Merge pull request #5646 from MicrosoftDocs/main

6/20/2025 AM Publish

Author: Taojunshen

articles/ai-foundry/model-inference/concepts/models.md

@@ -180,7 +180,6 @@ Microsoft models include various model groups such as MAI models, Phi models, he
 
 | Model  | Type | Tier | Capabilities |
 | ------ | ---- | --- | ------------ |
-| [MAI-DS-R1](https://ai.azure.com/explore/models/MAI-DS-R1/version/1/registry/azureml) |  chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | Global standard | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. |
 | [Phi-4-mini-instruct](https://ai.azure.com/explore/models/Phi-4-mini-instruct/version/1/registry/azureml) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:**  (4,096 tokens) <br /> - **Languages:** `ar`, `zh`, `cs`, `da`, `nl`, `en`, `fi`, `fr`, `de`, `he`, `hu`, `it`, `ja`, `ko`, `no`, `pl`, `pt`, `ru`, `es`, `sv`, `th`, `tr`, and `uk` <br />  - **Tool calling:** No <br /> - **Response formats:** Text |
 | [Phi-4-multimodal-instruct](https://ai.azure.com/explore/models/Phi-4-multimodal-instruct/version/1/registry/azureml) | chat-completion | Global standard | - **Input:** text, images, and audio (131,072 tokens) <br /> - **Output:**  (4,096 tokens) <br /> - **Languages:** `ar`, `zh`, `cs`, `da`, `nl`, `en`, `fi`, `fr`, `de`, `he`, `hu`, `it`, `ja`, `ko`, `no`, `pl`, `pt`, `ru`, `es`, `sv`, `th`, `tr`, and `uk` <br />  - **Tool calling:** No <br /> - **Response formats:** Text |
 | [Phi-4](https://ai.azure.com/explore/models/Phi-4/version/2/registry/azureml) | chat-completion | Global standard | - **Input:** text (16,384 tokens) <br /> - **Output:**  (16,384 tokens) <br /> - **Languages:** `en`, `ar`, `bn`, `cs`, `da`, `de`, `el`, `es`, `fa`, `fi`, `fr`, `gu`, `ha`, `he`, `hi`, `hu`, `id`, `it`, `ja`, `jv`, `kn`, `ko`, `ml`, `mr`, `nl`, `no`, `or`, `pa`, `pl`, `ps`, `pt`, `ro`, `ru`, `sv`, `sw`, `ta`, `te`, `th`, `tl`, `tr`, `uk`, `ur`, `vi`, `yo`, and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text |

articles/ai-foundry/model-inference/includes/use-chat-reasoning/about-reasoning.md

@@ -9,7 +9,7 @@ author: santiagxf
 
 ## Reasoning models
 
-Reasoning models can reach higher levels of performance in domains like math, coding, science, strategy, and logistics. The way these models produces outputs is by explicitly using chain of thought to explore all possible paths before generating an answer. They verify their answers as they produce them which helps them to arrive to better more accurate conclusions. This means that reasoning models may require less context in prompting in order to produce effective results. 
+Reasoning models can reach higher levels of performance in domains like math, coding, science, strategy, and logistics. The way these models produce outputs is by explicitly using chain of thought to explore all possible paths before generating an answer. They verify their answers as they produce them which helps them to arrive to better more accurate conclusions. This means that reasoning models may require less context in prompting in order to produce effective results. 
 
 Such way of scaling model's performance is referred as *inference compute time* as it trades performance against higher latency and cost. It contrasts to other approaches that scale through *training compute time*. 
 
@@ -19,4 +19,4 @@ Reasoning models then produce two types of outputs:
 > * Reasoning completions
 > * Output completions
 
-Both of these completions count towards content generated from the model and hence, towards the token limits and costs associated with the model. Some models may output the reasoning content, like `DeepSeek-R1`. Some others, like `o1`, only outputs the output piece of the completions.
+Both of these completions count towards content generated from the model and hence, towards the token limits and costs associated with the model. Some models may output the reasoning content, like `DeepSeek-R1`. Some others, like `o1`, only outputs the output piece of the completions.

articles/ai-services/openai/how-to/fine-tuning-direct-preference-optimization.md

@@ -51,7 +51,7 @@ Training datasets must be in `jsonl` format:
 
 ## Direct preference optimization model support
 
-- `gpt-4o-2024-08-06` supports direct preference optimization in its respective fine-tuning regions. Latest region availability is updated in the [models page](../concepts/models.md#fine-tuning-models)
+- `gpt-4o-2024-08-06`,`gpt-4.1-2025-04-14`,`gpt-4.1-mini-2025-04-14`  supports direct preference optimization in its respective fine-tuning regions. Latest region availability is updated in the [models page](../concepts/models.md#fine-tuning-models)
 
 Users can use preference fine tuning with base models as well as models that have already been fine-tuned using supervised fine-tuning as long as they are of a supported model/version.
 
