DeepSeek V3.2 Exp by DeepSeek

DeepSeek R1

DeepSeek Reasoner is a specialized model developed by DeepSeek that uses Chain of Thought (CoT) reasoning to improve response accuracy. Before providing a final answer, it generates detailed reasoning steps that are accessible through the API, allowing users to examine and leverage the model's thought process, served by Fireworks AI.

DeepSeek R1 Distill Llama 70B

DeepSeek-R1 is a state-of-the-art reasoning model trained with reinforcement learning and cold-start data, delivering strong performance across math, code, and complex reasoning tasks. It offers improved stability, readability, and multilingual handling compared to earlier versions, and is available alongside several high-quality distilled variants.

DeepSeek V3 0324

Fast general-purpose LLM with enhanced reasoning capabilities

DeepSeek V3.1

DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. DeepSeek has expanded their dataset by collecting additional long documents and substantially extending both training phases.

DeepSeek V3.1 Base

DeepSeek V3.1 Base is an improved version of the DeepSeek V3 model.

DeepSeek V3.1 Terminus

DeepSeek-V3.1-Terminus delivers more stable & reliable outputs across benchmarks compared to the previous version and addresses user feedback (i.e. language consistency and agent upgrades).

DeepSeek V3.2 Exp Thinking

DeepSeek-V3.2-Exp is an experimental model introducing the groundbreaking DeepSeek Sparse Attention (DSA) mechanism for enhanced long-context processing efficiency. Built on V3.1-Terminus, DSA achieves fine-grained sparse attention while maintaining identical output quality.