AI News

DeepSeek Opens Full-Suite App API, Letting Developers Replicate the Complete App 1:1

Phoenix TechnologyUpdated Nov 13 23:35

AI summary

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.

Why read this

AI score 67

The original article lists how capabilities such as web search, file input, and voice are integrated into the API, helping developers assess the scope that can be replicated and the billing method.

Topics

Tags

Body · AI translation

DeepSeek Opens "Full Suite" App API: Developers Can Replicate the Complete DeepSeek App 1:1

Phoenix Tech Download the App | Exclusive First Look November 13, 2026, 22:41:15 | From Beijing

Phoenix Tech News (Editor/Yunfei) On November 13, DeepSeek announced the official opening of its "full suite" app API, integrating capabilities from the DeepSeek App—including web search, file input, link reading, voice interaction, and security verification—into its existing API. By enabling the corresponding parameters, developers can implement complex conversational features in their own applications, and even replicate the complete DeepSeek App 1:1.

According to the official introduction, the V4.1-Flash model (deepseek-flash) now supports web search, deep-thinking search (autonomously searching the web and reading links during multi-step reasoning), file input (PDF, Office, images, and other formats), link reading, and model security verification under the Messages, Responses, and Chat Completions interfaces. The related tool calls and context assembly are all handled automatically by the server.

In addition, the above underlying capabilities and voice capabilities (Search, Fetch, OCR, ASR, TTS) can all be called individually as standalone interfaces, making it easier for developers to integrate them into their own workflows. DeepSeek has also open-sourced a lightweight front-end demo that supports importing historical conversations. On pricing, when users invoke the extended capabilities, in addition to token fees, corresponding tool-call fees will also be charged.

Source

Phoenix Technology