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-foundry/foundry-models/concepts/models.md
+28-46Lines changed: 28 additions & 46 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,7 +6,7 @@ author: msakande
6
6
ms.author: mopeakande
7
7
reviewer: santiagxf
8
8
ms.reviewer: fasantia
9
-
ms.date: 08/08/2025
9
+
ms.date: 09/03/2025
10
10
ms.service: azure-ai-model-inference
11
11
ms.topic: how-to
12
12
ms.custom:
@@ -35,38 +35,20 @@ Models sold directly by Azure include all Azure OpenAI models and specific, sele
35
35
36
36
### Azure OpenAI
37
37
38
-
Azure OpenAI in Azure AI Foundry Models offers a diverse set of models with different capabilities and price points. Learn more details at [Azure OpenAI Model availability](../../openai/concepts/models.md). These models include:
39
-
40
-
- State-of-the-art models designed to tackle reasoning and problem-solving tasks with increased focus and capability
41
-
- Models that can understand and generate natural language and code
42
-
- Models that can transcribe and translate speech to text
|[model-router](../../openai/concepts/models.md#model-router)| A model that intelligently selects from a set of underlying chat models to respond to a given prompt. |
51
-
|[computer-use-preview](../../openai/concepts/models.md#computer-use-preview)| An experimental model trained for use with the Responses API computer use tool. |
52
-
|[o-series models](../../openai/concepts/models.md#o-series-models)|[Reasoning models](../../openai/how-to/reasoning.md) with advanced problem solving and increased focus and capability. |
53
-
|[GPT-4o, GPT-4o mini, and GPT-4 Turbo](../../openai/concepts/models.md#gpt-4o-and-gpt-4-turbo)| Capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
54
-
|[GPT-4](../../openai/concepts/models.md#gpt-4)| A set of models that improve on GPT-3.5 and can understand and generate natural language and code. |
55
-
|[GPT-3.5](../../openai/concepts/models.md#gpt-35)| A set of models that improve on GPT-3 and can understand and generate natural language and code. |
56
-
|[Embeddings](../../openai/concepts/models.md#embeddings)| A set of models that can convert text into numerical vector form to facilitate text similarity. |
57
-
|[Image generation](../../openai/concepts/models.md#image-generation-models)| A series of models that can generate original images from natural language. |
58
-
|[Audio](../../openai/concepts/models.md#audio-models)| A series of models for speech to text, translation, and text to speech. GPT-4o audio models support either low latency *speech in, speech out* conversational interactions or audio generation. |
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?selectedCollection=OpenAI).
61
41
42
+
To learn more about the available Azure OpenAI models and their regions of availability, see [Azure OpenAI in Azure AI Foundry models](../../openai/concepts/models.md).
43
+
62
44
### Black Forest Labs models sold directly by Azure
63
45
64
46
The Black Forest Labs collection of image generation models include FLUX.1 Kontext [pro] for in-context generation and editing and FLUX1.1 [pro] for text-to-image generation.
65
47
66
-
| Model | Type | Capabilities | Project type |
67
-
| ------ | ---- | ------------ | ------------ |
68
-
|[FLUX.1-Kontext-pro](https://ai.azure.com/explore/models/FLUX.1-Kontext-pro/version/1/registry/azureml-blackforestlabs)| Image generation | - **Input:** text and image (5000 tokens and 1 image) <br /> - **Output:** One Image <br /> - **Tool calling:** No <br /> - **Response formats**: Image (PNG and JPG) | Foundry, Hub-based |
69
-
|[FLUX-1.1-pro](https://ai.azure.com/explore/models/FLUX-1.1-pro/version/1/registry/azureml-blackforestlabs)| Image generation | - **Input:** text (5000 tokens) <br /> - **Output:** One Image <br /> - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) | Hub-based |
48
+
| Model | Type | Capabilities |Region availability |Project type |
|[FLUX.1-Kontext-pro](https://ai.azure.com/explore/models/FLUX.1-Kontext-pro/version/1/registry/azureml-blackforestlabs)| Image generation | - **Input:** text and image (5000 tokens and 1 image) <br /> - **Output:** One Image <br /> - **Tool calling:** No <br /> - **Response formats**: Image (PNG and JPG) |- Global standard (all regions) |Foundry, Hub-based |
51
+
|[FLUX-1.1-pro](https://ai.azure.com/explore/models/FLUX-1.1-pro/version/1/registry/azureml-blackforestlabs)| Image generation | - **Input:** text (5000 tokens) <br /> - **Output:** One Image <br /> - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |- Global standard (all regions) |Hub-based |
70
52
71
53
72
54
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=black+forest+labs).
