LLM gateway
A single access point for all models, with budgets and quotas.
The LLM gateway provides a single OpenAI-compatible access point to European AI models. Per-team keys, budgets, quotas and usage tracking: generative AI under control.
- Open source souverain · LiteLLM (MIT)
- ○ MCP integration in progress
- Access on request (AI Lab)
Illustrative preview, fictional data
Features
Everything you need, nothing that tracks you.
OpenAI-compatible API
Switch providers without rewriting your applications.
European models
Mistral AI and open models, routed from Europe.
Per-team keys
A virtual key per team or per project.
Budgets and quotas
Spending and debit limits to avoid surprises.
Usage tracking
Usage by key, by model and by day.
Apollon foundation
All Apollon calls go through this gateway.
Powered by Apollon
Ask, and Apollon handles it in LLM gateway.
The MCP server for LLM gateway is being integrated: Apollon will soon be able to act on your behalf, with your approval.
- « Create a key for the data team with a €50 budget »
- « Which team is using the most this month? »
- « List available models »
Use cases
- Give the entire company access to generative AI, with budget controls.
- Replace OpenAI with a European model without changing your code.
- Track AI usage for each project.
The European alternative to
Hosted in Europe
On our servers in France, beyond the reach of the Cloud Act.
Secure single account
Eurathos sign-in with two-factor authentication and passkeys.
Open source souverain · LiteLLM (MIT)
Self-hosted, updated and secured by Eurathos.
Saved
Data backed up off-site, restore tested.
Works with
Ready to switch to LLM gateway ?