Roar AI
DiscordGet started
All models
DeepSeek · Open weights

DeepSeek-V4-Pro

DeepSeek-V4-Pro costs $1.56 per million input tokens and $3.12 per million output tokens on Roar AI. DeepSeek’s open flagship: a 1.6-trillion-parameter model under the plain MIT licence.

Input$1.56per 1M tokens
Output$3.12per 1M tokens
Context window1Mtokens

DeepSeek-V4-Pro API pricing

Input$1.56 per 1M tokens
Output$3.12 per 1M tokens
Cached input$0.234 per 1M tokens

Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $7.80. Every rate is published and stays the same from one request to the next. See every model.

Rates as of 20 November 2026.

Specs

Made byDeepSeek
ReleasedApril 2026
TypeChat
Context window1M tokens
Longest answer384K tokens
ReadsText
Thinks before answeringYes, adjustable
WeightsOpen (MIT)
Size1.6T total, 49B active
Processed inSingapore
Model iddeepseek-v4-pro

Is DeepSeek-V4-Pro worth the price?

Try DeepSeek-V4.1-Flash before you pay for DeepSeek V4 Pro. Flash costs less, reads images as well as text, and DeepSeek says it now beats V4-Pro on its own tests. Those scores have not been independently checked, so compare the two on your own work.

V4-Pro is the larger model, at 1.6 trillion parameters. DeepSeek reports 80.6% on SWE-bench Verified and a Codeforces rating of 3206 in its top reasoning mode, which makes it worth testing on hard coding and maths.

DeepSeek-V4-Pro and the models to compare it with, priced per 1M tokens
ModelInputOutputChoose it for
DeepSeek-V4-Pro$1.56$3.12Coding across large repositories.
DeepSeek-V4.1-Flash$0.195$0.78A low-cost default for coding, tool use and images.
Kimi K3$3.705$18.525Web research, images and video.
GLM-5.3$1.274$4.004Security analysis and command-line agents.

Prices per 1M tokens.

About DeepSeek-V4-Pro

DeepSeek-V4-Pro is the largest model DeepSeek has released: 1.6 trillion parameters, 49 billion of them at work on each token, with weights open under the MIT licence, the most permissive terms available on a model this size. DeepSeek reports 80.6% on SWE-bench Verified and a Codeforces rating of 3206 in its top reasoning mode.

Much of the engineering went into making a million-token context affordable: DeepSeek says its new attention design cuts the compute per token to about a quarter of V3.2’s at that length. It has three modes (no thinking, think high and think max) and reads text only.

What is DeepSeek-V4-Pro good for?

  • Coding agents working across large repositories.
  • Analysing very long documents, up to a million tokens.
  • Competitive programming and maths-heavy reasoning.

DeepSeek-V4-Pro limitations

  • Text only: it cannot read images.
  • DeepSeek says its newer V4.1-Flash now beats it, and no independent evaluator had reproduced the latest V4-Pro build’s scores at the time of writing.

How to use the DeepSeek-V4-Pro API

Use the OpenAI SDK you already have: point it at Roar AI and set the model name. Read the docs.

from openai import OpenAI

client = OpenAI(base_url="https://api.roar-ai.com/v1", api_key="roar_live_…")

reply = client.chat.completions.create(
    model="deepseek-v4-pro",
    messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)

DeepSeek-V4-Pro FAQ

How much does DeepSeek-V4-Pro cost?

Input is $1.56 per 1M tokens; output is $3.12 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $7.80.

Can I use DeepSeek-V4-Pro alongside other models?

Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from DeepSeek-V4-Pro to another model only means changing the model name in your code.

Is DeepSeek-V4-Pro open source?

Its weights are open under the MIT licence, so you could run it yourself. Through Roar AI you call it like any other model, with no servers to manage.

What is the context window of DeepSeek-V4-Pro?

DeepSeek-V4-Pro can read up to 1M tokens in one request, and write an answer of up to 384K tokens.

Can DeepSeek-V4-Pro read images and PDFs?

It reads text only. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge. Scanned pages need a model that can see images.

Start using DeepSeek-V4-Pro

Create a free account, get an API key and call DeepSeek-V4-Pro with the OpenAI SDK.