Skip to content

Commit 5c68e4e

Browse files
JillGrant615JillGrant615
authored
Merge pull request #4455 from aahill/ptu-apr-2
updating PTU
2 parents 0be805e + dd8e207 commit 5c68e4e

File tree

4 files changed

+44
-43
lines changed

4 files changed

+44
-43
lines changed

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

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -43,7 +43,7 @@ Azure OpenAI Service is powered by a diverse set of models with different capabi
4343

4444
| Model ID | Description | Context Window | Max Output Tokens | Training Data (up to) |
4545
| --- | :--- |:--- |:---|:---: |
46-
| `gpt-4.1` (2025-04-14) | - Text & image input <br> - Text output <br> - Chat completions API <br>- Responses API <br> - Streaming <br> - Function calling <br> Structured outputs (chat completions) | 1,047,576 | 32,768 | May 31, 2024 |
46+
| `gpt-4.1` (2025-04-14) | - Text & image input <br> - Text output <br> - Chat completions API <br>- Responses API <br> - Streaming <br> - Function calling <br> Structured outputs (chat completions) | - 1,047,576 <br> - 128,000 (provisioned managed deployments) | 32,768 | May 31, 2024 |
4747
| `gpt-4.1-nano` (2025-04-14) <br><br> **Fastest 4.1 model** | - Text & image input <br> - Text output <br> - Chat completions API <br>- Responses API <br> - Streaming <br> - Function calling <br> Structured outputs (chat completions) | 1,047,576 | 32,768 | May 31, 2024 |
4848
| `gpt-4.1-mini` (2025-04-14) | - Text & image input <br> - Text output <br> - Chat completions API <br>- Responses API <br> - Streaming <br> - Function calling <br> Structured outputs (chat completions) | 1,047,576 | 32,768 | May 31, 2024 |
4949

‎articles/ai-services/openai/concepts/provisioned-throughput.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -3,7 +3,7 @@ title: Azure OpenAI Service provisioned throughput
33
description: Learn about provisioned throughput and Azure OpenAI.
44
ms.service: azure-ai-openai
55
ms.topic: conceptual
6-
ms.date: 03/31/2025
6+
ms.date: 04/30/2025
77
manager: nitinme
88
author: aahill #ChrisHMSFT
99
ms.author: aahi #chrhoder

‎articles/ai-services/openai/how-to/provisioned-throughput-onboarding.md

Lines changed: 13 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -72,23 +72,24 @@ Customers that require long-term usage of provisioned, data zoned provisioned, a
7272
> Charges for deployments on a deleted resource will continue until the resource is purged. To prevent this, delete a resource’s deployment before deleting the resource. For more information, see [Recover or purge deleted Azure AI services resources](../../recover-purge-resources.md).
7373
7474
## How much throughput per PTU you get for each model
75-
The amount of throughput (measured in tokens per minute or TPM) a deployment gets per PTU is a function of the input and output tokens in a given minute.
7675

77-
Generating output tokens requires more processing than input tokens. For the models specified in the table below, 1 output token counts as 3 input tokens towards your TPM-per-PTU limit. The service dynamically balances the input & output costs, so users do not have to set specific input and output limits. This approach means your deployment is resilient to fluctuations in the workload.
7876

79-
To help with simplifying the sizing effort, the following table outlines the TPM-per-PTU for the specified models. To understand the impact of output tokens on the TPM-per-PTU limit, use the 3 input token to 1 output token ratio.
8077

81-
For a detailed understanding of how different ratios of input and output tokens impact the throughput your workload needs, see the [Azure OpenAI capacity calculator](https://ai.azure.com/resource/calculator). The table also shows Service Level Agreement (SLA) Latency Target Values per model. For more information about the SLA for Azure OpenAI Service, see the [Service Level Agreements (SLA) for Online Services page](https://www.microsoft.com/licensing/docs/view/Service-Level-Agreements-SLA-for-Online-Services?lang=1)
8278

