Deepseek V3.1
DeepSeek-V3.1, developed by DeepSeek, is a hybrid chat model that excels at tasks such as code generation, function calling, and math, thanks to its improved thinking mode and smarter tool calling capabilities. Notably, it features a long context window of 131,072 tokens, allowing it to process extensive inputs.
Input
Output
Context
131K
Max Output
128K
Parameters
684.5B
Technical Specifications
Model TypeChat
Context Window131,072 tokens
Max Output Tokens128,000 tokens
Parameters684.5B
Release DateAug 21, 2025
Training CutoffJul 1, 2025
Licensemit
Open SourceYes
Input Modalities
Text
Output Modalities
Text
Capabilities
Benchmarks
Artificial Analysis
6.3%
HLE
45.0%
AA-LCR
73.5%
GPQA
34.8%
Tau2-Bench
49.7%
AIME 2025
37.8%
IFBench
36.7%
SciCode
83.3%
MMLU Pro
49.7
Math
57.7%
LiveCodeBench
21.0
Intelligence
24.2%
Terminal-Bench Hard
Resources & Links
Estimated GPU Requirements for Deepseek V3.1
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by DeepSeek
Deepseek V3.1 Base131K context · 684.5B · Open weightsDeepseek Prover V1.5 SFT4K context · 6.9B · 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 weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 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.