DeepSeek Chat: The 2026 Guide to the Web App, Mobile and API

If you have searched for “deepseek chat”, you are probably trying to answer one concrete question: where do you actually type a prompt, and is it free? The short answer is that DeepSeek chat exists in three places — the browser app at chat.deepseek.com, the official iOS and Android apps, and a developer API that is compatible with the OpenAI and Anthropic formats. They look similar, but they bill differently, remember conversations differently, and expose different controls. This guide walks through each surface as of October 2026 and shows you which one to pick for everyday questions, long-document work, coding, or building your own product on top.

What “DeepSeek chat” actually means in 2026

The phrase gets used three different ways, and most confusion online comes from mixing them up:

• The web chat at chat.deepseek.com — a free ChatGPT-style interface in the browser.
• The mobile apps on iOS and Android, which use the same DeepSeek account as the web.
• The legacy API model ID deepseek-chat, which developers used to call from code. It was scheduled for retirement on 24 July 2026 and is no longer listed in DeepSeek’s docs; details below.

According to DeepSeek’s 17 October 2026 Change Log, the official web and app models were updated to DeepSeek-V4.1-Flash-1017 — the same model the API serves under the name deepseek-flash. The API also offers deepseek-v4-pro, served by DeepSeek-V4-Pro-0813. Both API models have a 1M-token context window and up to 384K tokens of output, and both are published as open weights under the MIT license on Hugging Face. If you want the deeper model story, see our dedicated DeepSeek V4 page.

The web chat at chat.deepseek.com

This is what most people mean by “DeepSeek chat”. Open the site, sign in with your DeepSeek account, and you land on a clean conversation pane with a prompt box at the bottom. No credit card is needed to chat.

Expert Mode and Instant Mode

These are the mode names DeepSeek has used in its own announcements. Its 24 April 2026 V4 preview announcement invited users to try the new models at chat.deepseek.com “via Expert Mode / Instant Mode”, and its 13 August 2026 release notes said V4 Pro was available on the app and web via “Expert Mode”. The 17 October 2026 Change Log then said the official web and app models had been updated to DeepSeek-V4.1-Flash-1017.

DeepSeek’s documentation does not describe today’s mode selector in more detail, so treat the labels you see in the app as the reference — they have changed between releases before. The older “DeepThink” button, which DeepSeek’s August 2025 V3.1 announcement described as the Think/Non-Think toggle, belongs to the previous generation.

Features the web chat gives you

• File upload. DeepSeek’s Change Log has mentioned file upload and webpage summarisation in the chat product since December 2024. The docs do not list the chat’s current file types or size limits, so check the upload menu.
• Web search. DeepSeek’s 17 October 2026 Change Log says its web and API search capabilities are powered by its in-house search engine.
• Chat history. Conversations are kept with your account; DeepSeek’s Privacy Policy (updated 10 February 2026) says you can manage, copy or delete your chat history in settings.

The mobile apps

The official DeepSeek app on the App Store and Google Play pairs with the same account. DeepSeek’s 17 October 2026 announcement says DeepSeek-V4.1-Flash-1017 is live on its website, app and API. If you need help picking between browser and app on a given device, our DeepSeek browser vs app comparison lays out the trade-offs (battery, share-sheet access, typing comfort, file handling).

Two points worth knowing before you install:

• Verify the publisher. Several lookalike apps exist. On Google Play the developer is shown as “DeepSeek”; on the App Store the seller is “Hangzhou DeepSeek Artificial Intelligence Co., Ltd” (store listings checked 23 October 2026). Cross-reference with our guide to verifying the official DeepSeek app.
• Availability varies by region. Italy’s data-protection authority ordered the app blocked in January 2025, and several US states restrict it on government devices. Check our availability by country page before travel.

Is DeepSeek chat free?

The consumer web and mobile products are free to use with an account. DeepSeek does not publicly document a daily message cap as of October 2026. The API is separate and billed per token — that is where “free” stops.

If your goal is to build something (a script, a bot, a product), you will want the API. That is a different surface and a different mental model. Full pricing on the DeepSeek API pricing page; a side-by-side of consumer vs developer access is in our DeepSeek free vs paid write-up.

The developer side: the API behind the chat

Developers call DeepSeek through HTTPS. Chat requests hit POST /chat/completions, the OpenAI-compatible endpoint at base URL https://api.deepseek.com. DeepSeek also offers an Anthropic-compatible interface at a separate base URL, https://api.deepseek.com/anthropic, so the Anthropic SDK works by setting that base_url and your DeepSeek api_key.

