DeepSeek-V4-Flash Update
DeepSeek-V4-Flash Update
Date: 2026-07-31 | DeepSeek-V4-Flash Update 日期：2026-07-31 | DeepSeek-V4-Flash 更新
The official release of the DeepSeek-V4-Flash API is now in public beta. The API calling method remains unchanged — simply set the model name to deepseek-v4-flash to use the latest version.
DeepSeek-V4-Flash API 正式版现已开启公测。API 调用方式保持不变——只需将模型名称设置为 deepseek-v4-flash 即可使用最新版本。
Significantly enhanced agent capabilities, with benchmark results far exceeding V4-Pro-Preview: 代理（Agent）能力显著增强，基准测试结果远超 V4-Pro-Preview：
- Terminal Bench 2.1: 82.7
- NL2Repo: 54.2
- Cybergym: 76.7
- DeepSWE: 54.4
- Toolathlon verified: 70.3
- Agent Last Exam: 25.2
- Automation Bench (Public): 25.1
- DSBench-FullStack: 68.7
- DSBench-Hard: 59.6
Note 1: For the Code Agent tasks in the public benchmark sets, the official DeepSeek-V4-Flash was tested using the DeepSeek Harness minimal mode (to be released soon) as the framework, with the max effort level, topp=0.95, and temperature=1.0. 注 1：在公共基准测试集的代码代理任务中，官方 DeepSeek-V4-Flash 使用 DeepSeek Harness 最小模式（即将发布）作为框架进行测试，设置包括最大努力等级（max effort level）、topp=0.95 以及 temperature=1.0。
Note 2: DSBench-FullStack is an internal full-stack development test set, and DSBench-Hard is an internal Coding Agent hard-problem test set. 注 2：DSBench-FullStack 为内部全栈开发测试集，DSBench-Hard 为内部代码代理难题测试集。
The official V4-Flash natively supports the Responses API format and is specifically adapted for Codex. For the specific configuration, please refer to the documentation. 官方 V4-Flash 原生支持 Responses API 格式，并针对 Codex 进行了专门适配。具体配置请参考文档。
DeepSeek-V4-Flash-0731 keeps the same model architecture and size as DeepSeek-V4-Flash-Preview, and was only re-post-trained. DeepSeek-V4-Flash-0731 保持了与 DeepSeek-V4-Flash-Preview 相同的模型架构和规模，仅进行了重新后训练（re-post-trained）。
Note: This update only upgrades the DeepSeek-V4-Flash API. The DeepSeek-V4-Pro API and the APP/WEB models are unchanged. The official release of DeepSeek-V4-Pro will follow soon. 注：本次更新仅升级 DeepSeek-V4-Flash API。DeepSeek-V4-Pro API 及 APP/WEB 端模型保持不变。DeepSeek-V4-Pro 的正式发布即将到来。
Date: 2026-04-24 | DeepSeek-V4 日期：2026-04-24 | DeepSeek-V4
The DeepSeek API now supports V4-Pro and V4-Flash, available via both the OpenAI ChatCompletions interface and the Anthropic interface. To access the new models, the base_url remains unchanged, and the model parameter should be set to deepseek-v4-pro or deepseek-v4-flash.
DeepSeek API 现已支持 V4-Pro 和 V4-Flash，可通过 OpenAI ChatCompletions 接口和 Anthropic 接口调用。要访问新模型，base_url 保持不变，模型参数应设置为 deepseek-v4-pro 或 deepseek-v4-flash。
The two legacy API model names, deepseek-chat and deepseek-reasoner, will be discontinued in three months (2026-07-24). During the current period, these two model names point to the non-thinking mode and thinking mode of deepseek-v4-flash, respectively. For more details, please refer to this documentation.
