Icon for Melious AI

Melious AI

European inference API serving 60+ open-weight models on OpenAI- and Anthropic-compatible endpoints

Melious AI is a German inference provider serving open-weight models (DeepSeek, GPT-OSS, GLM, Mistral, Kimi, Gemma, Qwen) through endpoints that speak both the OpenAI and Anthropic API formats, so most existing clients work by changing the base URL.

Beyond chat completions it covers embeddings, image generation and speech, all billed per token or per unit rather than by subscription.

Infrastructure runs across European providers in several countries, which is the reason to pick it over a US-hosted equivalent. A separate consumer chat product exists but the API is sold independently.

Pricing: Per token usage

Hosting Cloud
Pricing Usage Based, from EUR 49/month
HQ 🇩🇪 Germany
Compliance GDPR
Screenshot of Melious AI webpage

Melious AI prices by model

Per 1M tokens, read off Melious AI's own pricing page on the date shown.

Model Input / 1M Cached / 1M Output / 1M Checked Notes
DeepSeek V4.1 Flash €0.20 €0.01 €1.00 1 Oct 2026
GLM 5.3 €1.00 €0.20 €3.00 1 Oct 2026
GLM 5.3 Flash €0.10 €0.02 €0.40 1 Oct 2026
Kimi K3 €2.80 €0.70 €14.00 1 Oct 2026
Llama 3.3 70B Instruct €0.60 – €0.65 1 Oct 2026
MiniMax M3 €0.40 €0.10 €2.00 1 Oct 2026
Qwen3.8 27B €0.40 €0.10 €2.40 1 Oct 2026
gpt-oss-120b €0.04 – €0.20 1 Oct 2026
gpt-oss-20b €0.03 – €0.13 1 Oct 2026

Work on Melious AI? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →