General
Pricing
Pay per token, per GPU-hour or per TB stored. Our list prices are on this page, and storage comes with no egress or API fees.
From
€0.05
per 1M tokens
Open models hosted in Europe. Pay per token, per seat or for a dedicated endpoint.
From
€2.66
per GPU-hour
Dedicated NVIDIA clusters on fixed terms from 1 to 60 months.
Pay-as-you-go
€7.99
per TB/month
S3-compatible storage in Europe. No egress fees and no fees for API calls.
Same models, same API. Pay per token while traffic varies, give each person on your team a seat, or reserve dedicated GPUs for production workloads.
Start instantly
A serverless endpoint. Pay for the tokens you use, and nothing when traffic is quiet.
Pay per token, no commitment
Same API when you go dedicated
Best for new or variable traffic
From €0.01 per 1M tokens
For your team
A flat monthly price per person to chat with open models and your documents.
One price per user, per month
Predictable cost as your team grows
Buy direct or via your IT reseller
From €19 per seat/month
For steady traffic
GPUs reserved for your model, with predictable performance and pricing.
Reserved GPUs, not shared
We run the model for you
Best for steady, high-volume traffic
Commitment pricing, agreed per contract
Prices per 1M tokens, sorted cheapest first. All models hosted in Europe.
MODEL
CONTEXT
INPUT
OUTPUT
TEXT
Nemotron 3 Nano 30B
262K
€0.05
€0.22
Nemotron 3.5 Lightning
1M
€0.05
€0.22
Gemma 3 27B
110K
€0.09
€0.27
Qwen3 30B Instruct
262K
€0.09
€0.27
Qwen3 235B Instruct
262K
€0.18
€0.54
Hermes 4 405B
128K
€0.90
€2.70
GLM 5.1
200K
€1.26
€3.96
GLM 5.2
1M
€1.26
€3.96
Reasoning
gpt-oss-120b
131K
€0.14
€0.54
DeepSeek V4 Pro 0813
979K
€1.19
€3.56
DeepSeek V4 Pro
1M
€1.58
€3.15
Vision
MiniCPM V 4.5
32K
€0.59
€1.00
Kimi K3
1M
€2.70
€13.50
Embeddings
Qwen3 Embedding 8B
41K
€0.01
n/a
Fixed terms from 1 to 60 months. Longer terms get a lower rate, and you see the full price before you order.
From
€2.66
per GPU-hour
Clusters in Europe, North America and APAC
Own GPU capacity? List it with us. Tell us what you have, and our GPU team gets back to you.
S3-compatible storage in European data centers, always hot, with one flat price per TB. No storage tiers, no fees for egress and no fees for API calls.
Pay-as-you-go
€7.99
per TB/month
Pay monthly, with no long-term contract. Try it free for 30 days first, no credit card required.
Monthly payment based on demand
No long-term contract
Free egress and API calls
Assisted data migration possible
Core support
Reserved capacity
Partners only
Discounted
price per TB
Commit to capacity for 1, 3 or 5 years, starting at 25 TB. Our best terms for steady, growing storage.
Lower price per TB than pay-as-you-go
1, 3 or 5 year commitment, from 25 TB
Free egress and API calls
Assisted data migration included
Personal support
Tell us what you need. Our team sizes it with you and sends you a quote.
Reserved GPUs for your model, priced per contract
From 25 TB, on 1, 3 or 5 year terms
Custom, bespoke deployments available
Correct, no egress fees under our fair use policy. Fair use means egress in line with normal workloads. If your egress massively exceeds your stored volume over a sustained period, we’ll reach out to find a fair arrangement.
We offer European digital sovereignty with data protection under a single legal framework. Our vertically integrated technology stack delivers enterprise-grade performance, and published prices with no egress or API fees keep costs predictable.
Our headquarters are in Hamburg, Germany, and we operate under strict European data protection law.
Impossible Cloud is privately owned by its co-founders, Dr. Kai Wawrzinek and Dr. Christian Kaul, together with leading European venture capital firms and investors.
In 2021. Since then we have grown to several thousand customers and a strong partner network across Europe.
Per token is a serverless endpoint, so you pay only for the tokens you use. Per seat gives each person on your team one monthly price, from €19. Dedicated reserves GPUs for your model, priced per contract, which costs less once your traffic is steady.
No. Your prompts and responses aren’t cached or logged, and your data never trains our models.
Yes. Pick a model, tell us the workload, and we’ll get you set up.
Mistral, DeepSeek, Qwen, GLM, Hermes, Gemma, Nemotron, gpt-oss, Kimi and MiniCPM, plus vision and embedding models, hosted in Europe (EU or UK). Every model and its price is in the full price list. New families are added as they are released. If you need another model, tell us in the form.
Yes. Change the base URL and the key, and the rest of your code stays as it is.
With separate rates per million input and output tokens. Every model’s price is in the full price list on the managed inference page.
Yes. Per-seat plans start at €19 per user per month, for teams that chat with open models. Talk to sales to set one up.
Dedicated reserves GPU capacity for your model, and we still run it. Talk to sales to size it.
Yes. Impossible Cloud offers multiple regions across Europe, and you can write your data to each region independently.
An always-hot storage model with consistently low latency and high throughput. You can test it on your own workload with a free trial.
It is designed for 99.999999999% (11 nines) durability over a year. Erasure coding distributes data across servers, so disk or server failures don’t lose data. We still recommend versioning, access controls and regular backups.
Most customers use us with Veeam, Acronis, MSP360, Nakivo and Hornetsecurity, with deep or native integrations.
Yes. Object Lock prevents data from being changed or deleted for a defined retention period, for compliance and ransomware protection.
Yes. Full S3 compatibility makes migration straightforward, and reserved capacity plans include migration support at no extra cost.
Dedicated. You get full access to NVIDIA systems, with no sharing and no virtualization layer.
Per GPU-hour, on a fixed term from 1 to 60 months, depending on the cluster. Longer terms get a lower rate, and you see the full price before you order.
Impossible Cloud is the contractual partner, and support is provided through our service framework.
Impossible Cloud is ISO/IEC 27001 certified as a company, and our data centers are certified to ISO 27001, SOC 2 and PCI DSS.
Data is encrypted in transit and at rest, using industry-standard algorithms.
Identity and access management includes role-based access control and multi-factor authentication.
Europe's sovereign cloud platform. Built for businesses. Backed by security. Powered by partners.
Impossible Cloud combines managed inference, bare metal GPU and AI-native storage with enterprise-level performance, advanced security, and simple, transparent pricing — now available in North America.
%201%201.avif)
.svg){kind=small}