# DeepSeek

- 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 DeepSeek.

## Definition

```csharp
namespace Aspire.Hosting.Foundry;

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

## Fields

- [DeepSeekR1](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekr1) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.
- [DeepSeekR10528](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekr10528) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- 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.
- [DeepSeekV3](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekv3) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
- [DeepSeekV30324](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekv30324) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- 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.
- [DeepSeekV31](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekv31) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- DeepSeek-V3.1 is a hybrid model that enhances tool usage, thinking efficiency, and supports both thinking and non-thinking modes via chat template switching
- [DeepSeekV32](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekv32) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance
- [DeepSeekV32Speciale](/reference/api/csharp/aspire.hosting.foundry/deepseek/fields.md#deepseekv32speciale) : [FoundryModel](/reference/api/csharp/aspire.hosting.foundry/foundrymodel.md) `static` -- DeepSeek-V3.2 Speciale, a model that harmonizes high computational efficiency with superior reasoning and agent performance