两个旧版 API 模型名称 deepseek-chat 和 deepseek-reasoner 将在三个月后（2026-07-24）停止服务。在此期间，这两个模型名称分别指向 deepseek-v4-flash 的非思考模式和思考模式。更多详情请参考相关文档。
Date: 2025-12-01 | DeepSeek-V3.2 日期：2025-12-01 | DeepSeek-V3.2
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2.
deepseek-chat 和 deepseek-reasoner 均已升级至 DeepSeek-V3.2。
deepseek-chatcorresponds to DeepSeek-V3.2’s non-thinking mode.deepseek-chat对应 DeepSeek-V3.2 的非思考模式。deepseek-reasonercorresponds to DeepSeek-V3.2’s thinking mode.deepseek-reasoner对应 DeepSeek-V3.2 的思考模式。
DeepSeek-V3.2-Speciale
DeepSeek-V3.2-Speciale is served via a temporary endpoint: base_url="https://api.deepseek.com/v3.2_speciale_expires_on_20251215". Same pricing as V3.2, no tool calls, available until Dec 15th, 2025, 15:59 (UTC Time). For more details, please refer to this documentation.
DeepSeek-V3.2-Speciale 通过临时端点提供服务：base_url="https://api.deepseek.com/v3.2_speciale_expires_on_20251215"。定价与 V3.2 相同，不支持工具调用，有效期至 2025 年 12 月 15 日 15:59（UTC 时间）。更多详情请参考相关文档。
Date: 2025-09-29 | DeepSeek-V3.2-Exp 日期：2025-09-29 | DeepSeek-V3.2-Exp
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.2-Exp.
deepseek-chat 和 deepseek-reasoner 均已升级至 DeepSeek-V3.2-Exp。
deepseek-chatcorresponds to DeepSeek-V3.2-Exp’s non-thinking mode.deepseek-chat对应 DeepSeek-V3.2-Exp 的非思考模式。deepseek-reasonercorresponds to DeepSeek-V3.2-Exp’s thinking mode.deepseek-reasoner对应 DeepSeek-V3.2-Exp 的思考模式。
Date: 2025-09-22 | DeepSeek-V3.1-Terminus 日期：2025-09-22 | DeepSeek-V3.1-Terminus
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1-Terminus. deepseek-chat corresponds to DeepSeek-V3.1-Terminus’s non-thinking mode, while deepseek-reasoner corresponds to its thinking mode.
deepseek-chat 和 deepseek-reasoner 均已升级至 DeepSeek-V3.1-Terminus。deepseek-chat 对应 DeepSeek-V3.1-Terminus 的非思考模式，而 deepseek-reasoner 对应其思考模式。
This update maintains the model’s original capabilities while addressing issues reported by users, including: 本次更新在保持模型原有能力的同时，解决了用户反馈的问题，包括：
- Language consistency: Reduced occurrences of Chinese-English mixing and occasional abnormal characters. 语言一致性：减少了中英混杂和偶尔出现的异常字符。
- Agent capabilities: Further optimized the performance of the Code Agent and Search Agent. 代理能力：进一步优化了代码代理和搜索代理的性能。
Date: 2025-08-21 | DeepSeek-V3.1 日期：2025-08-21 | DeepSeek-V3.1
Both deepseek-chat and deepseek-reasoner have been upgraded to DeepSeek-V3.1. deepseek-chat corresponds to DeepSeek-V3.1’s non-thinking mode, while deepseek-reasoner corresponds to its thinking mode.
deepseek-chat 和 deepseek-reasoner 均已升级至 DeepSeek-V3.1。deepseek-chat 对应 DeepSeek-V3.1 的非思考模式，而 deepseek-reasoner 对应其思考模式。
Key updates in DeepSeek-V3.1: DeepSeek-V3.1 的关键更新：
- Hybrid reasoning architecture: A single model supports both thinking mode and non-thinking mode. 混合推理架构：单一模型同时支持思考模式和非思考模式。
- Improved reasoning efficiency: Compared to DeepSeek-R1-0528, DeepSeek-V3.1-Think provides answers in significantly less time. 推理效率提升：相比 DeepSeek-R1-0528，DeepSeek-V3.1-Think 的回答时间显著缩短。
- Enhanced agent capabilities: With post-training optimization, the new model achieves major improvements in tool usage and intelligent agent tasks.
