Keera Gateway
One endpoint for every model in the company
Keera Gateway is a Swiss LLM gateway. Your teams reach every model through one base URL, external providers only where your policy allows. Policies, budgets and audit in one place.
How Keera Gateway works
Everything that calls a model points at the same address. The gateway checks each request, writes it to the log and passes it on.
Your tools
- Coding agent in the terminal and the IDE
- Internal apps and copilots
- Notebooks and CI jobs
Keera Gateway
- Identity and team from your IdP
- Check policy, quota and budget
- Redact secrets and personal data
- Route to the model that is allowed
Models
- Open models on Keera Engine in Switzerland
- Your fine-tunes and on-prem clusters
- External providers, opened by policy
Every request into the audit log and your SIEM
OpenAI- and Anthropic-compatible: existing SDKs and agents switch with one environment variable. The providers and models are in the model catalogue, the setup in the documentation.
Four things Keera Gateway controls
One endpoint that belongs to you - and four decisions it makes on every single request.
The end of shadow AI
Block direct egress at the proxy and every AI request in the company becomes visible.
A policy per team
Which models and data classes a team or an API key can reach is written as a versioned policy - enforced on every request.
Cost you can attribute
Spend by team, API key and cost centre, with hard budget limits and an alert before the invoice.
Audit and redaction
Secrets and personal data are stripped at the edge. Who, which model, how many tokens and which decision stream immutably into your SIEM - the prompt itself does not.
Web UI or CLI, the same control
Policies, budgets, teams, models and every session are a few clicks away in the web UI. The keera CLI does the same from a script or your pipeline, and both write the same versioned policy. Anyone who just wants to chat opens Keera Chat, under the same policy.
Because every request goes through one endpoint, you finally see what your company does with LLMs. The live map draws a line where a request leaves your network and shows how many tokens and francs end up outside. Tokens, cost and refused requests per team, model and period are in the browser or as CSV.
Keera Gateway features
More than a proxy: each of these features works in the web UI and in the CLI.
Guardrails
Allowed models, rate limits and budgets - per organisation, team and key. Versioned, checked on every request, refused when in doubt.
Smart Filters
A small model reads every request and takes out secrets, client names and personal data - or stops it. Measure in shadow mode first, then enforce.
Smart Routers
A small model picks which model answers: the fast local one for short edits, the large one only when the task needs it.
Live map
Clients, gateway and models as a picture, with one line across it: above it stays on your own network, below it leaves the building. Requests cross it live.
Agent Sandboxes
The gateway offers coding agents isolated containers - as a development environment, or for a CI pipeline. Inside, they reach only what they really need.
SSO and roles
Sign-in against your own identity provider, LDAP or Active Directory, permissions from your directory groups. Every change goes into the audit log.
Questions about Keera Gateway
What teams ask us most before they set the gateway up.
Does Keera Gateway store my prompts?
No. Neither the prompt nor the answer is stored. Only the request is kept: who, when, which model, how many tokens, which decision. That gives you cost per team and an audit trail, and the log stays in your infrastructure.
Does Keera Gateway make us more secure?
Yes, mostly through the keys. The keys for every model sit in one place instead of in .env files, CI secrets and laptops. You grant them per team, revoke them in one place, and your applications never see the real key.
Does Keera Gateway help me with the EU AI Act?
Yes. The AI Act asks you to show what your company does with AI. The gateway logs every request with identity, model and decision, so the evidence is there when somebody asks. The compliance work stays yours.
How is Keera Gateway different from other AI gateways?
Others route requests too, and as open source that costs nothing. With Keera you also get the gateway run in Swiss data centres, enterprise support from people in Switzerland, and open models hosted in Switzerland behind it from day one. Your tools change one base URL and keep their APIs, so you stay independent - of us as well. You can read the source code on GitHub.
Does Claude Code work with Keera Gateway?
Yes. The gateway speaks the OpenAI and the Anthropic API. Claude Code, your own agent, an internal app or a notebook point at the gateway's base URL and carry on as before.
Does Keera Gateway add latency?
Very little. Policy, budget and log cost microseconds, next to a model answer that takes seconds. Only Smart Filters and Smart Routers add a small model call, and you switch those on yourself.
Is Keera Gateway lightweight?
Yes. Little memory, no heavy runtime, no farm of services in front of it. You run it next to your applications without building a platform for it.
Is Keera Gateway cloud native?
Yes. It runs as a container, scales horizontally and takes its configuration from the cluster. In your cloud, your cluster or your own data centre, it is the same software.
Questions, comments, quotes
Have a question or a comment? Need a quote for on-premise or an SLA? Write to us.