Here is a minimal Python example using the OpenAI SDK, following the pattern in DeepSeek’s “Your First API Call” page (the key comes from an environment variable):

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("DEEPSEEK_API_KEY"),
    base_url="https://api.deepseek.com",
)

resp = client.chat.completions.create(
    model="deepseek-flash",
    messages=[
        {"role": "system", "content": "You are a concise assistant."},
        {"role": "user", "content": "Summarise the Treaty of Westphalia in three bullets."},
    ],
    reasoning_effort="high",
    extra_body={"thinking": {"type": "enabled"}},
)
print(resp.choices[0].message.reasoning_content)  # reasoning
print(resp.choices[0].message.content)            # final answer

Thinking mode is the default on both API models, with reasoning_effort set to "low", "high" (the default) or "max"; the response returns reasoning_content alongside the final content. To opt out, pass extra_body={"thinking": {"type": "disabled"}}. Two technical points that catch newcomers out:

1. The API is stateless. DeepSeek does not remember previous turns on its side. You must resend the full messages array with each request. Contrast that with the web chat, which keeps history server-side for your account.
2. Thinking mode is a parameter, not a separate model. Both deepseek-flash and deepseek-v4-pro accept the same reasoning_effort / thinking fields. There is no “reasoner” model to choose.

Step-by-step setup, authentication, key management and error handling are covered in our DeepSeek API getting started tutorial.

The legacy deepseek-chat model ID

If you find the string deepseek-chat in older code or tutorials, it refers to a legacy API model ID, not to the web chat. From 24 April 2026, DeepSeek pointed deepseek-chat and deepseek-reasoner to the non-thinking and thinking modes of deepseek-v4-flash, and scheduled both names for retirement on 24 July 2026 at 15:59 UTC; they are no longer listed in the official docs. deepseek-v4-flash is itself now a legacy name that DeepSeek serves with DeepSeek-V4.1-Flash-1017. Migrating is a one-line change — set model="deepseek-flash" (or "deepseek-v4-pro"); the base_url does not change.

Pricing snapshot for the API

Prices per 1 million tokens, as of October 2026, from DeepSeek’s Models & Pricing page. Off-peak rates are half the peak rates. Peak hours are 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays; all other hours, including weekends, are off-peak.

deepseek-flash is the default choice for chat-shaped workloads and the only current API model that accepts images. Worked cost examples are on the DeepSeek API pricing page, and our DeepSeek cost estimator handles quick what-ifs on your own numbers.

Web chat vs API: a decision table

Where DeepSeek chat fits in the field

DeepSeek’s own positioning has shifted with each release, so date any claim you read. At the April 2026 V4 preview launch, DeepSeek described V4-Pro as having “performance rivaling the world’s top closed-source models”. On 10 September 2026 it said tests by multiple parties put V4.1-Flash ahead of V4-Pro on performance, cost, speed and total runtime. For DeepSeek-V4.1-Flash-1017, the model behind the web and app since 17 October 2026, the Change Log reports DeepSeek’s own scores of 42.6 on HLE without tools and 77.0 on DeepSWE v1.1. These are DeepSeek-reported numbers, not independent evaluations.

For head-to-head context, see DeepSeek vs ChatGPT and DeepSeek vs Claude. For the wider competitive field, the AI comparison hub carries the full set.

Privacy, regions and what to avoid pasting

DeepSeek processes web and app conversations on servers governed by Chinese law. That is a legitimate concern for sensitive client data, regulated information (health, legal, financial) or anything under NDA. If you fall into any of those categories, either run the open weights on infrastructure you control (see our install DeepSeek locally tutorial) or route through a provider hosted in a jurisdiction you trust. The longer discussion is on our DeepSeek privacy page.

Quick reference: which surface for which job

• Casual questions, drafting, study help: the web chat or the mobile app.
• Long research or long documents: the web chat, with file upload and web search.
• Coding agent or automated script: the API, deepseek-flash with thinking enabled (reasoning_effort "high" or "max"); deepseek-v4-pro is also available.
• High-volume classification or extraction: the API, deepseek-flash, JSON mode, system prompt cached.
• Anything sensitive or regulated: the open weights on your own infrastructure, or a trusted host.