DeepSeek-V4.1-Flash costs LKR 64.94 per million input tokens and LKR 260 per million output tokens on Roar AI, billed in Sri Lankan rupees on one invoice. DeepSeek’s current default: fast, low-cost, reads images, and ahead of the bigger V4-Pro on DeepSeek’s own tests.
Prices are shown in LKR to make model costs easier to estimate and manage for Sri Lankan teams, with the published US dollar rate beside each.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 455. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 20 November 2026. Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.
deepseek-v4.1-flashFor high-volume coding and tool use, it is a good place to start. DeepSeek reports 74.2% on the DeepSWE coding test, level with Claude Opus 5, and the model reads images as well as text. None of its launch scores were independently checked at release, so test it on your own work.
It is weaker on the hardest reasoning, with 36.8% on Humanity’s Last Exam against Opus 5’s 56.3%. Move up to a larger model if that is the work you need done.
| Model | Input | Output | Choose it for |
|---|---|---|---|
| DeepSeek-V4.1-Flash | LKR 64.94 | LKR 260 | Low-cost coding and tool use. |
| DeepSeek-V4-Pro | LKR 519 | LKR 1,039 | DeepSeek’s larger model, for hard coding and maths in text. |
| GPT-6 Luna | LKR 33.30 | LKR 167 | Simple, high-volume calls with reasoning switched off. |
| Claude Opus 5.5 | LKR 1,332 | LKR 6,660 | The hardest reasoning, where Flash falls behind. |
Prices per 1M tokens.
V4.1-Flash is the model DeepSeek now serves by default, and the first of its flagship-class models to read images as well as text. It is built to be cheap to run, with 552 billion parameters but only 8 billion active while reading your prompt and 16 billion while writing. DeepSeek reports 74.2% on the DeepSWE coding test, level with Claude Opus 5.
Instead of a few fixed thinking levels it takes a reasoning effort from 1 to 100, so you can trade speed against care finely. Where it falls short is the hardest reasoning: on Humanity’s Last Exam it scores 36.8% against Opus 5’s 56.3%.
Roar AI provides access to DeepSeek-V4.1-Flash through the Roar AI gateway, with usage billed in LKR and no foreign card needed. Developers can use DeepSeek-V4.1-Flash alongside other supported models without maintaining a separate integration for every provider.
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-v4.1-flash",
messages=[{"role": "user", "content": "Summarise this contract in plain English."}],
)Requests to DeepSeek-V4.1-Flash are processed in Singapore, outside Sri Lanka.
Roar AI’s locally hosted model is separate and is labelled as such: if a workload has to stay in the country, Qwen 3.8 27B LK runs on our own server in Colombo.
Input is LKR 64.94 per 1M tokens; output is LKR 260 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost LKR 455. Rupee prices are our published US dollar rates converted at LKR 333 to the dollar, our rate for November 2026 — the same rate your invoice uses.
Yes. DeepSeek-V4.1-Flash usage is billed in LKR on one monthly invoice with every other model you use, so there is no foreign card or separate DeepSeek account to set up.
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.
DeepSeek-V4.1-Flash can read up to 1.05M tokens in one request, and write an answer of up to 384K tokens.
It reads images directly. You can still send it a PDF: Roar AI turns each page into text first, at no extra charge.
Create a free account, get an API key and call DeepSeek-V4.1-Flash with the OpenAI SDK, billed in Sri Lankan rupees.