# MistralAI

- Kind: `class`
- Package: [Aspire.Hosting.Foundry](/reference/api/csharp/aspire.hosting.foundry.md)
- Version: `13.3.0-preview.1.26254.5`
- Namespace: `Aspire.Hosting.Foundry`
- Target framework: `net8.0`
- Source: [GitHub](https://github.com/microsoft/aspire/blob/5bd693ae1897dee5e2ce71c2cc08879c1c7eff51/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

Models published by Mistral AI.

## Definition

```csharp
namespace Aspire.Hosting.Foundry;

public static class MistralAI
{
    // ...
}
```

## Fields

- [Codestral2501](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#codestral2501) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Codestral 25.01 by Mistral AI is designed for code generation, supporting 80+ programming languages, and optimized for tasks like code completion and fill-in-the-middle
- [Ministral3B](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#ministral3b) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Ministral 3B is a state-of-the-art Small Language Model (SLM) optimized for edge computing and on-device applications. As it is designed for low-latency and compute-efficient inference, it it also the perfect model for standard GenAI applications that have
- [MistralDocumentAi2505](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistraldocumentai2505) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Document conversion to markdown with interleaved images and text
- [MistralDocumentAi2512](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistraldocumentai2512) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Document conversion to markdown with interleaved images and text
- [MistralLarge2407](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistrallarge2407) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Large (2407) is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge and coding capabilities.
- [MistralLarge2411](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistrallarge2411) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Large 24.11 offers enhanced system prompts, advanced reasoning and function calling capabilities.
- [MistralLarge3](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistrallarge3) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Large 3 is a state-of-the-art General-purpose Multimodal granular Mixture-of-Experts model with 39B active parameters, 673B total parameters featuring 128 experts per layer and Multi-Latent attention.
- [MistralMedium2505](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistralmedium2505) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Medium 3 is an advanced Large Language Model (LLM) with state-of-the-art reasoning, knowledge, coding and vision capabilities.
- [MistralNemo](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistralnemo) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Nemo is a cutting-edge Language Model (LLM) boasting state-of-the-art reasoning, world knowledge, and coding capabilities within its size category.
- [MistralSmall](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistralsmall) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Mistral Small can be used on any language-based task that requires high efficiency and low latency.
- [MistralSmall2503](/reference/api/csharp/aspire.hosting.foundry/mistralai/fields.md#mistralsmall2503) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- Enhanced Mistral Small 3 with multimodal capabilities and a 128k context length.