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
|[Llama-4-Scout-17B-16E-Instruct](https://aka.ms/aifoundry/landing/llama-4-scout-17b-16e-instruct)|[chat-completion](../how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)| - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
163
+
|[Llama-4-Scout-17B-16E-Instruct](https://aka.ms/aifoundry/landing/llama-4-scout-17b-16e-instruct)|[chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)| - **Input:** text and image (128,000 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
164
164
165
165
See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=meta). There are also several Meta models available as [models sold directly by Azure](#meta-models-sold-directly-by-azure).
166
166
@@ -173,8 +173,8 @@ Microsoft models include various model groups such as MAI models, Phi models, he
|[Phi-4-reasoning](https://aka.ms/azureai/landing/Phi-4-reasoning)|[chat-completion with reasoning content](../how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context)| - **Input:** text (32,768 tokens) <br /> - **Output:** text (32,768 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
177
-
|[Phi-4-mini-reasoning](https://aka.ms/azureai/landing/Phi-4-mini-reasoning)|[chat-completion with reasoning content](../how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context)| - **Input:** text (128,000 tokens) <br /> - **Output:** text (128,000 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
176
+
|[Phi-4-reasoning](https://aka.ms/azureai/landing/Phi-4-reasoning)|[chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context)| - **Input:** text (32,768 tokens) <br /> - **Output:** text (32,768 tokens) <br /> - **Languages:**`en` <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
177
+
|[Phi-4-mini-reasoning](https://aka.ms/azureai/landing/Phi-4-mini-reasoning)|[chat-completion with reasoning content](../model-inference/how-to/use-chat-reasoning.md?context=/azure/ai-foundry/context/context)| - **Input:** text (128,000 tokens) <br /> - **Output:** text (128,000 tokens) <br /> - **Languages:**`en` <br /> - **Tool calling:** No <br /> - **Response formats:** Text | Foundry, Hub-based |
178
178
179
179
See [the Microsoft model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=phi). There are also several Microsoft models available as [models sold directly by Azure](#microsoft-models-sold-directly-by-azure).
180
180
@@ -201,14 +201,7 @@ See [this model collection in Azure AI Foundry portal](https://ai.azure.com/expl
201
201
| ------ | ---- | ------------ |
202
202
|[tsuzumi-7b](https://ai.azure.com/explore/models/Tsuzumi-7b/version/1/registry/azureml-nttdata)| chat-completion | - **Input:** text (8,192 tokens) <br /> - **Output:** text (8,192 tokens) <br /> - **Languages:**`en` and `jp` <br /> - **Tool calling:** No <br /> - **Response formats:** Text |
203
203
204
-
## AI21 Labs
205
204
206
-
The Jamba family models are AI21's production-grade Mamba-based large language model (LLM) which uses AI21's hybrid Mamba-Transformer architecture. It's an instruction-tuned version of AI21's hybrid structured state space model (SSM) transformer Jamba model. The Jamba family models are built for reliable commercial use with respect to quality and performance.
## Other Foundry Models available for serverless API deployment
@@ -222,8 +215,8 @@ This section lists a selection of models available only through Serverless API d
222
215
|[Stable Diffusion 3.5 Large](https://ai.azure.com/explore/models/Stable-Diffusion-3.5-Large/version/1/registry/azureml-stabilityai)| Image generation | Partners and Community | - **Input:** text and image (1000 tokens and 1 image) <br /> - **Output:** 1 Image <br /> - **Tool calling:** No <br /> - **Response formats**: Image (PNG and JPG) |
223
216
|[Stable Image Core](https://ai.azure.com/explore/models/Stable-Image-Core/version/1/registry/azureml-stabilityai)| Image generation | Partners and Community | - **Input:** text (1000 tokens) <br /> - **Output:** 1 Image <br /> - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
224
217
|[Stable Image Ultra](https://ai.azure.com/explore/models/Stable-Image-Ultra/version/1/registry/azureml-stabilityai)| Image generation | Partners and Community | - **Input:** text (1000 tokens) <br /> - **Output:** 1 Image <br /> - **Tool calling:** No <br /> - **Response formats:** Image (PNG and JPG) |
225
-
|[Mistral-OCR-2503](https://aka.ms/aistudio/landing/mistral-ocr-2503)|[image to text](../../how-to/use-image-models.md)| Models sold directly by Azure | - **Input:** image or PDF pages (1,000 pages, max 50MB PDF file) <br> - **Output:** text <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON, Markdown |
226
-
|[Mistral-medium-2505](https://aka.ms/aistudio/landing/mistral-medium-2505)|[chat-completion](../how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)| Models sold directly by Azure | - **Input:** text (128,000 tokens), image <br /> - **Output:** text (128,000 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
218
+
|[Mistral-OCR-2503](https://aka.ms/aistudio/landing/mistral-ocr-2503)|[image to text](../how-to/use-image-models.md)| Models sold directly by Azure | - **Input:** image or PDF pages (1,000 pages, max 50MB PDF file) <br> - **Output:** text <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON, Markdown |
219
+
|[Mistral-medium-2505](https://aka.ms/aistudio/landing/mistral-medium-2505)|[chat-completion](../model-inference/how-to/use-chat-completions.md?context=/azure/ai-foundry/context/context)| Models sold directly by Azure | - **Input:** text (128,000 tokens), image <br /> - **Output:** text (128,000 tokens) <br /> - **Tool calling:** No <br /> - **Response formats:** Text, JSON |
227
220
|[Cohere-rerank-v3.5](https://ai.azure.com/explore/models/Cohere-rerank-v3.5/version/1/registry/azureml-cohere)| rerank <br> text classification | Partners and Community ||[Cohere's v2/rerank API](https://docs.cohere.com/v2/reference/rerank)|
228
221
|[Cohere-rerank-v3-english](https://ai.azure.com/explore/models/Cohere-rerank-v3-english/version/1/registry/azureml-cohere) <br> (deprecated) | rerank <br> text classification | Partners and Community ||[Cohere's v2/rerank API](https://docs.cohere.com/v2/reference/rerank) <br> [Cohere's v1/rerank API](https://docs.cohere.com/v1/reference/rerank)|
229
222
|[Cohere-rerank-v3-multilingual](https://ai.azure.com/explore/models/Cohere-rerank-v3-multilingual/version/1/registry/azureml-cohere) <br> (deprecated) | rerank <br> text classification | Partners and Community ||[Cohere's v2/rerank API](https://docs.cohere.com/v2/reference/rerank) <br> [Cohere's v1/rerank API](https://docs.cohere.com/v1/reference/rerank)|
0 commit comments