LLMBase

llmbase

Updated 40 minutes ago

LLMBase is a European AI platform hosted in Germany that provides access to 100+ AI models including GPT, Claude, Gemini, Grok, DeepSeek, Llama, Qwen, and MiniMax through an OpenAI-compatible API. The platform emphasizes privacy with zero data retention, GDPR compliance, and EU-hosted infrastructure. LLMBase offers both a consumer chat interface and an inference API for developers, with subscription plans starting at $9/month that include access to models from multiple providers.

Visit Website LLMs.txt

Browse 17 LLM models available from LLMBase. Compare prices and features.

Models (17)

Organization	Model Name	Original Model	Input	Output
DeepSeek	DeepSeek V4 Pro	`deepseek/deepseek-v4-pro`	-	-	View
DeepSeek	DeepSeek V4 Flash	`deepseek/deepseek-v4-flash`	-	-	View
Moonshot AI	Kimi K2.6	`moonshotai/kimi-k2.6`	-	-	View
Z.ai	GLM-5.1	`z-ai/glm-5.1`	-	-	View
qwen	Qwen3.6 35B A3B	`qwen/qwen3.6-35b-a3b`	-	-	View
google	Gemma 4 26B-A4B	`google/gemma-4-26b-a4b-it`	-	-	View
Minimax	MiniMax M2.5	`minimax/minimax-m2.5`	-	-	View
qwen	Qwen3.5-122B-A10B	`qwen/qwen3.5-122b-a10b`	-	-	View
qwen	Qwen3.5-35B-A3B	`qwen/qwen3.5-35b-a3b`	-	-	View
qwen	Qwen3.5-397B-A17B	`qwen/qwen3.5-397b-a17b`	-	-	View
Z.ai	GLM-5	`z-ai/glm-5`	-	-	View
qwen	Qwen3.5 9B	`qwen/qwen3.5-9b`	-	-	View
Moonshot AI	Kimi K2.5	`moonshotai/kimi-k2.5`	-	-	View
DeepSeek	DeepSeek-V3.2	`deepseek/deepseek-v3.2`	-	-	View
OpenAI	GPT OSS 120B	`openai/gpt-oss-120b`	-	-	View
qwen	Qwen3-Coder	`qwen/qwen3-coder`	-	-	View
Nvidia	Nemotron 3 Nano Omni 30B A3B Reasoning	`nvidia/nemotron-3-nano-omni-30b-a3b-reasoning`	-	-	View

Back to Providers Visit Website