All models

DeepSeekOpen weights

DeepSeek V4 Flash.

DeepSeek V4 Flash is DeepSeek's mixture-of-experts model with 284 billion parameters, of which 13 billion are active. It suits code, reasoning and agent workflows; the vision variant also understands images, documents and charts with the same text performance.

base_url="https://api.noirdoc.de/v1" model="deepseek/deepseek-v4-flash-max"

  • Data centres in the EU
  • no § 203 agreement
  • Zero retention
  • List prices

Details.

Where the model runs, which rules apply and what it can do.

§ 203 German Criminal Code (StGB)
No provider of this model has a confidentiality agreement
Weights
Open weights
Features
Tools, Vision, Reasoning and JSON
See how this looks in your account →
Map: DeepSeek V4 Flash.

Providers.

We offer DeepSeek V4 Flash through these providers.

Provider § 203 model=
€ · 1M tokens Input Cache Read Cache Write Output
Weber Cloud
deepseek/deepseek-v4-flash-max Max
Input 0.10 Output 0.10
Weber Cloud
deepseek/deepseek-v4-flash-think Think
Input 0.10 Output 0.10
Weber Cloud
deepseek/deepseek-v4-flash-vision-exp Vision (exp)
Input 0.10 Output 0.10
All DeepSeek models →

Get started.

Test selected models right away with €5 starter credit — every model from the first top-up. If you have questions first, talk to our sales team.

python · openai sdk api.noirdoc.de/v1
import os
from openai import OpenAI

client = OpenAI(
    # one line, that's all
    base_url="https://api.noirdoc.de/v1",
    api_key=os.environ["NOIRDOC_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash-max",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)