代理能力增强：通过后训练优化，新模型在工具使用和智能代理任务上取得了重大改进。
- SWE-bench Verified: 66.0
- SWE-bench Multilingual: 54.5
- Terminal-bench: 31.3
Date: 2025-05-28 | deepseek-reasoner 日期：2025-05-28 | deepseek-reasoner
deepseek-reasoner Model Upgraded to DeepSeek-R1-0528:
deepseek-reasoner 模型升级至 DeepSeek-R1-0528：
Enhanced Reasoning Capabilities (Significant benchmark improvements, Pass@1): 增强的推理能力（基准测试显著提升，Pass@1）：
- AIME 2025: 70.0 → 87.5 (+17.5)
- GPQA: 71.5 → 81.0 (+9.5)
- LCB_v6: 63.5 → 73.3 (+9.8)
- Aider: 57.0 → 71.6 (+14.6) Note: Complex reasoning tasks may consume more tokens compared to legacy R1 version. 注：复杂推理任务相比旧版 R1 可能消耗更多 Token。
Optimized Front-end Development: Generated web pages and games now feature improved aesthetics. 前端开发优化：生成的网页和游戏现在具有更好的美观度。
Reduced Hallucinations: Significantly suppressed hallucination issues present in legacy R1 version. 减少幻觉：显著抑制了旧版 R1 中存在的幻觉问题。
JSON Output & Function Calling Support: Function call performance: Tau-bench score: 53.5 (Airline) / 63.9 (Retail). JSON 输出与函数调用支持：函数调用性能：Tau-bench 得分 53.5 (航空) / 63.9 (零售)。
Date: 2025-03-24 | deepseek-chat 日期：2025-03-24 | deepseek-chat
deepseek-chat Model Upgraded to DeepSeek-V3-0324:
deepseek-chat 模型升级至 DeepSeek-V3-0324：
Enhanced Reasoning Capabilities (Significant improvements in benchmark performance): 增强的推理能力（基准测试性能显著提升）：
- MMLU-Pro: 75.9 → 81.2 (+5.3)
- GPQA: 59.1 → 68.4 (+9.3)
- AIME: 39.6 → 59.4 (+19.8)
- LiveCodeBench: 39.2 → 49.2 (+10.0)
Optimized Front-End Web Development: Improved accuracy in code generation; more aesthetically pleasing web pages and game front-ends. 前端网页开发优化：代码生成准确性提升；网页和游戏前端更美观。
Upgraded Chinese Writing Proficiency: Enhanced style and content quality; aligned with the R1 writing style; better quality in medium-to-long-form writing. 中文写作能力升级：风格和内容质量增强；对齐 R1 写作风格；中长文写作质量更佳。
Feature Enhancements: Improved multi-turn interactive rewriting; optimized translation quality and letter writing. 功能增强：改进多轮交互重写；优化翻译质量和信件写作。
Improved Chinese Search Capabilities: Enhanced report analysis requests with more detailed outputs. 中文搜索能力提升：增强了报告分析请求，输出更详细。
Function Calling Improvements: Increased accuracy in Function Calling, fixing issues from previous V3 versions. 函数调用改进：提升了函数调用的准确性，修复了之前 V3 版本的问题。
Date: 2025-01-20 | deepseek-reasoner 日期：2025-01-20 | deepseek-reasoner
deepseek-reasoner is our new model DeepSeek-R1. You can invoke DeepSeek-V3 by specifying model='deepseek-reasoner'.
deepseek-reasoner 是我们的新模型 DeepSeek-R1。您可以通过指定 model='deepseek-reasoner' 来调用 DeepSeek-V3。
Date: 2024-12-26 | deepseek-chat 日期：2024-12-26 | deepseek-chat
The deepseek-chat model has been upgraded.
deepseek-chat 模型已升级。