Statsig offers SDKs for integrating Azure AI models into server applications. These SDKs simplify the implementation of features like completions and embeddings in your server application. They provide easy-to-use APIs and automatically track metrics such as latency, token length, and model details, which you can use for optimization and experimentation. Use cases include:

* Implement Azure AI Models in your code with a [single lightweight framework](/integrations/azureai/model-client)
* [Stream completions](/integrations/azureai/completions) and [generate embeddings](/integrations/azureai/embeddings)
* [Capture invocation and usage metrics](/integrations/azureai/capturing-metrics) with no extra work
* [Run A/B tests on parameters](/integrations/azureai/running-experiments) like model, prompt, temperature and more

{% figure %}
![Azure AI integration architecture diagram](/images/integrations/azureai/introduction/b23c79c3-8501-4390-a3f3-3496970eb272.png)
{% /figure %}

## Supported SDKs

* Node JS: https://github.com/statsig-io/azureai-nodejs/
* Python: https://github.com/statsig-io/azureai-python/
* .Net: https://github.com/statsig-io/azureai-dotnet/