Your unified LLM gateway, hosted in France
🔒 VPS onlyAn AI hub that aggregates and distributes your models behind a unified API, installed and maintained by DINAO. Manage keys, quotas, and billing — routing and logs stay on our French servers.
What is New API?
New API is a next-generation LLM gateway and a aggregation and distribution hub for AI models. It allows cross-conversion of various large language models into OpenAI, Claude, or Gemini-compatible formats, offering a unified interface for model management, at both individual and enterprise scale.
Beyond a simple proxy, New API provides a modern multilingual interface, an integrated billing system (with online payment), multi-provider support with weighted load balancing, a comprehensive analytical dashboard, and advanced token management (model-specific restrictions). Several authentication methods are supported (OIDC, Telegram, etc.).
Written in Go and part of the one-api ecosystem, New API is designed for teams that want to centralize and govern AI access: a single API for all their applications, with quotas, billing, logs, and observability, while remaining in control of their infrastructure.
Host New API at DINAO
Resource tiers compatible with New API prerequisites (minimum 1 vCPU / 1 Go / 5 Go). Hosted in France, fully managed.
Application available on a dedicated VPS
This application requires privileged access to the host machine, incompatible with managed shared hosting. It is installed on a dedicated VPS server where you keep full control — managed by DINAO.
Technical reason: bind-mount d'un chemin hôte (volumes nommés uniquement en managé).
Discover the Docker VPS →Requirements for New API: 1 vCPU, 1 Go, 5 Go. Our Docker VPS at €11 excl. VAT per month covers them.
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…
What is New API for?
New API is a gateway that aggregates multiple LLM providers behind a unified API (OpenAI, Claude, or Gemini compatible). Your applications integrate only one interface, and you centrally manage keys, quotas, billing, and usage statistics.
Can I route to my own models?
Yes. You can distribute both external APIs (with your keys) and local models hosted on your DINAO instance, with load balancing between providers.
How do quotas and billing work?
New API offers fine-grained token management, model-specific restrictions, an analytical dashboard, and an integrated billing system to re-bill or cap usage per user or per key.
Where is the data hosted?
On DINAO infrastructure in France, in one of the available data centers. In local mode, routing and logs do not leave the territory.
Are technical skills required?
The gateway is administered via a web interface. DINAO handles installation, SSO, HTTPS, and updates; your developers configure providers and keys.
