> North Central US <br> Sweden Central <br> Switzerland North <br> UK South | 4,096 | Sep 2021 |
171-
| `gpt-35-turbo-16k` (0613) | Australia East <br> Canada East <br> East US <br> East US 2 <br> France Central <br> Japan East <br> North Central US <br> Sweden Central <br> Switzerland North<br> UK South | 16,384 | Sep 2021 |
172-
| `gpt-35-turbo-instruct` (0914) | East US <br> Sweden Central | 4,097 |Sep 2021 |
173-
| `gpt-35-turbo` (1106) | Australia East <br> Canada East <br> France Central <br> South India <br> Sweden Central<br> UK South <br> West US | Input: 16,385<br> Output: 4,096 | Sep 2021|
174-
|`gpt-35-turbo` (0125) **NEW** | Canada East <br> North Central US <br> South Central US | 16,385 | Sep 2021 |
188+
[!INCLUDE [GPT-35-Turbo](../includes/model-matrix/standard-gpt-35-turbo.md)]
175189

176190
**<sup>1</sup>** This model will accept requests > 4,096 tokens. It is not recommended to exceed the 4,096 input token limit as the newer version of the model are capped at 4,096 tokens. If you encounter issues when exceeding 4,096 input tokens with this model this configuration is not officially supported.
177191

@@ -182,16 +196,20 @@ These models can only be used with Embedding API requests.
182196
> [!NOTE]
183197
> `text-embedding-3-large` is the latest and most capable embedding model. Upgrading between embedding models is not possible. In order to migrate from using `text-embedding-ada-002` to `text-embedding-3-large` you would need to generate new embeddings.
184198
185-
| Model ID | Model Availability | Max Request (tokens) | Output Dimensions |Training Data (up-to)
199+
| Model ID | Max Request (tokens) | Output Dimensions |Training Data (up-to)
186200
|---|---| :---:|:---:|:---:|
187-
| `text-embedding-ada-002` (version 2) | Australia East <br> Canada East <br> East US <br> East US2 <br> France Central <br> Japan East <br> North Central US <br> Norway East <br> South Central US <br> Sweden Central <br> Switzerland North <br> UK South <br> West Europe <br> West US |8,191 | 1,536 | Sep 2021 |
188-
| `text-embedding-ada-002` (version 1) | East US <br> South Central US <br> West Europe |2,046 | 1,536 | Sep 2021 |
189-
| `text-embedding-3-large` | Canada East, East US, East US 2 | 8,191 | 3,072 |Sep 2021 |
190-
| `text-embedding-3-small` | Canada East, East US, East US 2 | 8,191| 1,536 | Sep 2021 |
201+
| `text-embedding-ada-002` (version 2) |8,191 | 1,536 | Sep 2021 |
202+
| `text-embedding-ada-002` (version 1) |2,046 | 1,536 | Sep 2021 |
203+
| `text-embedding-3-large` | 8,191 | 3,072 |Sep 2021 |
204+
| `text-embedding-3-small` | 8,191| 1,536 | Sep 2021 |
191205

192206
> [!NOTE]
193207
> When sending an array of inputs for embedding, the max number of input items in the array per call to the embedding endpoint is 2048.
194208
209+
#### Public cloud regions
210+
211+
[!INCLUDE [Embeddings](../includes/model-matrix/standard-embeddings.md)]
212+
195213
#### Azure Government regions
196214

197215
The following Embeddings models are available with [Azure Government](/azure/azure-government/documentation-government-welcome):
@@ -221,7 +239,6 @@ The following Embeddings models are available with [Azure Government](/azure/azu
221239
| `gpt-35-turbo` (1106) | North Central US <br> Sweden Central | Input: 16,385<br> Output: 4,096 | Sep 2021|
222240
| `gpt-35-turbo` (0125) | North Central US <br> Sweden Central | 16,385 | Sep 2021 |
223241

