deepseek-ai/DeepSeek-V4.1-Flash.

deepseek-ai/DeepSeek-V4.1-Flash is available through the Noirdoc gateway.

Get started → Providers and prices

base_url="https://api.noirdoc.de/v1" model="deepseek-ai/DeepSeek-V4.1-Flash"

Data centres in Germany
§ 203 confidentiality
Zero retention
List prices

Details.

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

Data centres in Germany AKI.IO Contracting party: AKI.IO GmbH · based in Berlin, Germany

§ 203 German Criminal Code (StGB): Confidentiality agreed with AKI.IO
Features: Tools, Vision, Reasoning and JSON

See how this looks in your account →

Providers.

We offer deepseek-ai/DeepSeek-V4.1-Flash through these providers.

Provider § 203 model=

€ · 1M tokens Input Cache Read Cache Write Output

AKI.IO DE German data centres

§ 203 agreed

deepseek-ai/DeepSeek-V4.1-Flash

Input 0.25 Cache Read 0.10 Output 1.00

More models.

Model

€ · 1M tokens Input Cache Read Cache Write Output

GPT-6.1 Sol Tools Vision Reasoning JSON GPT-6 model for agentic coding and computer use — also for document-heavy work and multi-step business workflows.

Input 2.16 Cache Read 0.11 Cache Write 2.70 Output 10.78 from 272K input tokens from 272K Input 4.23 Cache Read 0.22 Cache Write 2.70 Output 15.84

GPT-6 Sol Tools JSON Cost-efficient top tier of the GPT-6 family — for agentic coding, business automation and long software engineering tasks.

Input 2.16 Cache Read 0.22 Cache Write 2.70 Output 10.78 from 272K input tokens from 272K Input 4.25 Cache Read 0.44 Cache Write 5.28 Output 15.85

GPT-6 Luna Tools Vision Reasoning JSON Fast and affordable GPT-6 model — for high volumes, chat, classification and light agentic workflows.

Input 0.11 Cache Read 0.011 Cache Write 0.135 Output 0.54 from 272K input tokens from 272K Input 0.212 Cache Read 0.022 Cache Write 0.135 Output 0.792

GPT-5.6 Sol Tools Vision Reasoning JSON Most capable model of the GPT-5.6 family — extended reasoning, agentic workflows and code for the most demanding workloads.

Input 3.95 Cache Read 0.395 Cache Write 4.94 Output 19.75 from 272K input tokens from 272K Input 7.76 Cache Read 0.776 Cache Write 9.70 Output 29.06

GPT-5.6 Terra Tools Vision Reasoning JSON Balanced model of the 5.6 family — GPT-5.5-level performance at significantly lower cost.

Input 1.98 Cache Read 0.198 Cache Write 2.47 Output 11.85 from 272K input tokens from 272K Input 3.90 Cache Read 0.39 Cache Write 4.88 Output 17.46

GPT-5.6 Luna Tools Vision Reasoning JSON Fastest and cheapest 5.6 model — for high volumes and latency-critical applications.

Input 0.20 Cache Read 0.02 Cache Write 0.25 Output 1.19 from 272K input tokens from 272K Input 0.40 Cache Read 0.04 Cache Write 0.50 Output 1.77

GPT-5.4 Tools Vision Reasoning JSON Frontier model for demanding reasoning, agentic workflows and complex production workloads.

Input 2.47 Cache Read 0.247 Cache Write — Output 14.82 from 272K input tokens from 272K Input 4.86 Cache Read 0.486 Cache Write — Output 21.80

GPT-5.4 mini Tools Vision Reasoning JSON Compact GPT-5.4 variant for high throughput at low cost — solid on standard tasks.

Input 0.75 Cache Read 0.075 Cache Write — Output 4.45

GPT-5 mini Tools Vision Reasoning JSON Compact GPT-5 variant for high throughput at low cost — solid on standard tasks.

Input 0.26 Cache Read 0.0256 Cache Write — Output 1.99

GPT-OSS 120B Tools Reasoning JSON OpenAI's open-weight model — near-frontier reasoning with full deployment control.

Input 0.15 Cache Read — Cache Write — Output 0.55

Claude Opus 5.5 Tools Vision Reasoning JSON Opus-class Claude model for demanding reasoning — long-running agents, code review and multi-step changes across large codebases.

Anthropic · EU

Input 3.93 Cache Read 0.20 Cache Write 4.92 Output 19.67

Claude Sonnet 5.5 Tools Vision Reasoning JSON Sonnet-class Claude model for well-defined everyday work — features, bug fixes, documents, presentations and spreadsheets.

Anthropic · EU

Input 1.97 Cache Read 0.20 Cache Write 4.46 Output 9.83

Claude Haiku 4.5 Tools Vision Reasoning JSON Compact Claude model — for high volumes, classification and latency-critical applications.

Anthropic · EU

Input 1.00 Cache Read 0.10 Cache Write 1.25 Output 5.00

Gemini 4 Argon Tools Vision Reasoning JSON Google's flagship of the Gemini 4 generation for long, multi-step tasks such as software engineering, mathematics and agents, with tiered reasoning and 1M tokens of context.

Google Vertex · EU

Input 2.00 Cache Read 0.10 Cache Write — Output 9.90

Gemini 3.8 Flash Tools Vision Reasoning JSON Google's Flash model of the current Gemini generation — built for speed and high throughput.

