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/language-service/overview.md
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ author: laujan
6
6
manager: nitinme
7
7
ms.service: azure-ai-language
8
8
ms.topic: overview
9
-
ms.date: 03/05/2025
9
+
ms.date: 05/28/2025
10
10
ms.author: lajanuar
11
11
---
12
12
@@ -24,6 +24,7 @@ The Language service also provides several new features as well, which can eithe
24
24
* Customizable, which means you train an AI model using our tools to fit your data specifically.
25
25
26
26
Language features are also utilized in [agent templates](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/agent-catalog):
27
+
27
28
*[Intent routing agent](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/agent-catalog/msft-agent-samples/foundry-agent-service-sdk/intent-routing-agent) detects user intent and provides exact answering. Perfect for deterministically intent routing and exact question answering with human controls.
28
29
*[Exact question answering agent](https://github.com/azure-ai-foundry/foundry-samples/tree/main/samples/agent-catalog/msft-agent-samples/foundry-agent-service-sdk/exact-qna-agent) answers high-value predefined questions deterministically to ensure consistent and accurate responses.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/how-to/provisioned-throughput-onboarding.md
+9-9Lines changed: 9 additions & 9 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,7 +3,7 @@ title: Understanding costs associated with provisioned throughput units (PTU)
3
3
description: Learn about provisioned throughput costs and billing in Azure OpenAI.
4
4
ms.service: azure-ai-openai
5
5
ms.topic: conceptual
6
-
ms.date: 05/20/2025
6
+
ms.date: 05/28/2025
7
7
manager: nitinme
8
8
author: aahill
9
9
ms.author: aahi
@@ -77,14 +77,14 @@ The amount of throughput (measured in tokens per minute or TPM) a deployment get
77
77
78
78
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).
|Input TPM per PTU|3,000|14,900| 59,400 | 600 | 2,500|230|2,500|37,000|
87
-
|Latency Target Value|44 Tokens Per Second|50 Tokens Per Second|50 Tokens Per Second | 40 Tokens Per Second | 66 Tokens Per Second |25 Tokens Per Second|25 Tokens Per Second|33 Tokens Per Second|
|Input TPM per PTU|5,400 |3,000|14,900| 59,400 | 600 | 2,500|230|2,500|37,000|
87
+
|Latency Target Value| 66 Tokens Per Second| 40 Tokens Per Second|50 Tokens Per Second|60 Tokens Per Second | 40 Tokens Per Second | 66 Tokens Per Second |25 Tokens Per Second|25 Tokens Per Second|33 Tokens Per Second|
88
88
89
89
90
90
For a full list, see the [Azure OpenAI in Azure AI Foundry Models in Azure AI Foundry portal calculator](https://ai.azure.com/resource/calculator).
0 commit comments