# DeepSeek Fields

- Package: [Aspire.Hosting.Foundry](/reference/api/csharp/aspire.hosting.foundry.md)
- Type: [DeepSeek](/reference/api/csharp/aspire.hosting.foundry/deepseek.md)
- Kind: `Fields`
- Members: `8`

Models published by DeepSeek.

## DeepSeekR1

- Name: `DeepSeekR1`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.

```csharp
public static readonly FoundryModel DeepSeekR1
```

## DeepSeekR10528

- Name: `DeepSeekR10528`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

The DeepSeek R1 0528 model has improved reasoning capabilities, this version also offers a reduced hallucination rate, enhanced support for function calling, and better experience for vibe coding.

```csharp
public static readonly FoundryModel DeepSeekR10528
```

## DeepSeekV3

- Name: `DeepSeekV3`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

```csharp
public static readonly FoundryModel DeepSeekV3
```

## DeepSeekV30324

- Name: `DeepSeekV30324`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek-V3-0324 demonstrates notable improvements over its predecessor, DeepSeek-V3, in several key aspects, including enhanced reasoning, improved function calling, and superior code generation capabilities.

```csharp
public static readonly FoundryModel DeepSeekV30324
```

## DeepSeekV32

- Name: `DeepSeekV32`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance

```csharp
public static readonly FoundryModel DeepSeekV32
```

## DeepSeekV32Speciale

- Name: `DeepSeekV32Speciale`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek-V3.2 Speciale, a model that harmonizes high computational efficiency with superior reasoning and agent performance

```csharp
public static readonly FoundryModel DeepSeekV32Speciale
```

## DeepSeekV4Flash

- Name: `DeepSeekV4Flash`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.

```csharp
public static readonly FoundryModel DeepSeekV4Flash
```

## DeepSeekV4Pro

- Name: `DeepSeekV4Pro`
- Modifiers: `static` `readonly`
- Returns: [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md)
- Source: [GitHub](https://github.com/microsoft/aspire/blob/becb48e2d61099e35ae336d527d3875e928d6594/src/Aspire.Hosting.Foundry/FoundryModel.Generated.cs)

DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.

```csharp
public static readonly FoundryModel DeepSeekV4Pro
```