Newshot
Account

DeepSeek Releases Full-Suite App API: Developers Can Now Recreate the Complete DeepSeek App 1:1

Source: IT之家 Published: Developers 中文 APILaunchDeepSeek
AI summary

On the evening of November 13, DeepSeek announced the official opening of its full-suite app API: by enabling the corresponding parameters in the existing API, developers can access conversational features such as deep-thinking search and file input, while voice and related underlying capabilities (including OCR, ASR, and TTS) are also available as standalone interfaces that can be called individually or in combination. Developers can easily implement complex conversational features in their own apps and even recreate the complete DeepSeek App 1:1. This update integrates the DeepSeek App's various interactive features directly into the existing API; once the corresponding parameters are enabled, tool calls and context assembly are handled automatically by the server.

Translation(model translation, not the source's own text)

DeepSeek Releases Full-Suite App API: Developers Can Now Replicate the Complete DeepSeek App 1:1

IT Home, November 13 — Tonight (the 13th), DeepSeek announced the official opening of its full-suite app API: by enabling the corresponding parameters in the existing API, users can obtain dialogue features such as deep-thinking search and file input; voice and related underlying capabilities have also been opened as standalone interfaces (including OCR, ASR, TTS, etc.), supporting individual or combined calls.

Developers can easily implement complex dialogue features in their own applications, and even replicate the complete DeepSeek App 1:1.

This update integrates DeepSeek App's various interactive features directly into the existing API. After the corresponding parameters are enabled, the relevant tool calls and context assembly are handled automatically by the server.

Currently, the V4.1-Flash model (deepseek-flash) supports the following capabilities under the Messages, Responses, and Chat Completions interfaces:

  • Web search: In non-thinking mode, after enabling the deepseek_web_search tool, the model can automatically initiate web or image searches based on the question and answer with citations;
  • Deep-thinking search: In thinking mode, after enabling the deepseek_web_search tool, the model can autonomously search the web and read links during multi-step reasoning;
  • File input: Supports uploading files in PDF, Office, image, and other formats, completing plain-text extraction or mixed text-image parsing before splicing them into the dialogue context for the model to answer;
  • Link reading: After enabling the deepseek_read_url tool, the model can automatically identify links in user messages, fetch the webpage content, and answer in combination with the context;
  • Model safety: After enabling the safety-check parameter, DeepSeek will provide basic risk control, reviewing model input and output, and returning a refusal identifier when a risk is hit. If you provide application services externally, be sure to enable this parameter and bear obligations such as content safety review, large-model registration, and AI labeling.

In addition, to make it easier for developers to integrate their own workflows more flexibly, the above underlying capabilities and voice capabilities all support being called individually as standalone interfaces, including: Search, Fetch, OCR, ASR, TTS.

Using the above interfaces, developers can implement features essentially consistent with the DeepSeek App. To intuitively demonstrate this effect, DeepSeek has built and open-sourced a lightweight front-end Demo based on the new API, which supports directly importing DeepSeek conversation history.

  • Demo experience entry: https://cdn.deepseek.com/chat-demo
  • Sample code entry: https://github.com/deepseek-ai/chat-demo

According to IT Home, when users call the DeepSeek API to use extended capabilities, in addition to Token fees, they will also be charged for calls to the relevant tools.

  • Text / image search: 5 yuan / thousand calls
  • Webpage fetching: 5 yuan / thousand calls
  • Text recognition: 1.5 yuan / thousand pages
  • Speech recognition: limited-time 50% off, 0.39 yuan / hour after discount
  • Speech synthesis: limited-time 50% off, 1.5 yuan / ten thousand characters after discount

Advertisement statement: External redirect links contained in this article (including but not limited to hyperlinks, QR codes, passcodes, and other forms) are used to convey more information and save selection time; the results are for reference only. All articles on IT Home that contain external links include this statement.

Related Articles

  • DeepSeek web / API services return to normal after a 45-minute outage this afternoon
  • (Update: Restored) DeepSeek web / API services suffer partial outage, showing "server temporarily unavailable"
  • DeepSeek web / API services experience partial outage; officials are investigating
  • DeepSeek proposes Super-agent architecture design: dual-layer Router and Worker architecture to explore a more autonomous Agent system
  • DeepSeek completes a new round of funding of 10 billion yuan; sources say "Lenovo-affiliated" investors participate
  • Challenging Silicon Valley giants, sources say DeepSeek's latest funding round raised nearly 100 billion yuan

The translation is machine-generated and individual terms may be off. Nothing is rewritten or cut; the original is authoritative.

Published by IT之家
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