DeepSeek Fields
ClassFields8 members
Models published by DeepSeek.
DeepSeek-R1 excels at reasoning tasks using a step-by-step training process, such as language, scientific reasoning, and coding tasks.
public static readonly FoundryModel DeepSeekR1 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.
public static readonly FoundryModel DeepSeekR10528 A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.
public static readonly FoundryModel DeepSeekV3 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.
public static readonly FoundryModel DeepSeekV30324 DeepSeek-V3.2, a model that harmonizes high computational efficiency with superior reasoning and agent performance
public static readonly FoundryModel DeepSeekV32 DeepSeek-V3.2 Speciale, a model that harmonizes high computational efficiency with superior reasoning and agent performance
public static readonly FoundryModel DeepSeekV32Speciale DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
public static readonly FoundryModel DeepSeekV4Flash DeepSeek V4 is an efficient MoE model family with 1M context and near state-of-the-art open-source reasoning performance.
public static readonly FoundryModel DeepSeekV4Pro