Comparison · different shapes of GPU cloud

AxForge vs RunPod

Q: Where does AxForge process data?

In the EU only: serverless inference in eu-se-1 (Stockholm) and dedicated GPU rentals in eu-es-1 (Málaga). The region is pinned per API key, and prompts are processed with zero retention.

RunPod is a large on-demand GPU cloud built for instant scale; AxForge is an EU-hosted provider renting dedicated named machines per hour, on demand or by the week, month or year, with a zero-retention hosted model API.

eu-es-1 · Málaga eu-se-1 · Stockholm DGX Spark from €0.85/hour

Check availability Get API access Create an account, reserve capacity in the console and receive SSH access to your allocated system. 3M free tokens every 30 days with every new account.

At a glance

On-demand scale vs named machines

Dimension	AxForge	RunPod
What it is	A European infrastructure operator: dedicated machines plus a hosted open-model API, on hardware AxForge owns.	A large on-demand GPU cloud: rent GPU capacity on demand, at scale.
How you get compute	Create an account. Your API key is in the console. Check availability or reserve a dedicated DGX Spark in the console and receive SSH access to your allocated machine.	Sign up and launch in minutes, fully on demand.
GPU menu	Short and named: NVIDIA DGX Spark (GB10, 128 GB unified memory), Available; RTX 6000 Pro, RTX 5090, RTX 3090, H100, H200 and B200: request capacity in the console.	A very large menu of GPU types across on-demand pods and serverless workers.
Billing model	Dedicated machines by the hour, week, month or year: €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year; per-token billing on the hosted API.	Per-second, on-demand billing. Spin up and down as you need.
Hosted inference	A managed OpenAI-compatible model API (Qwen3.8 27B available now, plus embeddings, image and speech) with zero prompt retention.	Bring your own containers and models; serverless workers scale them for you.
EU data residency guarantee	EU-only by construction: serverless inference in eu-se-1 Stockholm (region pinned per key), dedicated GPUs in eu-es-1 Málaga.	Datacenters in many regions worldwide; you choose where a workload runs.
Hardware transparency	Named, owned machines with published serving details.	You pick a GPU SKU from the menu; the platform operates the fleet.

Honest routing

When RunPod is the better choice

A large on-demand GPU cloud wins on these requirements:

A huge on-demand pool	You need dozens of GPUs this minute from a very large on-demand pool.
Burst capacity	Spiky training or batch workloads where per-second billing and instant scale-up beat a reserved machine.
A specific GPU SKU	You want a particular card from a very large menu of GPU types.
Serverless workers	You want your own containers scaled up and down automatically, including to zero.

Honest routing

When AxForge is the better choice

EU sovereignty requirements	Processing must stay in the EU and you must be able to prove it: named machine, named region, pinned per key.
Predictable dedicated capacity	One named machine, your traffic only, a flat hourly, daily, weekly or monthly rate. No bidding, no preemption, no noisy neighbours.
A hosted model API	You want open-model inference as a managed API with zero prompt retention, instead of operating your own serving stack.
Auditability	You need to tell an auditor exactly what hardware ran the workload and how it was configured, and get answers from the engineers who run it.

The substance

What AxForge actually runs

Regions	eu-se-1 · Stockholm for serverless inference and RTX 3060 rentals, eu-es-1 · Málaga for dedicated DGX Spark workloads.
Data handling	Zero prompt retention: in-memory processing in Sweden, no disk, no logs, no training. Only billing metadata is kept. Full policy: axforge.ai/privacy.
API	OpenAI-compatible at https://api.axforge.ai/v1, with TLS 1.3 terminated in the EU.
Pricing	Qwen3.8 27B: €0.32 / 1M input · €2.00 / 1M output (launch pricing). GPU rentals: €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year for a dedicated DGX Spark. Full price list published.
Dedicated systems	NVIDIA DGX Spark (GB10, 128 GB unified memory) with full SSH access, by the hour, week, month or year from €0.85/hour, in eu-es-1 · Málaga. Check availability. Additional GPU classes: request capacity in the console.

FAQ

AxForge vs RunPod: common questions

Is AxForge a RunPod alternative in Europe?

For EU sovereignty requirements and predictable dedicated capacity, yes: AxForge rents dedicated named machines by the hour, week, month or year from EU regions and runs a zero-retention model API. For instant on-demand scale, burst workloads and a huge GPU menu, a large GPU cloud like RunPod is the better fit.

Can I rent a GPU machine from AxForge today?

Yes. NVIDIA DGX Spark systems (GB10, 128 GB unified memory) are rentable by the hour, week, month or year from Málaga, Spain (eu-es-1): Check availability or reserve the next available start in the console and receive SSH access to your allocated machine. RTX 6000 Pro, RTX 5090, RTX 3090, H100, H200 and B200 capacity can be requested in the console.

Does AxForge have per-second billing like RunPod?

AxForge bills dedicated machines by the hour, week, month or year: €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year, and the hosted model API per token. If you need per-second billing and scale-to-zero, an on-demand GPU cloud is the right tool.

What does the AxForge model API cost?

Qwen3.8 27B is €0.32 per million input tokens and €2.00 per million output tokens (launch pricing). GPU rentals carry published launch pricing too: a dedicated DGX Spark is €1.19/hour on demand · €0.95/hour by the week · €0.91/hour by the month · €0.85/hour by the year, and the full price list is public.

Where does AxForge process data?

In the EU only: serverless inference in eu-se-1 (Stockholm) and dedicated GPU rentals in eu-es-1 (Málaga). The region is pinned per API key, and prompts are processed with zero retention.