DeepSeek: Web Chat, App and API Guide

Use DeepSeek for conversation, writing, coding and working with documents. This page brings together its web, mobile, Harness desktop and API entry points, with an explanation of reasoning and search.

Product overview

About the DeepSeek product

DeepSeek brings conversation, multi-step reasoning, verifiable web search and coding into one assistant. Those capabilities are accessible through four product entry points.

Developed by
Hangzhou DeepSeek
Product name
The brand is written DeepSeek; English materials also use the spaced form Deep Seek.
Ways to access
Web chat, an iOS/Android app, Harness for desktop, and the API platform.
Main capabilities
Deep Thinking and Smart Search, plus coding and work with long documents and tables.
Models and licences
The family includes DeepSeek-V4.1, DeepSeek-V4 and the R1 reasoning series. R1 weights are available under an MIT licence.
Typical uses
Everyday questions, writing, project development and applications using the API.
Capability guide

Tasks DeepSeek supports

The chat interface provides Deep Thinking and Smart Search switches. The first expands reasoning; the second uses verifiable web information in the answer.

Using Smart Search

Search combines answers with verifiable pages from the web. Questions about current versions, news or prices can therefore use recent information instead of only stored knowledge.

Open-weight models

Some DeepSeek models have openly released weights. R1 uses an MIT licence and supports research, local deployment and fine-tuning.

Harness on the desktop

Harness is a desktop agent for documents, spreadsheets and code. Plugins extend its capabilities, and longer tasks can continue in the background.

Integrate through the API

Your application can call the models through a request format compatible with mainstream SDKs. Streaming responses and structured output are supported.

Drafting and research tasks

Use it to draft and revise text, summarise long reports, compare options and organise raw material into structured conclusions.

Using Deep Thinking

The model works through its reasoning before giving an answer. This is suited to mathematics, logic and tasks requiring several steps.

Access options

Choose from four access methods

All four access options use the same underlying models. They differ mainly in use scenario and whether installation is required.

Access method Supported devices Installation required? Open the service
DeepSeek App iOS or Android devices Yes; use the official app store Find the official DeepSeek app in App Store or a mainstream Android store
DeepSeek Harness desktop Desktop computers Desktop app installation required Visit the official Harness page
DeepSeek API access Applications and servers No installation; register and create an API key platform.deepseek.com
DeepSeek browser access Devices with a web browser Not required chat.deepseek.com
Help and answers

DeepSeek questions answered

About the DeepSeek product

DeepSeek is a general-purpose AI assistant and model family developed by Hangzhou DeepSeek. DeepSeek is the brand spelling; the spaced English form Deep Seek refers to the same product.

How is DeepSeek priced?

The web chat can be used free of charge. API calls are billed for input and output tokens; rates depend on the model and the platform pricing page.

Where can I get the DeepSeek app?

The web version needs no download: open the official chat address in a browser. For mobile, look for the official app in App Store or a mainstream Android store; the official Harness page provides desktop access.

Can the API search and crawl web pages?

Yes. Smart Search uses verifiable web sources in the browser app. The API also offers web search and page crawling, documented in the official API guide.

Continue reading

Chinese guides for practical use

The Chinese pages provide more detail on models, API setup and practical tutorials.