DeepSeek-V4.1-Flash costs $0.195 per million input tokens and $0.78 per million output tokens on Roar AI. DeepSeek’s current default: fast, low-cost, reads images, and ahead of the bigger V4-Pro on DeepSeek’s own tests.
Example: 1,000 requests with 3,000 input and 1,000 output tokens each cost $1.36. Every rate is published and stays the same from one request to the next. See every model.
Rates as of 20 November 2026.
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 | $0.195 | $0.78 | Low-cost coding and tool use. |
| DeepSeek-V4-Pro | $1.56 | $3.12 | DeepSeek’s larger model, for hard coding and maths in text. |
| GPT-6 Luna | $0.10 | $0.50 | Simple, high-volume calls with reasoning switched off. |
| Claude Opus 5.5 | $4 | $20 | 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%.
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."}],
)Input is $0.195 per 1M tokens; output is $0.78 per 1M tokens. For example, 1,000 requests with 3,000 input and 1,000 output tokens each cost $1.36.
Yes. Every model on Roar AI is on the same API key and the same monthly invoice, so switching from DeepSeek-V4.1-Flash to another model only means changing the model name in your code.
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.