This is a base model trained for raw text prediction, not instruction-following. Prompts should be written as examples, not simple requests.

Favicon de deepseek

DeepSeek: DeepSeek V3.1 Base

deepseek/deepseek-v3.1-base

Pesos do modelo

This is a base model, trained only for raw next-token prediction. Unlike instruct/chat models, it has not been fine-tuned to follow user instructions. Prompts need to be written more like training text or examples rather than simple requests (e.g., “Translate the following sentence…” instead of just “Translate this”).

DeepSeek-V3.1 Base is a 671B parameter open Mixture-of-Experts (MoE) language model with 37B active parameters per forward pass and a context length of 128K tokens. Trained on 14.8T tokens using FP8 mixed precision, it achieves high training efficiency and stability, with strong performance across language, reasoning, math, and coding tasks.

Modalidades
Contexto
164K
Lançado
20 de ago. de 2025
Data de corte do conhecimento
mar. de 2025

Atividade

Volume de tokens e tráfego de requisições para este modelo ao longo do tempo.

Atualmente indisponível por meio do roteamento intrarregional da UE. Documentação de roteamento na região

Perguntas frequentes