Microsoft’s collaboration with Mistral AI continues to accelerate AI innovation. After the successful launch of Mistral Large, Mistral AI’s flagship model, we’re thrilled to unveil Mistral Small – a compact yet powerful language model designed for efficiency.
Available in the Azure AI model catalog, Mistral Small joins our growing collection of LLMs. Developers can access it through Models as a Service (MaaS), enabling seamless API-based interactions.
Mistral Small
As per insights provided by Mistral AI, Mistral Small is Mistral AI's smallest proprietary Large Language Model (LLM). It can be used on any language-based task that requires high efficiency and low latency.
Mistral Small is:
- A small model optimized for low latency: Very efficient for high volume and low latency workloads. Mistral Small is Mistral's smallest proprietary model, it outperforms Mixtral 8x7B and has lower latency.
- Specialized in RAG: Crucial information is not lost in the middle of long context windows. Supports up to 32K tokens.
- Strong in coding: Code generation, review and comments with support for all mainstream coding languages.
- Multi-lingual by design: Best-in-class performance in French, German, Spanish, and Italian - in addition to English. Dozens of other languages are supported.
- Efficient guardrails baked in the model, with additional safety layer with safe prompt option.
Get started with Mistral Small on Azure AI
Provision an API Endpoint: Create your Mistral Small API endpoint in seconds.
Experiment: Try it out in the Azure AI Studio playground or integrate it with popular LLM app development tools.
Build Safely: Leverage dual-layer safety mechanisms to create reliable and secure Generative AI applications.
Here are the prerequisites:
- If you don’t have an Azure subscription, get one here: https://azure.microsoft.com/en-us/pricing/purchase-options/pay-as-you-go
- Create an Azure AI Studio hub and project. Make sure you pick East US 2/Sweden Central as the Azure region for the hub.
Next, you need to create a deployment to obtain the inference API and key:
- Open the Mistral Small model card in the model catalog: https://aka.ms/aistudio/landing/mistral-small
- Click on Deploy and select the Pay-as-you-go option.
- Subscribe to the Marketplace offer and deploy. You can also review the API pricing at this step.
- You should land on the deployment page that shows you the API and key in less than a minute. You can try out your prompts in the playground.
The prerequisites and deployment steps are explained in the product documentation: https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models-mistral.
You can use the API and key with various clients. Review the API schema if you are looking to integrate the REST API with your own client: https://learn.microsoft.com/en-us/azure/ai-studio/how-to/deploy-models-mistral#reference-for-mistral.... Let’s review samples for some popular clients.
Explore the power of Mistral Small – where efficiency meets innovation!
