Skip to main content
When you call a model through Eden AI, your request is forwarded to the underlying provider, whose own policy governs what happens to it.

​
How Eden AI handles your data

Eden AI stores no request or response content by default, and never trains on your data. You can choose to have us store your request metadata by enabling log retention in your profile settings. See Data Retention for details.

​
How each provider handles your data

The tables below show, for each provider on Eden AI, the country of the company Eden AI contracts with (Incorporated in), whether it may train on your data (Trains?), whether Zero Data Retention (nothing stored) is available (ZDR), and how long data is kept otherwise (Retention). When ZDR is in effect, retention is None. Not verified means the provider offers zero data retention only as an option, and Eden AI has not yet confirmed it is enabled on its account. Until then those providers do not count as zero data retention, and Retention shows the provider’s default. Incorporated in is the country where the provider company that Eden AI signs with is incorporated. For many providers this is a European subsidiary rather than the parent company’s home country: Microsoft Azure, for example, is contracted through Microsoft Ireland Operations. It is not where your data is processed, and the laws of other countries, such as the GDPR, can apply as well. For processing location, see EU data residency.
This information was last updated on 23 October 2026.

​
LLM providers

​
Models that keep data on a ZDR provider

A Yes above is the provider’s default. These models keep data even on a provider marked Yes, so they never count as zero data retention: Scaleway keeps no data in normal operation, but may store full requests for up to two weeks when it detects misuse or a server error. To check a specific model, read the zero_data_retention field of its provider entry in Listing Models, for example vertex/claude-opus-5: true means no data is kept, false means it is, null means not verified yet. The same model can have different values on different providers. With view=models, read the field on each entry under endpoints. The field already includes these exceptions.

​
Expert Model providers

Beyond LLMs, Eden AI offers Expert Models for OCR, document parsing, image, audio, video, translation, and web search. The providers below are specific to those features; the LLM providers above also serve some Expert Models, with the same data handling. Trains? reads “May train” only where a provider trains on your data with no opt-out.

​
EU data residency

This is a separate question from retention: it is about where your data is processed, not whether it is stored. To keep processing inside the EU, use the EU endpoint (api.eu.edenai.run), which routes only through EU-eligible providers: Amazon Bedrock (eu-west-1, Ireland), Google Vertex (EU multi-region), Microsoft Azure (EU Data Zone), Arkane Cloud, Mistral, OVHcloud and Scaleway (EU-hosted), and Databricks, Nebius and Qwen (EU-region routing). Confirm the live list any time with api.eu.edenai.run/v3/models.

​
Reduce your data exposure

  • Zero Data Retention (nothing stored): for LLMs, pin your model and fallbacks to Amazon Bedrock, Cerebras, Cloudflare, DeepInfra, Fireworks, Flex AI, Google (Vertex), Infomaniak, IONOS, Microsoft Azure, Nebius, OVHcloud, Scaleway, Tencent, TensorX, xAI, or Z.ai, minus the models listed under Models that keep data on a ZDR provider. The simplest way is to set routing.zero_data_retention: true on the request (see Requiring zero data retention), which only routes to models whose zero_data_retention is true. For Expert Models, pick a provider marked Yes in the table above.
  • EU processing: use the EU endpoint (see EU data residency above).
  • Logs off by default: Eden AI stores no content unless you enable log retention.