OpenAI-compatible Inference API

One AI API under European law.

For developer and compliance teams: OpenAI-compatible, predictable costs, a live model catalog and a DPA in your dashboard. We show you how each model is processed.

AI Chat AI Inference API

GDPR / DSGVO

German company

ISO 27001

Certified data centres

No Training

Never on your data

DPA

Included

Models & Pricing

10 EU-hosted Open Source Models

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

Model	Context	Cache /1M	Input /1M	Output /1M
DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash	1M	$0.05	$0.40	$1.40
GLM 5.3 Flash z-ai/glm-5.3-flash	1M	$0.07	$0.20	$0.60
Qwen3.8 27B qwen/qwen3.8-27b	1M	$0.10	$0.50	$3.20
Kimi K3 moonshotai/kimi-k3	1M	$0.60	$4.00	$18.00
Kimi K2.7 Code moonshotai/kimi-k2.7-code	256K	$0.30	$1.50	$6.30
MiniMax M3 minimax/minimax-m3	512K	$0.10	$0.50	$1.90
DeepSeek V4 Pro deepseek/deepseek-v4-pro	1M	$0.20	$1.80	$3.60
Kimi K2.6 moonshotai/kimi-k2.6	256K	$0.20	$0.90	$4.00
Qwen3 Embedding 8B qwen/qwen3-embedding-8b	31K	$0.00	$0.02	$0.00
gpt-oss-120b openai/gpt-oss-120b	128K	$0.09	$0.18	$0.72

Models in this public API catalog are identified as EU-hosted.

API documentation

Estimate your cost

What would your monthly volume cost?

Pick a model and a typical workload, or adjust monthly token volume, input/output ratio, and cache hit rate yourself.

Get API Key

Model

$0.00

$0.00 blended / 1M tokens

Presets:

Tokens / month

Input / output ratio

85 / 15

Cache hit rate

60%

Plug and Play

Serve the latest AI models via API

Use the documented OpenAI-compatible chat-completions and models API with supported SDKs. Check the reference for endpoint and field boundaries.

Base URLapi.llmbase.ai: /v1
BillingUsage based: API
PricingPer model: Live

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: "deepseek/deepseek-v4.1-flash",
  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="deepseek/deepseek-v4.1-flash",
    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": "deepseek/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'