Deepseek V3 Base
DeepSeek, the creator, develops the Deepseek V 3 Base model, a chat-type language model with a context window of 131,072 tokens, capable of function calling, JSON mode, reasoning, streaming, and text generation. It is genuinely best at handling long-range dependencies and complex tasks due to its large context window and innovative architecture, which includes a Mixture-of-Experts (MoE) design and Multi-head Latent Attention (MLA).
Input
Output
Context
131K
Max Output
-
Parameters
684.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output TokensNot available
Parameters684.5B
Release DateDec 25, 2024
Training CutoffJul 1, 2024
LicenseMIT & Model License
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jun 24, 2026
Start building with the right model.
Automatically route workloads to the right model for every task, every time.