Skip to content

Commit d920603

Browse files
committed
models
1 parent c2d7308 commit d920603

File tree

2 files changed

+31
-15
lines changed

2 files changed

+31
-15
lines changed

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

Lines changed: 28 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -61,20 +61,22 @@ For a tutorial on DeepSeek-R1, see [Tutorial: Get started with DeepSeek-R1 reaso
6161

6262
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=deepseek).
6363

64+
### Microsoft
65+
66+
Microsoft models include various model groups such as MAI models, Phi models, healthcare AI models, and more. Some Microsoft models are offered as [Azure Ecosystem Models](#azure-ecosystem-models). 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).
67+
68+
69+
| Model | Type | Tier | Capabilities |
70+
| ------ | ---- | --- | ------------ |
71+
| [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. |
72+
6473
### Mistral AI
6574

66-
Mistral AI offers two categories of models: premium models including Mistral Large and Mistral Small and open models including Mistral Nemo.
75+
Mistral AI offers two categories of models: premium models including Mistral Large and Mistral Small and open models including Mistral Nemo. Some Mistral models are offered as [Azure Ecosystem Models](#azure-ecosystem-models).
6776

6877
| Model | Type | Tier | Capabilities |
6978
| ------ | ---- | --- | ------------ |
70-
| [Mistral-small-2503](https://ai.azure.com/explore/models/Mistral-small-2503/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
71-
| [Mistral-Large-2411](https://ai.azure.com/explore/models/Mistral-Large-2411/version/2/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (128,000 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
7279
| [Codestral-2501](https://ai.azure.com/explore/models/Codestral-2501/version/2/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (262,144 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** en <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
73-
| [Ministral-3B](https://ai.azure.com/explore/models/Ministral-3B/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
74-
| [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
75-
| [Mistral-large-2407](https://ai.azure.com/explore/models/Mistral-large-2407/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
76-
| [Mistral-small](https://ai.azure.com/explore/models/Mistral-small/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
77-
| [Mistral-large](https://ai.azure.com/explore/models/Mistral-large/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
7880

7981
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=mistral).
8082

@@ -84,7 +86,8 @@ Meta Llama models and tools are a collection of pretrained and fine-tuned genera
8486

8587
| Model | Type | Tier | Capabilities |
8688
| ------ | ---- | --- | ------------ |
87-
| [Llama-4-Instruct](https://ai.azure.com/explore/models/Llama-3.3-70B-Instruct/version/4/registry/azureml-meta) | chat-completion | Global standard | - **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 |
89+
| [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 | Global standard | - **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 |
90+
| [Llama-3.3-70B-Instruct](https://ai.azure.com/explore/models/Llama-3.3-70B-Instruct/version/4/registry/azureml-meta) | chat-completion | Global standard | - **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 |
8891

8992
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=meta).
9093

@@ -142,7 +145,6 @@ Meta Llama models and tools are a collection of pretrained and fine-tuned genera
142145

143146
| Model | Type | Tier | Capabilities |
144147
| ------ | ---- | --- | ------------ |
145-
| [Llama-3.3-70B-Instruct](https://ai.azure.com/explore/models/Llama-3.3-70B-Instruct/version/4/registry/azureml-meta) | chat-completion | Global standard | - **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 |
146148
| [Llama-3.2-11B-Vision-Instruct](https://ai.azure.com/explore/models/Llama-3.2-11B-Vision-Instruct/version/1/registry/azureml-meta) | chat-completion | Global standard | - **Input:** text and image (128,000 tokens) <br /> - **Output:** (8,192 tokens) <br /> - **Languages:** `en` <br /> - **Tool calling:** No* <br /> - **Response formats:** Text |
147149
| [Llama-3.2-90B-Vision-Instruct](https://ai.azure.com/explore/models/Llama-3.2-90B-Vision-Instruct/version/1/registry/azureml-meta) | chat-completion | Global standard | - **Input:** text and image (128,000 tokens) <br /> - **Output:** (8,192 tokens) <br /> - **Languages:** `en` <br /> - **Tool calling:** No* <br /> - **Response formats:** Text |
148150
| [Meta-Llama-3.1-405B-Instruct](https://ai.azure.com/explore/models/Meta-Llama-3.1-405B-Instruct/version/1/registry/azureml-meta) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (8,192 tokens) <br /> - **Languages:** `en`, `de`, `fr`, `it`, `pt`, `hi`, `es`, and `th` <br /> - **Tool calling:** No* <br /> - **Response formats:** Text |
@@ -178,6 +180,22 @@ Microsoft models include various model groups such as MAI models, Phi models, he
178180