224-
225242
### Whisper models
226243

227244
| Model ID | Model Availability | Max Request (audio file size) |

‎articles/ai-services/openai/includes/model-matrix/quota.md

Lines changed: 31 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
---
2+
title: 'Quota regional limits'
3+
titleSuffix: Azure OpenAI Service
4+
description: Quota and limits for Azure OpenAI by region.
5+
manager: nitinme
6+
ms.service: azure-ai-openai
7+
ms.topic: include
8+
ms.date: 03/13/2024
9+
---
10+
11+
The default quota for models varies by model and region. Default quota limits are subject to change.
12+
13+
| Region | GPT-4 | GPT-4-32K | GPT-4-Turbo | GPT-4-Turbo-V | GPT-35-Turbo | GPT-35-Turbo-Instruct | Text-Embedding-Ada-002 | text-embedding-3-small | text-embedding-3-large | Babbage-002 | Babbage-002 - finetune | Davinci-002 | Davinci-002 - finetune | GPT-35-Turbo - finetune | GPT-35-Turbo-1106 - finetune | GPT-35-Turbo-0125 - finetune |
14+
|:-----------------|:-------:|:-----------:|:-------------:|:---------------:|:--------------:|:-----------------------:|:------------------------:|:------------------------:|:------------------------:|:-------------:|:------------------------:|:-------------:|:------------------------:|:-------------------------:|:------------------------------:|:-------------------------------|
15+
| australiaeast | 40 K | 80 K | 80 K | 30 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
16+
| brazilsouth | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
17+
| canadaeast | 40 K | 80 K | 80 K | - | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | - | - | - |
18+
| eastus | - | - | 80 K | - | 240 K | 240 K | 240 K | 350 K | 350 K | - | - | - | - | - | - | - |
19+
| eastus2 | 40 K | 80 K | 80 K | - | 300 K | - | 350 K | 350 K | 350 K | - | - | - | - | - | - | - |
20+
| francecentral | 20 K | 60 K | 80 K | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
21+
| japaneast | 40 K | 80 K | - | 30 K | 313 K | - | 350 K | - | - | - | - | - | - | - | - | - |
22+
| northcentralus | - | - | 80 K | - | 300 K | - | 350 K | - | - | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
23+
| norwayeast | - | - | 150 K | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
24+
| southafricanorth | - | - | - | - | - | - | 350 K | - | - | - | - | - | - | - | - | - |
25+
| southcentralus | - | - | 80 K | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
26+
| southindia | - | - | 150 K | - | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
27+
| swedencentral | 40 K | 80 K | 150 K | 30 K | 305 K | 240 K | 350 K | - | - | 240 K | 250 K | 240 K | 250 K | 250 K | 250 K | 250 K |
28+
| switzerlandnorth | 40 K | 80 K | - | 30 K | 300 K | - | 350 K | - | - | - | - | - | - | - | - | - |
29+
| uksouth | 40 K | 80 K | 80 K | - | 240 K | - | 350 K | - | - | - | - | - | - | - | - | - |
30+
| westeurope | - | - | - | - | 240 K | - | 240 K | - | - | - | - | - | - | - | - | - |
31+
| westus | - | - | 80 K | 30 K | 300 K | - | 350 K | - | - | - | - | - | - |

‎articles/ai-services/openai/includes/model-matrix/standard-embeddings.md

Lines changed: 29 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
1+
---
2+
title: Standard Embeddings models
3+
titleSuffix: Azure OpenAI Service
4+
description: embedding model regional availability
5+
manager: nitinme
6+
ms.service: azure-ai-openai
7+
ms.topic: include
8+
ms.date: 03/13/2024
9+
---
10+
11+
| `Region` | `text-embedding-ada-002`, `2` | `text-embedding-ada-002`, `1` | `text-embedding-3-small`, `1` | `text-embedding-3-large`, `1` |
12+
|:-----------------|:---------------------------------:|:---------------------------------:|:---------------------------------:|:---------------------------------:|
13+
| australiaeast | ✅ | - | - | - |
14+
| brazilsouth | ✅ | - | - | - |
15+
| canadaeast | ✅ | - | ✅ | ✅ |
16+
| eastus | ✅ | ✅ | ✅ | ✅ |
17+
| eastus2 | ✅ | - | ✅ | ✅ |
18+
| francecentral | ✅ | - | - | - |
19+
| japaneast | ✅ | - | - | - |
20+
| northcentralus | ✅ | - | - | - |
21+
| norwayeast | ✅ | - | - | - |
22+
| southafricanorth | ✅ | - | - | - |
23+
| southcentralus | ✅ | ✅ | - | - |
24+
| southindia | ✅ | - | - | - |
25+
| swedencentral | ✅ | - | - | - |
26+
| switzerlandnorth | ✅ | - | - | - |
27+
| uksouth | ✅ | - | - | - |
28+
| westeurope | ✅ | - | - | - |
29+
| westus | ✅ | - | - | - |

0 commit comments

Comments
 (0)