@@ -70,4 +70,4 @@ Users can use preference fine tuning with base models as well as models that hav
 
 - Explore the fine-tuning capabilities in the [Azure OpenAI fine-tuning tutorial](../tutorials/fine-tune.md).
 - Review fine-tuning [model regional availability](../concepts/models.md#fine-tuning-models)
-- Learn more about [Azure OpenAI quotas](../quotas-limits.md)
+- Learn more about [Azure OpenAI quotas](../quotas-limits.md)

articles/ai-services/openai/includes/global-batch-limits.md

@@ -24,19 +24,25 @@ The table shows the batch quota limit. Quota values for global batch are represe
 
 |Model|Enterprise agreement|Default| Monthly credit card based subscriptions | MSDN subscriptions | Azure for Students, Free Trials |
 |---|---|---|---|---|---|
+| `gpt-4.1`| 5 B | 200 M | 50 M | 90 K | N/A |
+| `gpt-4.1 mini` | 15B | 1B | 50M | 90k | N/A |
+| `gpt-4.1-nano` | 15 B | 1 B | 50 M | 90 K | N/A |
 | `gpt-4o` | 5 B | 200 M | 50 M | 90 K | N/A|
 | `gpt-4o-mini` | 15 B | 1 B | 50 M | 90 K | N/A |
 | `gpt-4-turbo` | 300 M | 80 M | 40 M | 90 K | N/A |
 | `gpt-4` | 150 M | 30 M | 5 M | 100 K | N/A |
 | `gpt-35-turbo` | 10 B | 1 B | 100 M | 2 M | 50 K |
 | `o3-mini`| 15 B | 1 B | 50 M | 90 K | N/A |
+| `o4-mini` | 15 B | 1 B | 50 M | 90 K | N/A |
 
 B = billion | M = million | K = thousand
 
 ### Data zone batch
 
 |Model|Enterprise agreement|Default| Monthly credit card based subscriptions | MSDN subscriptions | Azure for Students, Free Trials |
 |---|---|---|---|---|---|
+| `gpt-4.1` | 500 M | 30 M | 30 M | 90 K | N/A|
+| `gpt-4.1-mini` | 1.5 B | 100 M | 50 M | 90 K | N/A |
 | `gpt-4o` | 500 M | 30 M | 30 M | 90 K | N/A|
 | `gpt-4o-mini` | 1.5 B | 100 M | 50 M | 90 K | N/A |
 | `o3-mini` | 1.5 B | 100 M | 50 M | 90 K | N/A |

articles/ai-services/openai/quotas-limits.md

@@ -128,11 +128,15 @@ The following sections provide you with a quick guide to the default quotas and
 
 | Model|Tier| Quota Limit in tokens per minute (TPM) | Requests per minute |
 |---|---|:---:|:---:|
+| `codex-mini`| Enterprise agreement | 10 K | 10 M |
+| `o3-pro` | Enterprise agreement | 160 | 1.6 M |
 | `o4-mini` | Enterprise agreement | 10 M | 10 K |
 | `o3` | Enterprise agreement | 10 M | 10 K |
 | `o3-mini` | Enterprise agreement | 50 M | 5 K |
 | `o1` & `o1-preview` | Enterprise agreement | 30 M | 5 K |
 | `o1-mini`| Enterprise agreement | 50 M | 5 K |
+| `codex-mini`| Default | 1 K | 1 M |
+| `o3-pro` | Default | 1.6 K | 16 M |
 | `o4-mini` | Default | 1 M | 1 K  |
 | `o3` | Default | 1 M | 1 K |
 | `o3-mini` | Default | 5 M | 500 |

articles/ai-services/openai/whats-new.md

@@ -22,7 +22,7 @@ This article provides a summary of the latest releases and major documentation u
 
 ### codex-mini & o3-pro models released
 
-- `codex-mini and `o3-pro` are now available. To learn more, see the [getting started with reasoning models page](./how-to/reasoning.md)
+- `codex-mini` and `o3-pro` are now available. To learn more, see the [getting started with reasoning models page](./how-to/reasoning.md)
 
 ## May 2025
 

articles/machine-learning/includes/machine-learning-sdk-v1.md

@@ -6,4 +6,4 @@ ms.date: 04/22/2022
 ms.author: sgilley
 ---
 
-**APPLIES TO:** :::image type="icon" source="../media/yes.png" border="false"::: [Python SDK azureml **v1**](/python/api/overview/azure/ml/?view=azure-ml-py&preserve-view=true)
+**APPLIES TO:** :::image type="icon" source="../media/yes.png" border="false"::: [Azure Machine Learning SDK v1 for Python](/python/api/overview/azure/ml/?view=azure-ml-py&preserve-view=true)