English
Contact sales

Full power of AI, full control of your data.

Hosted in the European Union, no model training on your data, an audit trail behind every action. You pay only for what you actually use.

Start free Talk to us
  • No credit card needed
  • Data stays in the EU
  • No training on your data
  • Pay only for real usage

Full power of AI, full control of your data.

Processed and stored in the European Union, on European infrastructure.

One platform instead of six subscriptions.

Chat, deep research, automations, knowledge, code and data sit on one account. One place to grant access, one trail to answer a question in, one bill at the end of the month. Your organization decides which models are available, who may use them, and how much they may spend.

What your team gets

Five parts, one account, one set of permissions.

How it works

Three decisions, and the platform holds the rest.

  1. 01

    Bring your models, or use ours.

    Point a deployment at a provider you already pay for, or pick from the catalogue. The name in the request is your own name for the model, so swapping what is behind it changes nothing in your code.

  2. 02

    Give it your knowledge.

    Upload documents into a knowledge base. Answers are grounded in what you uploaded and cite the exact passage, with the page it came from. Access is granted per base, per group and per person.

  3. 03

    Let it act, within limits.

    Agents reach the outside world through a broker that mints a capability for one run and nothing more. Anything with consequences can wait for a second person to approve it.

Every answer comes with a receipt.

One line per request, written once and never edited: the key, the model, the tokens, the cost. Agent runs are hash chained, so removing a step after the fact breaks the chain and can be detected.

Time Key Model Status Tokens Latency
09:24:11 service:chat-api gpt-oss-120b 200 4,379 6615 ms
09:24:04 key:prod-eu glm-5.2 200 1,429 742 ms
09:23:58 service:agents-api gpt-oss-120b 200 1,529 866 ms
09:23:51 key:prod-eu mistral-large 200 1,409 556 ms
09:23:44 service:chat-api glm-5.2 200 1,348 627 ms
09:23:36 service:research-api gpt-oss-120b 200 379 937 ms
09:23:29 key:ci glm-5.2 429 0 12 ms
09:23:21 service:chat-api gpt-oss-120b 200 1,347 1062 ms

Built for a company that has to answer for it

The questions your security review will ask, answered by how the platform is built rather than by a policy document.

  1. Data in the European Union

    Processed and stored in the EU, on European infrastructure, under European law.

  2. No training on your data

    Your prompts, documents and files are never used to train a model, ours or anybody else's.

  3. Prompts are not archived by default

    The trail keeps metadata, token counts and cost. Keeping the full request body is a decision an organization makes, not the default.

  4. One organization cannot see another

    Every token carries the organization it belongs to, and every service derives access from that token rather than from anything the client sends.

  5. Least privilege, enforced server side

    Roles map to a fixed catalogue of permissions. The interface hides what you may not do and every backend independently refuses it.

  6. Retention you set, with legal hold

    Two clocks: the payload is scrubbed, then the record is deleted. A legal hold suspends both until it is lifted.

Read the security model

You pay for what actually ran.

No seats to forecast, no plan to grow into. Usage is priced per unit, taken from a balance you top up, and refused before it is spent rather than invoiced after.

  1. Metered per unit

    Tokens per model, web searches, seconds of code execution, function runs, stored data per day, document operations and site runtime.

  2. Reserved before the call

    The worst case cost of a request is held against the balance before it goes upstream, so a burst of parallel requests cannot spend the same money twice.

  3. A budget per key

    Give an integration its own ceiling. When it is reached the key is refused, and the refusal says which limit stopped it.

  4. One bill, in euro

    Everything on one invoice, with the usage behind it visible per day, per model and per key.

How billing works

Our blog

All writing

Questions we are asked before the first call

Short answers. The longer ones are on the security and pricing pages.

Where is our data processed?
In the European Union. The platform runs on European infrastructure and the databases, object storage and audit trails stay in the EU.
Do you train models on our data?
No. Prompts, documents and generated files are used to answer your requests and for nothing else.
Which models can we use?
The ones your organization enables. The catalogue is per organization and an administrator decides what appears for everybody else. Open weight models such as Llama, Mistral, Qwen and gpt-oss run on European infrastructure and cost the same to call as any other entry in the catalogue, so keeping a workload on open source is a choice about price and independence rather than a compromise on how it is used.
Can we use our own provider account?
Yes. A deployment maps a name you choose to a provider and an upstream model, so your requests keep using your name for it.
What happens when the balance runs out?
The next paid request is refused with a reason rather than run on credit. Spend limits per key and per organization work the same way.
Is there a contract or a minimum?
No subscription is required to start. You top up a balance and use it, and you can set a limit so nothing runs beyond it.

Start with a question, not a project.

Create an account, ask something real, and look at what the trail recorded. That is the whole evaluation.

Start free Talk to us