DeepSeek-V4-Pro
DeepSeek’s open flagship: a 1.6-trillion-parameter model under the plain MIT licence.
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 you will find 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.
Where it’s strong
Coding agents working across large repositories.
Analysing very long documents, up to a million tokens.
Competitive programming and maths-heavy reasoning.
Where to be careful
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.
Price in rupees
For scale: 1,000 requests of about 3,000 tokens in and 1,000 out cost $7.80 — a long prompt and a page of answer each. Every rate is published and stays the same from one request to the next. See every model.
Specs
deepseek-v4-proUsing it from Sri Lanka
DeepSeek-V4-Pro is billed in rupees, on the same monthly invoice as every other model your team uses — no foreign card, no separate DeepSeek account, and one key for all of it.
Prompts sent to DeepSeek-V4-Pro are processed outside Sri Lanka. If a workload has to stay in the country, Qwen3.8-27B (Colombo) runs on our own servers in Colombo.
Call it
Use the OpenAI SDK you already have — point it at Roar AI and name the model. 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."}],
)Compare DeepSeek-V4-Pro
Questions
How much does DeepSeek-V4-Pro cost in Sri Lanka?
Input is $1.56 per 1M tokens; output is $3.12 per 1M tokens. For scale, 1,000 requests of about 3,000 tokens in and 1,000 out cost $7.80. The rate is published and does not change from one request to the next.
Can I pay for DeepSeek-V4-Pro in Sri Lankan rupees?
Yes. Usage is billed to one monthly invoice in rupees, together with every other model your team uses, and you can also pay by card. There is no separate DeepSeek account to open and no foreign card needed.
Does DeepSeek-V4-Pro keep data in Sri Lanka?
No — prompts sent to DeepSeek-V4-Pro are processed outside Sri Lanka. If your data has to stay in the country, use Qwen3.8-27B (Colombo), which runs on our servers in Colombo.
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.