DeepSeek opens full-suite app APIs with web search, files, voice, OCR, ASR, TTS
DeepSeek announced the release of a full-suite API covering the capabilities of its consumer app, including web search, deep-thinking search, file input, link reading, safety, voice, OCR, ASR, and TTS. These features are available as standalone interfaces or built-in tools, with V4.1-Flash (deepseek-flash) supporting them across Messages, Responses, and Chat Completions, with server-side tool calls and context assembly. DeepSeek also open-sourced a lightweight chat frontend demo that supports importing conversation history, enabling developers to replicate the full app experience.
Coverage timeline
DeepSeek News
Search, files, links, safety, and voice. The capabilities behind the DeepSeek App are now available through the DeepSeek API. Enable built-in features with a few parameters, or call standalone APIs such as OCR, ASR, and TTS. Build richer conversations or recreate the full DeepSeek App in your own application. Try our open-source frontend demo, with support for importing DeepSeek conversation history. 🔗 Demo: https://cdn.deepseek.com/chat-demo 📦 Code: https://github.com/deepseek-ai/chat-demo 📖 Details: https://api-docs.deepseek.com/guides/build_a_chatbot 🛠️ Built-in tools. Flexible APIs. V4.1-Flash ( deepseek-flash ) now supports these capabilities across Messages , Responses , and Chat Completions , with tool calls and context assembly handled server-side: 🔹 Web Search: Search the web or images with citations in non-thinking mode. 🔹 Deep Thinking Search: Search and read pages throughout multi-step reasoning. 🔹 File Input: Parse PDFs, Office files, images, and more into conversat
量子位量子位
突发！DeepSeek开放全家桶API 一水 2026-11-14 10:39:56 来源： 量子位 官方App功能均可自由组合调用 周五晚上搞事，D老师通通都不藏了！ 就在刚刚，DeepSeek宣布， 正式开放全家桶应用API 。 什么意思？ 以前大家在DeepSeek App里用得顺手的联网搜索、深度思考搜索、文件上传、链接阅读等功能，现在开发者通过API通通都能直接用上了，而且不必打包使用，它们都有独立接口，支持单独调用、分别计费。 划重点， 语音能力也首次加入开放行列 ，包括语音识别、语音合成等接口。 官方还放出一句相当有意思的话： 开发者甚至可以1：1复刻出完整的DeepSeek App 。 不是哥们，连自家产品都允许别人照着做啊？？ DeepSeek还贴心亲自打了个样，直接开源了一套轻量级聊天前端Demo，支持导入DeepSeek历史对话。 也就是说，开发者不用再从头折腾搜索、文件解析、语音识别这些基础功能，就能快速搭出一个功能接近DeepSeek App的产品。 消息一出，评论区也是相当热闹。 有网友直接感叹： 什么叫1：1复刻出完整的DeepSeek App？？？人工智能之光！ 全家桶应用API开放一览 具体来看，这次DeepSeek一口气开放了这些能力： 这里有两个变化值得单独说说。 首先，联网搜索其实不是第一次开放，早在今年10月17日，DeepSeek就已经开放了自研Search和Fetch接口。 但当时，开发者还需要自己处理不少工具调用和模型之间的衔接工作。 比如用户问“最近AI圈发生了什么”，开发者需要先让模型判断要不要搜索，再调用Search找网页、用Fetch读取内容，最后把结果重新交给模型总结。 这一整套流程，都得开发者自己写代码串起来。 现在就简单多了。 开发者只要给模型打开联网搜索功能，什么时候搜索、搜什么、要读哪些网页，以及如何根据搜索结果继续回答，DeepSeek都会自动完成。 其次是语音，这次终于有了官方独立接口。 此前，DeepSeek App虽然已经支持语音交互，但公开的模型API并没有提供同样完整的语音能力。 开发者想做一个能听会说的DeepSeek助手，通常还需要另外接入语音识别、语音合成服务。 现在，ASR和TTS都可以通过DeepSeek官方接口调用了。 而且，上述底层能力也不必全部打包使用。 DeepSeek还
Related stories
Developer Shares ~200-Line Pure JAX Implementation of DeepSeek V3
A developer posted a minimal implementation of DeepSeek V3 on Hacker News, written in about 200 lines of pure JAX. The code is presented as a compact educational example rather than a full production deployment.
1 reports · 1 sources219 points · 19 comments
DeepSeek open-sources Super-agent architecture for autonomous bug-fixing agents
DeepSeek has publicly released the architectural blueprint for its Super-agent, a research prototype of a personal agent that maintains cross-session context to handle multi-task coordination. Internal tests show the agent can autonomously identify bugs and submit pull requests without being explicitly prompted, with a median task completion time of 12.4 minutes in simulated multi-task environments. DeepSeek positions this as a step toward reducing human attention bottlenecks in multi-task workflows.
3 reports · 3 sources
DeepSeek open-sources DeepInfer inference stack, reports 82% gross margin
DeepSeek released its internal inference framework DeepInfer under the Apache 2.0 license, along with the token codec component deepseek-recipe. The framework, which supports DeepSeek-V4.1-Flash and targets Nvidia SM100 GPUs and Huawei Ascend 950 NPUs, reportedly achieves a throughput of 155 trillion tokens per day per cluster, with API revenue of $38 per GPU-hour at off-peak pricing, implying a gross margin of 82% after GPU rental costs. The release sparked discussions about the profitability of AI inference services.
3 reports · 3 sources2335 points · 890 comments
DeepSeek launches creator mode for Harness custom plugins
DeepSeek has released a creator mode for its DeepSeek Harness platform, enabling users to build custom plugins for complex tasks. Examples include a 3D model renderer and a video editing workbench, expanding the platform's versatility.
News updates every hour. Subscribe in your RSS reader to get new stories automatically.
Subscribe