@@ -75,11 +57,11 @@ See [this model collection in Azure AI Foundry portal](https://ai.azure.com/expl
75
57
76
58
DeepSeek family of models includes DeepSeek-R1, which excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.
|[Llama-4-Maverick-17B-128E-Instruct-FP8](https://ai.azure.com/explore/models/Llama-4-Maverick-17B-128E-Instruct-FP8/version/1/registry/azureml-meta)| chat-completion | - **Input:** text and images (1M tokens) <br /> - **Output:** text (1M tokens) <br /> - **Languages:**`ar`, `en`, `fr`, `de`, `hi`, `id`, `it`, `pt`, `es`, `tl`, `th`, and `vi` <br /> - **Tool calling:** No* <br /> - **Response formats:** Text |- Global standard (all regions) |Foundry, Hub-based |
79
+
|[Llama-3.3-70B-Instruct](https://ai.azure.com/explore/models/Llama-3.3-70B-Instruct/version/4/registry/azureml-meta)| chat-completion | - **Input:** text (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Languages:**`en`, `de`, `fr`, `it`, `pt`, `hi`, `es`, and `th` <br /> - **Tool calling:** No* <br /> - **Response formats:** Text |- Global standard (all regions) |Foundry, Hub-based |
98
80
99
81
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Meta). There are also several Meta models available [from partners and community](#meta).
100
82
101
83
### Microsoft models sold directly by Azure
102
84
103
85
Microsoft models include various model groups such as MAI models, Phi models, healthcare AI models, and more. To see all the available Microsoft models, view [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=phi).
|[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)| - **Input:** text (163,840 tokens) <br /> - **Output:** (163,840 tokens) <br /> - **Languages:**`en` and `zh` <br /> - **Tool calling:** No <br /> - **Response formats:** Text. |- Global standard (all regions) | Foundry, Hub-based |
108
90
109
91
See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Microsoft). There are also several Microsoft models available [from partners and community](#microsoft).
110
92
111
93
### Mistral models sold directly by Azure
112
94
113
-
| Model | Type | Capabilities | Project type
114
-
| ------ | ---- | ------------ | ------------ |
115
-
|[mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral)| Image-to-Text | - **Input:** image or PDF pages ( 30 pages, max 30MB PDF file) <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Tool calling:** no <br /> - **Response formats:** Text, JSON, Markdown | Foundry |
95
+
| Model | Type | Capabilities |Region availability |Project type |
|[mistral-document-ai-2505](https://ai.azure.com/explore/models/mistral-document-ai-2505/version/1/registry/azureml-mistral)| Image-to-Text | - **Input:** image or PDF pages ( 30 pages, max 30MB PDF file) <br /> - **Output:** text <br /> - **Languages:** en <br /> - **Tool calling:** no <br /> - **Response formats:** Text, JSON, Markdown |- Global standard (all regions) <br> - Data zone standard (US) | Foundry |
116
98
117
99
See [the Mistral model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=Mistral+AI). There are also several Mistral models available [from partners and community](#mistral-ai).
118
100
@@ -121,10 +103,10 @@ See [the Mistral model collection in Azure AI Foundry portal](https://ai.azure.c
121
103
122
104
xAI's Grok 3 and Grok 3 Mini models are designed to excel in various enterprise domains. Grok 3, a non-reasoning model pretrained by the Colossus datacenter, is tailored for business use cases such as data extraction, coding, and text summarization, with exceptional instruction-following capabilities. It supports a 131,072 token context window, allowing it to handle extensive inputs while maintaining coherence and depth, and is adept at drawing connections across domains and languages. On the other hand, Grok 3 Mini is a lightweight reasoning model trained to tackle agentic, coding, mathematical, and deep science problems with test-time compute. It also supports a 131,072 token context window for understanding codebases and enterprise documents, and excels at using tools to solve complex logical problems in novel environments, offering raw reasoning traces for user inspection with adjustable thinking budgets.
Copy file name to clipboardExpand all lines: articles/ai-foundry/openai/concepts/models.md
+1-17Lines changed: 1 addition & 17 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -18,23 +18,7 @@ ms.custom:
18
18
19
19
# Azure OpenAI in Azure AI Foundry models
20
20
21
-
Azure OpenAI is powered by a diverse set of models with different capabilities and price points. Model availability varies by region and cloud. For Azure Government model availability, refer to [Azure OpenAI in Azure Government](../azure-government.md).
|[`model-router`](#model-router)| A model that intelligently selects from a set of underlying chat models to respond to a given prompt. |
30
-
|[`computer-use-preview`](#computer-use-preview)| An experimental model trained for use with the Responses API computer use tool. |
31
-
|[`o-series models`](#o-series-models)|[`Reasoning models`](../how-to/reasoning.md) with advanced problem solving and increased focus and capability. |
32
-
|[`GPT-4o, GPT-4o mini, and GPT-4 Turbo`](#gpt-4o-and-gpt-4-turbo)| Capable Azure OpenAI models with multimodal versions, which can accept both text and images as input. |
33
-
|[`GPT-4`](#gpt-4)| A set of models that improve on GPT-3.5 and can understand and generate natural language and code. |
34
-
|[`GPT-3.5`](#gpt-35)| A set of models that improve on GPT-3 and can understand and generate natural language and code. |
35
-
|[Embeddings](#embeddings)| A set of models that can convert text into numerical vector form to facilitate text similarity. |
36
-
|[`Image generation`](#image-generation-models)| A series of models that can generate original images from natural language. |
37
-
|[`Audio`](#audio-models)| A series of models for speech to text, translation, and text to speech. GPT-4o audio models support either low latency *speech in, speech out* conversational interactions or audio generation. |
0 commit comments