AI Infrastructure from Europe

The European
AI Inference API.

GDPR-compliant. ISO certified. No training on your data. Servers in Germany and Finland — OpenAI drop-in replacement.

Get API Key Documentation

Pay-per-use — no monthly fees. From $0.20/1M tokens.

GDPR / DSGVO

Fully compliant

ISO 27001

Certified

No Training

Never on your data

DPA

Included

Models & Pricing

28 EU-hosted Open Source Models

Open source models hosted in European data centers. Pay-per-use — no monthly fees.

Model	Context	Input /1M	Output /1M
GLM 5.2 ~z-ai/glm-latest	1M	$1.40	$4.40
GLM 5.2 z-ai/glm-5.2	1M	$1.40	$4.40
Kimi K2.7 Code ~moonshotai/kimi-latest	256K	$0.95	$4.00
Kimi K2.7 Code moonshotai/kimi-k2.7-code	256K	$0.95	$4.00
Nemotron 3 Ultra 550B A55B nvidia/nemotron-3-ultra-550b-a55b	256K	$0.60	$2.90
MiniMax M3 ~minimax/minimax-latest	1M	$0.40	$1.40
MiniMax M3 minimax/minimax-m3	1M	$0.40	$1.40
DeepSeek V4 Pro ~deepseek/deepseek-latest	1M	$1.80	$3.60
DeepSeek V4 Pro deepseek/deepseek-v4-pro	1M	$1.80	$3.60
DeepSeek V4 Flash deepseek/deepseek-v4-flash	1M	$0.20	$0.30
Qwen3.6-35B-A3B ~qwen/qwen-small-latest	256K	$0.25	$1.20
Qwen3.6-35B-A3B qwen/qwen3.6-35b-a3b	256K	$0.25	$1.20
Kimi K2.6 moonshotai/kimi-k2.6	256K	$0.90	$4.00
Gemma 4 26B A4B google/gemma-4-26b-a4b-it	256K	$0.13	$0.40
Gemma 4 31B google/gemma-4-31b-it	256K	$0.20	$0.50
Qwen3.5-9B qwen/qwen3.5-9b	250K	$0.80	$1.25
Qwen3.5-122B-A10B qwen/qwen3.5-122b-a10b	256K	$0.40	$3.00
Qwen3.5 397B A17B ~qwen/qwen-latest	256K	$0.60	$3.60
Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b	256K	$0.60	$3.60
FLUX 2 Klein black-forest-labs/FLUX-2-klein-9b	—	Free	Free
Qwen3-VL-30B-A3B-Instruct ~qwen/qwen-vl-latest	256K	$0.25	$0.75
Qwen3-VL-30B-A3B-Instruct qwen/qwen3-vl-30b-a3b-instruct	256K	$0.25	$0.75
gpt-oss-20b openai/gpt-oss-20b	128K	$0.07	$0.20
gpt-oss-120b openai/gpt-oss-120b	128K	$0.09	$0.36
Qwen3 Coder 480B A35B ~qwen/qwen-coder-latest	256K	$0.40	$1.60
Qwen3 Coder 480B A35B qwen/qwen3-coder	256K	$0.40	$1.60
Llama 4 Maverick meta-llama/llama-4-maverick	1M	$0.35	$1.00
Mistral Nemo mistral/mistral-nemo	59K	$0.10	$0.15

All models hosted exclusively on European servers.

API documentation

Plug and Play

Serve the latest AI models via API

We offer full compatibility with OpenAI API, allowing you to easily integrate powerful language models into your applications using OpenAI's official libraries.

Uptime in 30 days: 99.999%
Latency on average: 45ms
per Million Tokens (*Depends on model): $0.20

Full API documentation

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: process.env.LLMBASE_API_KEY,
  baseURL: 'https://api.llmbase.ai/v1'
});

const chat = await openai.chat.completions.create({
  model: "~z-ai/glm-latest",
  messages: [{ role: "user", content: "Hello!" }],
});

from openai import OpenAI

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

response = client.chat.completions.create(
    model="~z-ai/glm-latest",
    messages=[{"role": "user", "content": "Hello!"}]
)

curl https://api.llmbase.ai/v1/chat/completions \
  -H "Authorization: Bearer LLMBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "~z-ai/glm-latest",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'