Understand this story
On November 13, 2026, DeepSeek announced that it will open up the search, file input, URL reading, security check, and voice capabilities behind the DeepSeek App through the DeepSeek API. According to the DeepSeek API changelog, V4.1-Flash (deepseek-flash) supports these built-in capabilities in Messages, Responses, and Chat Completions, with tool calling and context assembly handled server-side; developers can enable them through parameters such as deepseek_web_search and deepseek_read_url, or call standalone APIs such as OCR, ASR, and TTS separately. The company also provides an open-source frontend demo that supports importing DeepSeek conversation history. Extended capabilities are billed separately based on tool usage in addition to standard token fees, and applications aimed at the public must enable security checks, while content moderation, model filing, and AI-generated content labeling remain the developer's responsibility. Tianyi Cui reposted the news and said he looks forward to the community growing more diverse products once the barrier to implementing product features is lowered.
AI-generated from public reports
Developments
1 confirmed developments
- Source:DeepSeek API Changelog
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 16
Caixin
SpaceX Starship's 15th test flight achieves first orbital-return spacecraft recovery; Hong Kong Disneyland suspected of suffering a cyberattack; Seres and Huawei Terminal re-divide responsibilities
On SpaceX Starship's 15th test flight, a spacecraft returned from Earth orbit to the launch site for the first time and was successfully caught by the launch tower's robotic arm; the spacecraft flew for about 22.5 hours, orbited Earth 14 times and deployed 26 third-generation Starlink satellites, but the Super Heavy booster was not recovered as planned. About 17,000 electronic ticket QR codes at Hong Kong Disneyland are suspected to have been stolen; the park has reported the matter to police and suspended ticket sales and hotel bookings on its official website. Seres and Huawei Terminal have re-divided responsibilities, with Yu Chengdong giving up sales leadership.
Nov 15
TMTPost · AGI
Digital Intelligence Weekly: Jensen Huang Resigns as NVIDIA CEO, Alibaba Plans to Spin Off PingTouGe for Hong Kong Listing, Anthropic Launches IPO Roadshow
On November 12, NVIDIA announced that Jensen Huang has resigned from the positions of President, CEO and Director; CFO Colette Kress will serve as interim CEO, and the board has initiated a formal search. During intraday trading, its market capitalization briefly fell below $4 trillion. Alibaba plans to spin off its chip subsidiary PingTouGe for a separate listing on the Main Board of the Hong Kong Stock Exchange via H shares. As of April 2026, cumulative shipments of its Zhenwu series AI chips reached 560,000 units. Anthropic has launched its IPO roadshow, with an offering price of $70-78, corresponding to a valuation of approximately $1 trillion, a notable decline from the $1.5 trillion at the time of filing.
Nov 14
AYi AI Notes
DeepSeek packages web search, document parsing, and voice capabilities as open APIs
DeepSeek has packaged the web search, PDF and Office document parsing, web link scraping, security screening, as well as OCR, ASR, and TTS capabilities from its official App into open APIs. Currently, these are only available for deepseek-flash (V4.1-Flash) and are enabled via parameter switches when calling. On pricing: web search and link scraping cost $0.75 per 1,000 calls, document parsing costs $0.225 per 1,000 pages, speech recognition costs $0.058 per hour, and off-peak input tokens cost $0.15 per million. Meanwhile, DeepSeek has open-sourced the chat-demo frontend project on GitHub under the MIT license; you can run it locally by double-clicking index.html, and it can import chat history exported from the App.
Testing Catalog
AI Daily: Anthropic IPO seeks to raise up to $64.4 billion
Anthropic's IPO is set to be priced on November 18 and to list around November 19 under the ticker ANT, with fundraising of up to $64.4 billion. Gemini 4 Hydrogen is now generally available in GitHub Copilot; the DeepSeek API adds search, file, and voice features, and offers standalone OCR, ASR, and TTS. Sesame exits preview and launches a $20 Plus paid plan and a Pro plan, while keeping the free tier.
QbitAI
DeepSeek Opens the Full Suite Application API, Including Standalone Speech Recognition and Synthesis Interfaces
DeepSeek announced the opening of its full suite application API. Capabilities such as web search, deep-thinking search, file upload, and link reading can all be called individually through standalone interfaces and billed separately; the speech recognition and speech synthesis interfaces are being opened for the first time. The company says developers can replicate the complete DeepSeek App 1:1, and it has open-sourced a lightweight chat front-end demo that supports importing historical conversations. On pricing, speech recognition is originally 0.78 yuan/hour, now at a 50% discount of 0.39 yuan/hour; speech synthesis is 1.5 yuan per 10,000 characters, and OCR is 1.5 yuan per 1,000 pages; the V4.1-Flash model already supports the relevant conversation extension features under the three types of interfaces: Messages, Responses, and Chat Completions.
East Money
DeepSeek Opens Full-Suite App API, Letting Developers Replicate the Complete DeepSeek App
DeepSeek has announced the opening of its full-suite app API. By enabling the corresponding parameters in the existing API, developers can obtain conversational capabilities such as deep-thinking search, file input, link reading, and model safety. The underlying voice-related capabilities have also been opened as independent interfaces, including OCR, ASR, and TTS, and can be called individually or in combination. The V4.1-Flash model (deepseek-flash) now supports these capabilities under the Messages, Responses, and Chat Completions interfaces, with tool calling and context stitching handled automatically by the server. In addition to token fees, extended capabilities are charged separately: text/image search and web scraping are both 5 yuan per thousand calls, text recognition is 1.5 yuan per thousand pages, speech recognition is 0.39 yuan per hour, and speech synthesis is 1.5 yuan per ten thousand characters.
