Deepseek V3.1 Base
DeepSeek develops the Deepseek V 3.1 Base, a chat model that excels at tasks such as function calling, reasoning, and text generation, thanks to its hybrid architecture and post-training optimization. With a context window of 131,072 tokens, this model is capable of handling long-range dependencies and complex inputs.
Input
Output
Context
131K
Max Output
8K
Parameters
684.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens8,000 tokens
Parameters684.5B
Release DateAug 19, 2025
Training CutoffMar 1, 2025
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Resources & Links
Estimated GPU Requirements for Deepseek V3.1 Base
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by DeepSeek
Deepseek Prover V1.5 SFT4K context · Open weightsDeepseek V3.2 Speciale164K context · 685.4B · Open weightsDeepseek Math 7B Base4K context · 7B · Open weightsDeepseek R1 Distill Qwen 32B131K context · 32.8B · Open weightsDeepseek V3 Base131K context · 684.5B · Open weightsDeepseek V2 Lite Chat33K context · 15.7B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Jul 30, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.