One single door to all your LLMs
The AI gateway open-source LiteLLM, installed and maintained by DINAO. Call 100+ models in OpenAI format from a single point, hosted on our French servers — keys, costs, and access under your control.
What is LiteLLM?
LiteLLM is an open-source AI gateway providing unified access to more than 100 language model providers — OpenAI, Anthropic, Gemini, Bedrock, Azure, Cohere, local models… — all through an OpenAI-compatible format. You call any LLM with the same interface, and you switch models without rewriting your code.
Beyond routing, LiteLLM adds a layer of governance: virtual keys per team or project, spend tracking, guardrails, load balancing, logging and an administration dashboard. It is the tool for centralizing and controlling all of an organization's AI calls.
On the technical side, the proxy relies on Python, PostgreSQL in production and Redis under heavy load, with performance of a few milliseconds of latency at around a thousand requests per second. Deployed in containers by DINAO and routed to a local model, it becomes a sovereign gateway hosted in France.
Host LiteLLM at DINAO
Resource tiers compatible with LiteLLM prerequisites (minimum 1 vCPU / 1 Go / 5 Go). Hosted in France, fully managed.
- 1 allocated vCPU
- 2 GB RAM
- 20 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 2 allocated vCPU
- 4 GB RAM
- 40 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 4 allocated vCPU
- 8 GB RAM
- 80 GB NVMe
- Daily backups
- Managed & monitored by DINAO
- 8 allocated vCPU
- 16 GB RAM
- 160 GB NVMe
- Daily backups
- Managed & monitored by DINAO
Managed LiteLLM hosting in France
Self-hosting LiteLLM means a server to maintain, security updates, backups and monitoring. With our managed LiteLLM hosting, you use the application: we run the infrastructure.
- Deployed in minutes, always kept up to date
- Daily backups included
- Continuous monitoring, data hosted in France (GDPR)
- Prefer self-hosted with root access? LiteLLM also runs on our Docker VPS.
This application uses AI
The container hosts the application, not the AI engine (which requires dedicated GPUs) : inference is handled externally, with your own provider key. Prioritize a sovereign engine — Mistral AI, NumSpot, Scaleway, or OVHcloud AI Endpoints (France, GDPR) ; an international provider (OpenAI, Anthropic…) only if a specific capability requires it. Inference subscriptions are not included in hosting.
Technical details
You may also like…
Other applications managed by DINAO in the same category, hosted in France and GDPR compliant.
You might be wondering…
Does LiteLLM host models or call them?
It's a gateway : it routes your calls to the provider of your choice, in OpenAI format. You can point it to a local model hosted by DINAO (sovereign) or to an external API.
Do my prompts stay in France?
The gateway, its keys, and its logs run on your instance in France. If you route it to a local model, your prompts do not leave; if routed to an external API, the content goes to the provider (see sovereignty note).
How to control costs and access?
LiteLLM allows creating virtual keys by team or project, tracking spending (spend tracking), setting quotas and guardrails — centralized governance of your AI calls.
Do I need to rewrite my code to change models?
No. All models are exposed in OpenAI format : you change provider or model via configuration, without modifying your application.
Can the gateway handle the load?
Yes. With PostgreSQL and Redis, LiteLLM handles high traffic (around 1000 req/s) with low latency. Higher tiers add load-balancing and high availability.