Phoenix Technology
DeepSeek opens up its full suite API, V4.1-Flash supports web search and file parsing
DeepSeek has integrated the App's capabilities—deep-thinking search, file upload, link reading, voice interaction, and text recognition—into its existing API, and the company says developers can replicate the complete DeepSeek App 1:1. V4.1-Flash now supports these capabilities under the Messages, Responses, and Chat Completions interfaces; after enabling parameters such as deepseek_web_search and deepseek_read_url, tool calling and context assembly are handled server-side. The company has also open-sourced a lightweight front-end demo that covers web search, file and image upload, read-aloud answers, voice input, and Markdown and Mermaid rendering.
English text is being prepared.
DeepSeek Opens the Full Suite App API, Allowing Developers to Replicate the Complete DeepSeek App 1:1
DeepSeek has announced the official opening of the full suite app API. By enabling the corresponding parameters in the existing API, developers can obtain chat features such as deep-thinking search and file input, while underlying capabilities including voice and OCR, ASR, and TTS have also been opened as standalone interfaces. Currently, the V4.1-Flash model (deepseek-flash) supports web search, deep-thinking search, file input, link reading, and model safety checks under the Messages, Responses, and Chat Completions interfaces. DeepSeek has also built and open-sourced a lightweight front-end demo based on the new API, which supports directly importing historical conversations; when calling extended capabilities, tool-calling fees will be charged in addition to token fees.
Nov 13
DeepSeek API ChangelogFirst-partySelected
DeepSeek Opens the App's Search, File, Voice and Other Capabilities to the API
English text is being prepared.
Zhidx
DeepSeek Opens Full-Suite App API, Allowing Developers to Replicate the DeepSeek App 1:1
DeepSeek has officially opened the full-suite app API, integrating App capabilities such as web search, deep-thinking search, file input, and link reading into the existing API; developers can call them by enabling the corresponding parameters. It has also opened independent tool interfaces including search, web scraping, OCR, speech recognition, and speech synthesis, and DeepSeek says developers can replicate the complete DeepSeek App 1:1. In addition to model Token fees, using the extended capabilities also requires paying tool invocation fees based on the tools called and usage; DeepSeek-V4.1-Flash (deepseek-flash) already supports multiple new capabilities across the three types of interfaces: Messages, Responses, and Chat Completions.
Phoenix Technology
DeepSeek Opens Full-Suite App API, Letting Developers Replicate the DeepSeek App 1:1
DeepSeek has officially opened its full-suite app API, integrating capabilities such as web search, deep-thinking search, file input, and link reading into the existing API; developers can invoke them by enabling the corresponding parameters. It has also opened independent tool interfaces including search, web scraping, OCR, speech recognition, and speech synthesis. DeepSeek says developers can replicate the complete DeepSeek App 1:1, and it provides a demo and GitHub sample code. In addition to model token fees, using extended capabilities such as web search, file parsing, and speech requires paying tool-call fees based on usage volume; DeepSeek-V4.1-Flash already supports these new capabilities across the Messages, Responses, and Chat Completions interfaces.
Phoenix Technology
DeepSeek Opens Full-Suite App API, Letting Developers Replicate the Complete App 1:1
On November 13, DeepSeek announced the opening of its full-suite app API, integrating web search, file input, link reading, voice interaction, and security verification into the existing API; developers can enable the corresponding parameters to implement complex conversation features in their own applications. The V4.1-Flash model (deepseek-flash) already supports these capabilities under the Messages, Responses, and Chat Completions interfaces, with tool calling and context stitching handled automatically by the server. Search, Fetch, OCR, ASR, and TTS can also be called separately as standalone interfaces. The company has also open-sourced a lightweight frontend Demo that supports importing historical conversations; in addition to Token fees, extended capabilities incur separate tool-calling charges.
Tianyi CuiSelected
DeepSeek Opens Up App's Search, File, Voice and Other Capabilities via API
DeepSeek announced that the search, file, link, safety and voice capabilities behind its App are now available through the DeepSeek API. Developers can enable built-in features with a few parameters, or call standalone APIs such as OCR, ASR and TTS. The company also provides an open-source frontend demo that supports importing DeepSeek conversation history, which can be used to build richer conversations or recreate the full App experience in their own applications. Tianyi Cui reposted the news and said he looks forward to the community growing more diverse products once the barrier to implementing product features is lowered.
DeepSeek
DeepSeek Opens Up App's Search, File, Voice and Other Capabilities via API
DeepSeek announced that the search, file, link, security and voice capabilities behind its App are now available through the DeepSeek API. Developers can enable built-in features with a few parameters, or call APIs such as OCR, ASR and TTS separately, and an open-source frontend demo that supports importing DeepSeek conversation history has been provided.
Heat trend for this story
- Current
- 6
- Period peak
- 105 Nov 14 05:00
- 24-hour change
- -91%
Move the pointer or select the chart to inspect hourly heat. Use the left and right arrow keys with a keyboard.