179181
See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=phi).
180182

183+
### Mistral AI
184+
185+
Mistral AI offers two categories of models: premium models including Mistral Large and Mistral Small and open models including Mistral Nemo.
186+
187+
| Model | Type | Tier | Capabilities |
188+
| ------ | ---- | --- | ------------ |
189+
| [Mistral-small-2503](https://ai.azure.com/explore/models/Mistral-small-2503/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
190+
| [Mistral-Large-2411](https://ai.azure.com/explore/models/Mistral-Large-2411/version/2/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (128,000 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
191+
| [Ministral-3B](https://ai.azure.com/explore/models/Ministral-3B/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
192+
| [Mistral-Nemo](https://ai.azure.com/explore/models/Mistral-Nemo/version/1/registry/azureml-mistral) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
193+
| [Mistral-large-2407](https://ai.azure.com/explore/models/Mistral-large-2407/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (131,072 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** `en`, `fr`, `de`, `es`, `it`, `zh`, `ja`, `ko`, `pt`, `nl`, and `pl` <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
194+
| [Mistral-small](https://ai.azure.com/explore/models/Mistral-small/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** text (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
195+
| [Mistral-large](https://ai.azure.com/explore/models/Mistral-large/version/1/registry/azureml-mistral) <br> (deprecated) | chat-completion | Global standard | - **Input:** text (32,768 tokens) <br /> - **Output:** (4,096 tokens) <br /> - **Languages:** fr, de, es, it, and en <br /> - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON |
196+
197+
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=mistral).
198+
181199
### NTT Data
182200

183201
**tsuzumi** is an autoregressive language optimized transformer. The tuned versions use supervised fine-tuning (SFT). tsuzumi handles both Japanese and English language with high efficiency.

articles/ai-foundry/model-inference/faq.yml

Lines changed: 3 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -17,13 +17,11 @@ sections:
1717
- name: General
1818
questions:
1919
- question: |
20-
What's the difference between Azure OpenAI in Foundry Models and Foundry Models?
20+
What's the difference between Azure OpenAI and Foundry Models?
2121
answer: |
22-
Azure OpenAI gives customers access to advanced language models from OpenAI. Foundry Models extends such capability giving customers access to all the flagship models in Azure AI under the same service, endpoint, and credentials. It includes Azure OpenAI, Cohere, Mistral AI, Meta Llama, AI21 labs, etc. Customers can seamlessly switch between models without changing their code.
22+
Azure OpenAI gives customers access to advanced language models from OpenAI. Foundry Models extends such capability giving customers access to all the flagship models in Azure AI Foundry under the same service, endpoint, and credentials. It includes Azure OpenAI, Cohere, Mistral AI, Meta Llama, AI21 labs, etc. Customers can seamlessly switch between models without changing their code.
2323
24-
Both Azure OpenAI and Foundry Models are part of the Azure AI Foundry services (formerly known Azure AI Services) family and build on top of the same security and enterprise promise of Azure.
25-
26-
While Foundry Models focus on inference, Azure OpenAI can be used with more advanced APIs like batch, fine-tuning, assistants, and files.
24+
Azure OpenAI is an Azure Direct model family in Foundry Models.
2725
- question: |
2826
What's the difference between Azure AI services and Azure AI Foundry?
2927
answer: |

0 commit comments

Comments
 (0)