How much does IONOS AI Model Hub cost?

IONOS AI Model Hub pricing: Per token usage.

Is IONOS AI Model Hub open source?

No, IONOS AI Model Hub is not open source.

Home / Inference APIs / IONOS AI Model Hub

IONOS AI Model Hub

OpenAI-compatible API for open-weight LLMs and image models, hosted in IONOS EU data centers

IONOS AI Model Hub is the inference API from IONOS, the German hosting and cloud provider. It serves open-weight models through an OpenAI-compatible REST API: Llama 3.1 from 8B to 405B, Mistral variants, gpt-oss-120b, Qwen3 Coder, FLUX.1 and FLUX.2 for image generation, and multilingual embedding models.

Pricing is per token, starting around $0.17/1M tokens for Llama 3.1 8B, with per-image pricing for the FLUX models. Everything runs in IONOS-operated EU data centers with ISO 27001 certification and GDPR compliance, which makes it one of the larger European alternatives to US-hosted inference APIs.

Pricing: Per token usage

Hosting Cloud

Pricing Usage Based, from $0.11/1M tokens (Qwen3.5-9B)

HQ 🇩🇪 Germany

Compliance GDPR

Visit website →

Pricing

Screenshot of IONOS AI Model Hub webpage

IONOS AI Model Hub prices by model

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

Model	Input / 1M	Cached / 1M	Output / 1M	Checked	Notes
Llama 3.3 70B Instruct	€0.65	–	€0.65	25 Sep 2026	Price on ionos.de; the US site lists $0.71 / $0.71
Qwen3.8 27B	€0.40	–	€2.70	15 Oct 2026	Excl. VAT (zzgl. USt). The US site (cloud.ionos.com) lists $0.45/$2.70.
gpt-oss-120b	€0.15	–	€0.65	25 Sep 2026	Price on ionos.de; the US site lists $0.17 / $0.71