Grunden AI
OpenAI-compatible API for open-weight models, run on Grunden's own GPU clusters in Nordic data centers
Grunden AI serves open-weight models through an OpenAI-compatible API, with an Anthropic-compatible Messages endpoint too. Inference runs on its own Nvidia B300 clusters in Nordic data centers, with no external model providers in between.
Chat models today are GLM 5.3, GLM 5.3 Flash and Gemma 4 26B, plus endpoints for embeddings, reranking, PII redaction, speech-to-text and text-to-speech.
Billing is per token in EUR from a prepaid wallet, with no minimum volume. Async requests cost half.
Pricing: Per token usage
Grunden AI prices by model
Per 1M tokens, read off Grunden AI's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| GLM 5.3 | €0.90 | €0.90 | €1.80 | 15 Oct 2026 | Standard plan (cached input at the input rate). Cache plan: EUR 1.50 in / 0.40 cached / 4.00 out. Async at half price. |
| GLM 5.3 Flash | €0.20 | €0.20 | €0.60 | 15 Oct 2026 | Standard plan (cached input at the input rate). Cache plan: EUR 0.40 in / 0.08 cached / 1.20 out. Async at half price. |
Grunden AI Alternatives
Explore 135 products in the Inference APIs category. View all Grunden AI alternatives.
Heabsy
EU inference API on its own GPUs in the EEA, with zero data retention and OpenAI- and Anthropic-compatible endpoints.
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
Inceptron
EU-hosted LLM inference with an in-house compiler: serverless open-weight model APIs and dedicated GPU deployments
Hetzner GPU Servers
Dedicated single-GPU servers with NVIDIA RTX PRO Blackwell cards, billed hourly, in Finland and Germany
TrustRoute
OpenAI-compatible LLM gateway hosted in Switzerland, with per-workload rules on which models data may reach
Work on Grunden AI? Feature it at the top of Inference APIs.
Is your product missing?