gpuflow-ctrllive
regionSpain
hardwareNVIDIA B200
models·token factory
- DeepSeek V4 Proready·~23 ms
active sandboxes·sandbox
- claude-code@sandbox-001· proactivo·1h 23m
active gpus·gpu dedicada
- gpu-002· 1× B200activo·2h 41m
gpuflow
Token Factory, Sandbox and a dedicated GPU on a single European cluster.
Start with the API, spin up a persistent Sandbox you manage yourself (with agent templates ready if you want them) or reserve a full B200 GPU. All on European infrastructure, with one balance in euros.
- cert.ISO 27001 · ENS Medium
- data inEU · Spain
- invoicein EUR
- computeNVIDIA B200
products
Combine all the AI infrastructure you need.
Inference with the API, agents in the Sandbox, heavy workloads on a dedicated GPU, separately or combined. All on a single balance, one invoice.
API
Token Factory
LLM API compatible with OpenAI + Anthropic SDKs
curl api.gpuflow.ai/v1
- < 100 ms TTFT
- ·NVIDIA B200
- ·prepaid
from 0.06 €/ M input tokenscredit from 10 €
SANDBOX
Sandbox
SSH container with preinstalled agent templates
ssh dev@sandbox-001
- Internal RDMA
- ·DDN EXAScaler
- ·configurable auto-suspend
from 0.15 €/ active hour+ volume from €5/month
GPU
Dedicated GPU
A whole B200 or a MIG slice, by the month or year.
nvidia-smi -L
- MIG or full
- ·NVIDIA B200
- ·180 GB · FP4
from 1.10 €/ hourmonthly reserved −10%
see it in action
Watch it run.
API, Sandbox and GPU on the same European cluster and the same provider. Switch tabs and watch it go.
soporte.acme.com
powered by GPUFlowHi! I'm Acme's assistant. How can I help?
How do I change my payment method?
Sure. Go to Settings → Billing, tap “Payment method” and add your card. It applies instantly and never interrupts your service.
qwen-3.5-9b · TTFT 41 ms · España
infrastructure
Sovereign hardware, no shared tenant.
Dedicated NVIDIA B200 GPUs, RDMA fabric, parallel storage and certifications your DPO can read. All in Spain.
01NVIDIA B200
NVIDIA B200
Latest-gen accelerators, dedicated, on bare metal. No shared tenant.
02Spain
Spain
Data center on Spanish soil. No international transfers, no sub-processors outside the EU.
03RDMA internal network
RDMA internal network
Low latency between nodes for multi-GPU and sustained throughput in production.
04DDN EXAScaler
DDN EXAScaler
High-speed parallel storage for datasets, checkpoints and persistent volumes.
05ISO 27001
ISO 27001 · ENS Medium
Operational certifications. Standard DPA ready to sign. Optional zero retention for enterprise.
06Spanish invoice in EUR
Spanish invoice in EUR
Deductible for EU companies and freelancers, valid for intra-EU reverse charge. No USD/EUR conversion, no month-end FX surprises.
models
Open source models, deployed and ready.
All models run on our own infrastructure in Spain. Prices per million tokens, input and output split. If you need another model, ask us.
- DeepSeek
- Z.ai
- Alibaba
Prices in EUR per million tokens, VAT included. Check the full pricing for credit tiers, volume discounts and sandbox rates.
The names and logos of DeepSeek, Z.ai, Alibaba, Google, Meta and NVIDIA are trademarks of their respective owners. They appear here solely to indicate the open-source models we serve on our infrastructure.
support
You email us. A human answers.
No tickets, no chatbots, no queues. We are a small team in Spain. If you have a technical question, an invoice to reconcile, or need a model we have not yet deployed, you email us and we reply.
Primary channel
[email protected]A continuous email thread. No ticket queues, no lost context. You write, we reply.
frequently asked questions
What people almost always ask before starting.
Where is my data processed?
All data is processed at a datacenter in Spain. It never leaves the European Union and is not replicated to other regions. The platform is ISO 27001 and ENS Medium certified, and we have a standard DPA ready to sign.
Is it compatible with the OpenAI or Anthropic SDK?
Yes. The API exposes /v1/chat/completions (OpenAI) and /v1/messages (Anthropic). Point your SDK at api.gpuflow.ai with your API key and the catalog models are available directly. We support SSE streaming and function calling where the model allows it.
Do I need an account to try? Do I need a card?
Account yes, 1 minute with email or SSO. Card no, on confirming your account you get 5 € of credit to call the API or spin up a Sandbox without paying anything.
How does billing work?
Prepaid model. Top up credit when you want and consume by real usage, measured in tokens (Token Factory) or active hours (Sandboxes). Automatic notification when balance drops below 20%. Deductible Spanish invoice on every top-up.
What happens if the environment goes idle?
We only charge for the hours the sandbox is active. After the idle time you configured (from 10 min to 4 h, or manual stop only) with no SSH activity or user processes, it suspends automatically and stops billing compute. Your persistent volume survives intact and is available again in 5-8 seconds on reconnect.
Can I cancel or delete my sandbox?
Yes, anytime from the dashboard. Billing is prorated to the exact moment of cancellation. If you delete, the persistent volume and all snapshots are removed; you have up to 7 days to undo the deletion if it was accidental.
Do you have a public SLA?
Yes, we publish real-time status at gpuflow.ai/status. The contractual SLA with support response times is agreed in enterprise plans.
Your AI infrastructure, sovereign and in euros.
Data that never leaves Europe, billing in euros and one balance across API, Sandbox and GPU. Create an account and start with €5 free, no card required.
Building a European startup? Apply for up to €5,000 in credits