站内导读
中文 DeepSeek-V4.1-Flash-1017 是 DeepSeek-V4.1-Flash 的小版本更新，在推理、编码、Agent 任务与视觉基准上均有提升，同时缩短任务执行时间与输出长度，降低使用成本。模型支持 1M token 上下文，采用 MIT 许可，仓库提供 Python 版 prompt 编码参考实现与 Rust 工具包 deepseek-recipe，适合构建 Agent 与多模态应用的开发者。
日本語 DeepSeek-V4.1-Flash-1017 は DeepSeek-V4.1-Flash の小規模アップデートで、推論・コーディング・Agent タスク・視覚ベンチマークの精度が向上し、実行時間と出力長も短縮されています。コンテキスト長は 1M token、ライセンスは MIT です。リポジトリには Python 製のプロンプト符号化リファレンスと Rust 製ツールキット deepseek-recipe が含まれ、Agent やマルチモーダル用途の開発者に向きます。
한국어 DeepSeek-V4.1-Flash-1017은 DeepSeek-V4.1-Flash의 소규모 업데이트로, 추론·코딩·Agent 작업·시각 벤치마크 성능이 향상되었고 작업 실행 시간과 출력 길이도 줄었습니다. 컨텍스트는 1M token이며 MIT 라이선스로 배포됩니다. 저장소에는 Python 기반 prompt 인코딩 참조 구현과 Rust 툴킷 deepseek-recipe가 포함되어 있어 Agent 및 멀티모달 애플리케이션을 만드는 개발자에게 적합합니다.
English DeepSeek-V4.1-Flash-1017 is a minor update to DeepSeek-V4.1-Flash, improving reasoning, coding, agentic tasks and visual benchmarks while cutting task execution time and output length. It offers a 1M token context under the MIT license. The repo ships a Python prompt-encoding reference and the Rust toolkit deepseek-recipe, suited to developers building agent and multimodal applications.
README · 详细文档
来源 · 查看原文
license: mit libraryname: transformers pipelinetag: image-text-to-text ---
DeepSeek-V4.1-Flash-1017
<!-- markdownlint-disable first-line-h1 --> <!-- markdownlint-disable html --> <!-- markdownlint-disable no-duplicate-header -->
<div align="center"> <img src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/logo.svg?raw=true" width="60%" alt="DeepSeek-V4.1" /> </div> <hr> <div align="center" style="line-height: 1;"> <a href="https://www.deepseek.com/" target="blank" style="margin: 2px;"> <img alt="Homepage" src="https://github.com/deepseek-ai/DeepSeek-V2/blob/main/figures/badge.svg?raw=true" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://chat.deepseek.com/" target="blank" style="margin: 2px;"> <img alt="Chat" src="https://img.shields.io/badge/🤖%20Chat-DeepSeek%20V4.1-536af5?color=536af5&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> </div> <div align="center" style="line-height: 1;"> <a href="https://huggingface.co/deepseek-ai" target="blank" style="margin: 2px;"> <img alt="Hugging Face" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-DeepSeek%20AI-ffc107?color=ffc107&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> <a href="https://twitter.com/deepseekai" target="blank" style="margin: 2px;"> <img alt="Twitter Follow" src="https://img.shields.io/badge/Twitter-deepseekai-white?logo=x&logoColor=white" style="display: inline-block; vertical-align: middle;"/> </a> </div> <div align="center" style="line-height: 1;"> <a href="LICENSE" style="margin: 2px;"> <img alt="License" src="https://img.shields.io/badge/License-MIT-f5de53?&color=f5de53" style="display: inline-block; vertical-align: middle;"/> </a> </div>
<p align="center"> <a href="https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/main/DeepSeekV41Tech_Report.pdf"><b>Technical Report</b> 👁️</a> </p>
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.
<div align="center">
| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 | | :--- | :---: | :---: | :---: | :---: | :---: | :---: | | HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 | | Terminal-Bench 4.0 | 42.3 | 31.2 | 12.6 | 37.9 | 39.9 | 51.8 | | DeepSWE v1.1 | 77.0 | 74.2 | 67.5 | 66.9 | 73.0 | 74.0 | | ProgramBench | 29.1 | 20.3 | 17.5 | 19.0 | 23.0 | 37.0 | | NL2Repo-Bench | 68.2 | 65.4 | 58.0 | 58.0 | 56.8 | 75.3 | | Automation-Bench v1.0.6 | 60.5 | 54.8 | 46.7 | 48.8 | 45.8 | 50.3 | | Agents’ Last Exam | 35.4 | 31.8 | 27.6 | 28.5 | 26.7 | 28.6 | | Apex Bench v1.1 | 72.1 | 64.6 | 47.8 | 56.6 | 54.3 | 65.8 | | Chartography (w/tools) | 83.0 | 78.9 | 68.1 | — | 79.9 | 84.0 | | BabyVision (w/tools) | 92.5 | 89.6 | 85.7 | — | 88.9 | 94.1 | | ZeroBench-main (w/tools) | 51.0 | 49.0 | 41.0 | — | 53.0 | 52.0 |
</div>
† 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:
| Parameter | Value | | :--- | :--- | | temperature | 1.0 | | top_p | 1.0 | | context_window | 1M tokens | | max_tokens | ≥ 256K |
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.