DeepSeek
Class static net8.0
Models published by DeepSeek.
namespace Aspire.Hosting.Foundry;
public static class DeepSeek{ // ...} 8 members
Fields8
Section titled FieldsDeepSeekR1static DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.
DeepSeekR10528static 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.
DeepSeekV3static A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
DeepSeekV30324static 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.
DeepSeekV32static DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance
DeepSeekV32Specialestatic DeepSeek-V3.2 Speciale, a model that harmonizes high computational efficiency with superior reasoning and agent performance
DeepSeekV4Flashstatic DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
DeepSeekV4Prostatic DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.