DeepSeek-V4.1-Flash-1017

技术报告 👁️

简介

DeepSeek-V4.1-Flash-1017 是 DeepSeek-V4.1-Flash 的一次小版本更新，在推理、编程、Agent 任务和视觉基准测试中均取得显著提升。与此同时，该模型缩短了任务执行时间和输出长度，使用户能够以更快的速度和更低的成本完成任务，并在多种 Agent 执行框架中推进性能与成本的帕累托前沿。

† 表示 HLE 的纯文本子集。Terminal-Bench 4.0 使用 Claude Code 执行框架，DeepSWE v1.1 使用 Mini-SWE-V2 执行框架。

提示词编码

本次发布不包含 Jinja 格式的聊天模板。encoding 文件夹包含一个自包含的 Python 参考实现（encoding.py），以及针对多轮对话、工具调用、思考模式、数值型推理强度、对话中途的系统消息和交错图像内容的测试用例。

针对生产环境，我们还发布了 deepseek-recipe。这是一组带有 Python 绑定的 Rust 库，作为持续维护、支持协议处理的工具包提供相同的提示词格式。它可以将 Messages、Chat Completions 和 Responses API 请求转换为 Conversation 格式，将其编码为 DeepSeek V4 和 V4.1 提示词或 token ID，并将模型输出解析回完整响应或流式响应，涵盖思考、工具调用、图像和生成设置。模型推理、工具执行和 HTTP 传输则由调用方负责。

最简推理

有关权重转换和在本地运行推理的说明，请参阅 inference 文件夹。

推荐采样参数：

许可证

本仓库和模型权重采用 MIT 许可证。

引用

bibtex @misc{deepseekai2026deepseekv41flash, title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression}, author={DeepSeek-AI}, year={2026}, }

联系方式

如有任何问题，请提交 issue，或通过 service@deepseek.com 联系我们。

DeepSeek-V4.1-Flash-1017

Technical Report 👁️

Introduction

DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, delivering substantial improvements across reasoning, coding, agentic tasks, and visual benchmarks. Alongside these gains, the model reduces task execution time and output length, enabling users to complete tasks faster and at lower cost and advancing the performance–cost Pareto frontier across multiple agent harnesses.

† denotes the text-only subset of HLE. We use the Claude Code harness for Terminal-Bench 4.0 and the Mini-SWE-V2 harness for DeepSWE v1.1.

Prompt Encoding

This release does not include a Jinja-format chat template. The encoding folder contains a self-contained Python reference implementation (encoding.py) with test cases for multi-turn conversations, tool calling, thinking mode, numeric reasoning effort, mid-conversation system messages, and interleaved image content.

For production use, we additionally release deepseek-recipe, a set of Rust libraries with Python bindings that provides the same prompt format as a maintained, protocol-aware toolkit. It converts Messages, Chat Completions, and Responses API requests into the Conversation format, encodes them into DeepSeek V4 and V4.1 prompts or token IDs, and parses model output back into complete or streamed responses — covering thinking, tool calls, images, and generation settings. Model inference, tool execution, and HTTP transport are left to the caller.

Minimal Inference

Please refer to the inference folder for instructions on weight conversion and running inference locally.

Recommended sampling parameters:

License

This repository and the model weights are licensed under the MIT License.

Citation

@misc{deepseekai2026deepseekv41flash,
      title={DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression},
      author={DeepSeek-AI},
      year={2026},
}

Contact

If you have any questions, please raise an issue or contact us at service@deepseek.com.