8379

84-
|Topic| **gpt-4o** | **gpt-4o-mini** | **o1**|
85-
| --- | --- | --- | --- |
86-
|Global & data zone provisioned minimum deployment|15|15|15|
87-
|Global & data zone provisioned scale increment|5|5|5|
88-
|Regional provisioned minimum deployment|50|25|50|
89-
|Regional provisioned scale increment|50|25|50|
90-
|Input TPM per PTU |2,500|37,000|230|
91-
|Latency Target Value |25 Tokens Per Second|33 Tokens Per Second|25 Tokens Per Second|
80+
The amount of throughput (measured in tokens per minute or TPM) a deployment gets per PTU is a function of the input and output tokens in a given minute. Generating output tokens requires more processing than input tokens.  Starting with GPT 4.1 models and later, the system matches the global standard price ratio between input and output tokens. Cached tokens are deducted 100% from the utilization.
81+
82+
For example, for `gpt-4.1:2025-04-14`, 1 output token counts as 4 input tokens towards your utilization limit which matches the [pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/). Older models use a different ratio and for a deeper understanding on how different ratios of input and output tokens impact the throughput your workload needs, see the [Azure OpenAI capacity calculator](https://ai.azure.com/resource/calculator).
83+
84+
85+
|Topic| **gpt-4o** | **gpt-4o-mini** | **o1**| gpt-4.1 |
86+
| --- | --- | --- | --- | --- |
87+
|Global & data zone provisioned minimum deployment|15|15|15|15 |
88+
|Global & data zone provisioned scale increment|5|5|5| 5 |
89+
|Regional provisioned minimum deployment|50|25|50| 50 |
90+
|Regional provisioned scale increment|50|25|50| 50 |
91+
|Input TPM per PTU |2,500|37,000|230| 3000 |
92+
|Latency Target Value |25 Tokens Per Second|33 Tokens Per Second|25 Tokens Per Second| 44 Tokens Per Second |
9293

9394
For a full list, see the [Azure OpenAI Service in Azure AI Foundry portal calculator](https://ai.azure.com/resource/calculator).
9495

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

Lines changed: 29 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -6,34 +6,34 @@ manager: nitinme
66
ms.service: azure-ai-openai
77
ms.topic: include
88
ms.custom: references_regions
9-
ms.date: 03/31/2025
9+
ms.date: 05/01/2025
1010
---
1111

12-
| **Region** | **o3-mini**, **2025-01-31** | **o1**, **2024-12-17** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o**, **2024-11-20** | **gpt-4o-mini**, **2024-07-18** |
13-
|:-------------------|:---------------------------:|:----------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
14-
| australiaeast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
15-
| brazilsouth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
16-
| canadaeast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
17-
| eastus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
18-
| eastus2 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
19-
| francecentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
20-
| germanywestcentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
21-
| italynorth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
22-
| japaneast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
23-
| koreacentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
24-
| northcentralus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
25-
| norwayeast | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
26-
| polandcentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
27-
| southafricanorth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
28-
| southcentralus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
29-
| southeastasia | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
30-
| southindia | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
31-
| spaincentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
32-
| swedencentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
33-
| switzerlandnorth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
34-
| switzerlandwest | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
35-
| uaenorth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
36-
| uksouth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
37-
| westeurope | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
38-
| westus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
39-
| westus3 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
12+
| **Region** | **gpt-4.1**, **2025-04-14** | **o3-mini**, **2025-01-31** | **o1**, **2024-12-17** | **gpt-4o**, **2024-05-13** | **gpt-4o**, **2024-08-06** | **gpt-4o**, **2024-11-20** | **gpt-4o-mini**, **2024-07-18** |
13+
|:-------------------|:---------------------------:|:---------------------------:|:----------------------:|:--------------------------:|:--------------------------:|:--------------------------:|:-------------------------------:|
14+
| australiaeast | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
15+
| brazilsouth | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
16+
| canadaeast | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
17+
| eastus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
18+
| eastus2 | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
19+
| francecentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
20+
| germanywestcentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
21+
| italynorth | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
22+
| japaneast | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
23+
| koreacentral | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
24+
| northcentralus | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
25+
| norwayeast | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
26+
| polandcentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
27+
| southafricanorth | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
28+
| southcentralus | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
29+
| southeastasia | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
30+
| southindia | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
31+
| spaincentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
32+
| swedencentral | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
33+
| switzerlandnorth | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
34+
| switzerlandwest | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
35+
| uaenorth | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
36+
| uksouth | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
37+
| westeurope | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
38+
| westus | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
39+
| westus3 | - | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |

0 commit comments

Comments
 (0)