Google Vertex · EU

Input 1.49 Cache Read 0.149 Cache Write — Output 7.41

Gemini 3.5 Flash Lite Tools Vision Reasoning JSON Compact Flash variant for simple, very frequent tasks — tuned for low latency.

Google Vertex · EU

Input 0.30 Cache Read 0.03 Cache Write — Output 2.47

Gemini 3.1 Flash Lite Tools Vision Reasoning JSON Earlier Flash-Lite generation — stable for existing integrations and simple high-volume tasks.

Google Vertex · EU

Input 0.25 Cache Read 0.025 Cache Write — Output 1.49

Llama 3.3 70B Tools JSON Robust open-weight generalist with good value for money across broad workloads.

Input 0.65 Cache Read — Cache Write — Output 0.65

Mistral Small 24B Tools Vision JSON Mid-sized all-rounder — reliable quality for everyday text and chat tasks.

Input 0.10 Cache Read — Cache Write — Output 0.30

Qwen 3.8 27B Tools Vision Reasoning JSON Compact Qwen model with 27B parameters — a balanced generalist for chat, reasoning and tool calls.

weber.cloud · DE

Input from 0.15 Cache Read 0.10 Cache Write — Output 0.65

Qwen 3.6 35B A3B Tools Vision Reasoning JSON Efficient Qwen MoE — strong in multilingual work and reasoning at low cost.

Input 0.15 Cache Read — Cache Write — Output 0.50

Qwen 3.5 397B A17B Tools Vision Reasoning JSON Large Qwen MoE with 397B parameters, 17B of them active — for code, agents and image and video understanding.

Input 0.60 Cache Read — Cache Write — Output 3.60

Qwen 3.5 9B Tools Vision Reasoning JSON Compact multimodal Qwen model with 9B parameters — an efficient architecture for reasoning, code and image understanding.

Input 0.10 Cache Read — Cache Write — Output 0.20

DeepSeek V4 Flash Tools Vision Reasoning JSON Fast variant of the DeepSeek V4 series — a generalist with strengths in code and analysis.

weber.cloud · DE

Input from 0.30 Cache Read 0.09 Cache Write — Output 1.20

GLM 5 Turbo Tools Vision Reasoning JSON Fast GLM model for agents — optimised for long execution chains, tool use and scheduled workflows.

Input 1.08 Cache Read 0.27 Cache Write — Output 3.60

GLM 5V Turbo Tools Vision Reasoning JSON Natively multimodal GLM agent model — for vision-based coding and planning over many steps.

Input 1.08 Cache Read 0.27 Cache Write — Output 3.60

Apertus 70B Tools Reasoning JSON Open Swiss model, transparently trained — a good generalist with a European focus.

Input 1.25 Cache Read — Cache Write — Output 2.00

claude-haiku-5-5 Tools Vision Reasoning JSON

Anthropic · EU

Input 0.099 Cache Read 0.01 Cache Write 0.124 Output 0.499 from 100K input tokens from 100K Input 0.495 Cache Read 0.05 Cache Write 0.618 Output 2.47

deepseek-ai/DeepSeek-V4-Pro-0813 Tools Reasoning JSON

Input 1.80 Cache Read 0.45 Cache Write — Output 3.60

gemini-4-carbon Tools Vision Reasoning JSON

Google Vertex · EU

Input 2.00 Cache Read 0.10 Cache Write — Output 9.90

google/gemma-4-26B-A4B-it Tools Vision Reasoning JSON

Input 0.10 Cache Read — Cache Write — Output 0.50

google/gemma-4-26B-A4B-it-chat Tools Vision Reasoning JSON

Input 0.10 Cache Read — Cache Write — Output 0.50

google/gemma-4-31B-it Tools Vision Reasoning JSON

Input 0.40 Cache Read — Cache Write — Output 0.60

MiniMaxAI/MiniMax-M2.5 Tools Vision Reasoning JSON

Input 0.27 Cache Read 0.08 Cache Write — Output 1.08

MiniMaxAI/MiniMax-M3 Tools Vision Reasoning JSON

Input 0.36 Cache Read 0.09 Cache Write — Output 1.80

mistralai/Mistral-Small-4-119B-2603 Tools Reasoning JSON

Input 0.20 Cache Read — Cache Write — Output 0.60

moonshotai/Kimi-K3 Tools Vision Reasoning JSON

Input 2.70 Cache Read 0.68 Cache Write — Output 13.50

openai/gpt-oss-20b Tools Reasoning JSON

Input 0.10 Cache Read — Cache Write — Output 0.20

Qwen/Qwen3.5-122B-A10B Tools Vision Reasoning JSON

Input 0.60 Cache Read — Cache Write — Output 3.40

Qwen/Qwen3.8-2.4T-A95B Tools Reasoning JSON

Input 2.25 Cache Read 0.57 Cache Write — Output 5.40

Qwen/Qwen3.8-Flash-Next Tools Vision Reasoning JSON

Input 0.18 Cache Read 0.05 Cache Write — Output 0.45

zai-org/GLM-5.2 Tools Reasoning JSON

Input 2.30 Cache Read — Cache Write — Output 6.90

zai-org/GLM-5.3 Tools Reasoning JSON

Input 1.58 Cache Read 0.40 Cache Write — Output 4.05

zai-org/GLM-5.3-Flash Tools Vision Reasoning JSON

Input 0.18 Cache Read 0.05 Cache Write — Output 0.45

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-ai/DeepSeek-V4.1-Flash",  # provider & model
    messages=[{"role": "user", "content": "Hello"}],
)