# September 30: Support for Azure AI Inference models, Mistral Pixtral and latest Google Gemini models ### New Features * :bulb: Graphlit now supports the [Azure AI Model Inference API](https://learn.microsoft.com/en-us/azure/ai-studio/reference/reference-model-inference-api?tabs=python) (aka Models as a Service) model service which offers serverless hosting to many models such as Meta Llama 3.2, Cohere Command-R, and many more. For Azure AI, all models are 'custom', and you will need to provide the serverless endpoint, API key and number of tokens accepted in context window, after provisioning the model of your choice. * We have added support for the multimodal Mistral Pixtral model, under the model enum `PIXTRAL_12B_2409`. * We have added versioned model enums for Google Gemini, so you can access `GEMINI_1_5_FLASH_001`, `GEMINI_1_5_FLASH_002`, `GEMINI_1_5_PRO_001` and `GEMINI_1_5_PRO_002`. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://changelog.graphlit.dev/september-2024/september-30-support-for-azure-ai-inference-models-mistral-pixtral-and-latest-google-gemini-models.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.