deepseek-ai / deepseek-v3.1-terminus

DeepSeek-V3.1-Terminus Overview

Model Summary

DeepSeek-V3.1-Terminus is an updated checkpoint of the DeepSeek-V3 family and refines model stability, multilingual consistency, and agent behavior. It improves agent and code/search capabilities while addressing mixed-language and character issues seen in earlier checkpoints.

This model is ready for commercial/non-commercial use.

Third-Party Community Consideration:

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA DeepSeek-V3.1-Terminus Model Card.

GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the NVIDIA Open Model License Agreement. Additional Information: MIT.

Deployment Geography:

Global

Use Case:

Reasoning, search/agent workflows, code assistance, multilingual QA, and knowledge retrieval for research and enterprise applications.

Release Date:

build.nvidia.com 10/06/2025 via link

Huggingface 08/21/2025 via link

Reference(s):

References: https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus

Model Architecture

Architecture Type: Transformer

Network Architecture: DeepSeek-V3 Mixture-of-Experts variant with MLA

Total Parameters: ~685B

Base Model: DeepSeek-V3 family

Input

Input Types: Text

Input Formats: String

Input Parameters: One Dimensional (1D)

Other Input Properties: Undisclosed

Output

Output Types: Text

Output Format: String

Output Parameters: One Dimensional (1D)

Other Output Properties: Undisclosed

Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Software Integration

Runtime Engines:

SGLang

Supported Hardware Microarchitecture Compatibility:

NVIDIA Blackwell

NVIDIA Hopper

Operating Systems: Linux

The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.

Model Version(s)

Model Version(s)

DeepSeek-V3.1-Terminus

Training, Testing, and Evaluation Datasets

Training Dataset

Training Data Collection: Undisclosed

Training Labeling: Undisclosed

Training Properties: Undisclosed

Data Modality: Text
Text Training Data Size: [1 Billion to 10 Trillion Tokens]

Testing Dataset

Testing Data Collection: Undisclosed

Testing Labeling: Undisclosed

Testing Properties: Undisclosed

Evaluation Dataset

Evaluation Benchmark Score: Undisclosed

Evaluation Data Collection: Undisclosed

Evaluation Labeling: Undisclosed

Evaluation Properties: Undisclosed

Inference

Acceleration Engine: SGLang

Test Hardware: B200

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here

country_code