Skip to main content

Documentation Index

Fetch the complete documentation index at: https://www.edenai.co/docs/llms.txt

Use this file to discover all available pages before exploring further.

Eden AI exposes a regional endpoint that routes your requests exclusively through providers and models cleared for European processing. Use it when your workload requires data residency in the EU or when your compliance posture forbids fallback to providers outside the region.

​
Base URLs

RegionBase URL
Global (default)https://api.edenai.run
EUhttps://api.eu.edenai.run
Everything else — your API key, authentication header, request bodies, response shapes — is identical. You only swap the host.
Your API key works on both endpoints. There is no separate EU key to issue.

​
Calling the EU endpoint

curl -X POST https://api.eu.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/mistral-large-latest",
    "messages": [{"role": "user", "content": [{"type": "text", "text": "Bonjour"}]}]
  }'

​
Discovering EU-available models

When you hit the discovery endpoints on api.eu.edenai.run, the response is automatically filtered to providers and models that are available in the EU.
Discovery endpoints (/v3/models, /v3/info) are public — no API key needed to browse availability.
curl https://api.eu.edenai.run/v3/models
Each model entry carries a regions array so you can see at a glance which regions cover it: 
{
  "id": "mistral/mistral-large-latest",
  "object": "model",
  "owned_by": "mistral",
  "regions": [{ "code": "eu", "name": "Europe" }],
  "capabilities": { "pdf": true, "reasoning": false, "web_search": false, "tool_calling": true }
}

​
Error: provider not available in the EU

If you call the EU endpoint with a model or provider that has not been cleared for European processing, Eden AI rejects the request before any provider is contacted. HTTP 451 — Unavailable For Legal Reasons LLM endpoints (/v3/chat/completions, /v3/embeddings, …) return the error in OpenAI-compatible shape: 
{
  "error": {
    "message": "Provider(s)/model(s) google/gemini-3.5-flash are not available on the EU endpoint.",
    "type": "request_forbidden",
    "param": null,
    "code": "region_not_allowed"
  }
}
Universal AI and expert-model endpoints (/v3/universal-ai) return the same status with the FastAPI envelope: 
{
  "detail": {
    "error": "Provider or model not available in this region",
    "message": "Provider(s)/model(s) <provider/model> are not available on the EU endpoint."
  }
}
In both cases the gate runs ahead of input validation and file fetching, so a rejected request never touches the upstream provider, never spends credits, and never leaves the EU boundary. Detect the rejection programmatically via the HTTP 451 status, or via code: "region_not_allowed" on LLM responses.
The same check applies to every provider you list in the request — including fallbacks and any provider you pass via model. A single non-EU entry in the list will reject the whole call.

​
Behavior notes

  • Caching is region-scoped. Cached responses on the global endpoint and the EU endpoint never share state.
  • Sandbox works the same way. Calls authenticated with sandbox_api_token honor the same regional filtering — point your sandbox traffic at api.eu.edenai.run to mirror the production routing.
  • Fallback respects the region. When a fallback list is provided, every entry must be EU-eligible. Non-EU fallbacks trigger a 451 the same way a non-EU primary does.
  • No silent downgrade. There is no automatic re-route from the EU endpoint to the global endpoint. If no EU-eligible provider exists for your request, the call fails — it does not leak out of the region.

​
Next Steps

LLM Models

Browse available LLM models and their regions

Expert Model Providers

Discover providers per feature in the EU

Servers Location

Where Eden AI and its providers host data

Data Retention

How long Eden AI keeps your data