Your AI under European law.Run by a German company.

Chat and API with 40+ AI models for teams that need GDPR-ready AI: EU-hosted open models, a DPA for every business, and a clear note on where each model runs.

Start chatting Explore the API

Operated in Germany
No training on your data
GDPR · DPA available

Trusted by companies of all sizes and industries

Your AI under European law

Private by default. European by design.

Leading AI models for your whole team. Prompts and files are not used for training, a DPA covers business use, and every model shows where it runs.

Operated in Germany

LLMBase is run by a German company. Personal data is processed under the GDPR and German data protection law.

No training on your data

Prompts, files, chats, and outputs are not used to train, fine-tune, evaluate, or improve AI models.

You see where each model runs

Open models listed as EU-hosted run in the EU. Proprietary models are processed by their providers and only receive your content when you select them. Terms depend on the model, and we show them per model.

A DPA for your business

Business customers complete the DPA in the dashboard, with technical and organisational measures, subprocessors, and retention terms.

Speed you can compare

Every model lists its measured output speed, so you can pick a fast model for everyday work.

Controls for the whole team

Manage roles, model access, and shared projects from one business workspace.

From Germany. Trusted across Europe.

LLMBase is operated by a German company, and personal data is processed under the GDPR and German data protection law. Teams across the EU get a DPA with technical and organisational measures, EU-hosted open models, and hosting details for every model.

GDPR
DPA available
No training on your data

Read our privacy policy

LLMBase · GermanyEU member states

The latest models

Recently added to LLMBase, with context, speed, and reasoning at a glance.

DeepSeek V4.1 Flash

DeepSeek

EU-hosted

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

1.0M206 tok/sReasoning

GLM 5.3 Flash

Z.ai

EU-hosted

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

1.3M51 tok/sReasoning

Qwen3.8 27B

Qwen

EU-hosted

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

1.0M80 tok/sReasoning

DeepSeek V4 Pro 0423

DeepSeek

EU-hosted

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...

1.0M115 tok/sReasoning

Kimi K3

MoonshotAI

EU-hosted

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...

1.0M53 tok/sReasoning

Kimi K2.7 Code

MoonshotAI

EU-hosted

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...

262K96 tok/s

View all 43 models

One platform. Two ways to work.

A private AI chat for everyone on your team, and an OpenAI-compatible API for everything you build.

For everyone

AI Chat

Chat with privacy-first open models hosted in Europe, and with Claude, GPT, and Gemini when you choose them.

40+ AI Models
Web search and files
Images and reasoning
Shared team projects

Open AI Chat

For developers

Developer Platform

OpenAI-compatible inference for open models on European infrastructure, with pay-as-you-go credits.

OpenAI SDK compatible
Streaming and tool calls
Usage-based billing
Model catalog API

main.py

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmbase.ai/v1",
    api_key=os.environ["LLMBASE_API_KEY"],
)

reply = client.chat.completions.create(
    model="<model-id-from-/v1/models>",
    messages=[{"role": "user", "content": "Hallo!"}],
)

Explore the Platform

Simplify model access