> ## Documentation Index
> Fetch the complete documentation index at: https://docs.prisme.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# LLM Provider Data Retention & ZDR
> A neutral, sourced comparison of data retention and Zero Data Retention (ZDR) options across major AI model providers.
Prisme.ai's [LLM Gateway](/api-reference/llm-gateway) can route inference to several external model providers, or to self-hosted models. The data-retention behaviour of a request therefore depends on the **provider and route you choose**, not on Prisme.ai alone. This page summarises, as neutrally as possible, what each major provider documents about retention and **Zero Data Retention (ZDR)**, with links to the official sources.
For **which of these routes Prisme.ai treats as production-compliant** (and which are evaluation-only), see [Prisme.ai Data-Retention Posture](/resources/security/prisme-data-retention-posture). For how Prisme.ai itself handles your data, see [Data Privacy](/resources/security/data-privacy) and [Compliance](/resources/security/compliance).
**Method & scope.** Statements below are drawn from each provider's official documentation and public privacy policies, verified against the live pages on **26 June 2026**. Exact terms (scope, price, eligibility, regions) must be confirmed in your signed contract and subprocessor list. **Public ZDR and contractual ZDR do not always overlap.** Items that could not be confirmed from a static official page are explicitly flagged as *to confirm contractually*.
## How to read this page
Two things are frequently conflated and should be kept distinct:
* **Opt-out of training** — the provider does not train on your data. Common, often default on paid tiers.
* **Zero Data Retention (ZDR)** — the provider does not *store* your inputs/outputs at all (beyond what is technically required to return the response).
A provider can offer the first without the second. For a strong requirement (regulated sector, strict NDA, sensitive personal data), ask for a **signed ZDR arrangement** plus an independent audit report (SOC 2 Type II or ISO 27001) that covers the retention policy.
## Summary table
| Provider | ZDR by default | How to obtain ZDR | Scope covered | Hosting / residency |
| ----------------------------- | ---------------------------------------------- | -------------------------------------------- | ----------------------------------------------------------------- | ------------------------------------------------------------------ |
| **OVHcloud AI Endpoints** | Yes — contractual (no storage, even ephemeral) | Nothing to configure | Inference (open-weight models) | OVHcloud (European / sovereign positioning) |
| **Mistral La Plateforme** | No | Scale plan, stateless API calls only | Stateless inference | EU by default; explicit US endpoint hosts in US |
| **Anthropic (direct API)** | No, but minimal retention | ZDR arrangement on approval | Messages API, Token Counting, Claude Code (Commercial/Enterprise) | Region-routed (data residency feature) |
| **AWS Bedrock** | Yes for standard models | Set mode `none` (lock via SCP) | Inference; some models excluded | Per chosen AWS region; cross-region inference can move processing |
| **Google Vertex / Gemini** | No | Disable cache + opt out of abuse logging | Inference; not all features | Per chosen GCP region; residency configurable |
| **Azure AI Foundry / OpenAI** | No | "Modified abuse monitoring" (Limited Access) | Stateless inference | Per region; deployment type (Global / DataZone) affects processing |
## Provider details
### OVHcloud AI Endpoints
**Default (contractual).** OVHcloud's *Conditions Particulières des Services Public Cloud* (Annex 10 — AI Endpoints, version 28 April 2025) state that the service *"ne comprend ni sauvegarde ni stockage, même éphémère"* (**no backup or storage, even ephemeral**) and that *"OVHcloud n'a aucune connaissance des Inputs et des Outputs … ne les réutilise pas, de quelque manière que ce soit … n'effectue aucune sauvegarde des Inputs ou des Outputs"* (**OVHcloud has no knowledge of, does not reuse, and does not store inputs or outputs**). The marketing page adds that only billing data is kept and that data is never used to train or improve models. Models are **third-party open-weight products** under their own open-source licences — there is **no access to proprietary models** such as Claude or GPT.
Hosting is positioned as **European / sovereign (OVHcloud)**, but the public page does not enumerate specific regions — **confirm the serving region** in your contract.
**Sources:** [AI Endpoints product page](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/) · [Capabilities & limits](https://docs.ovhcloud.com/en/guides/public-cloud/ai-machine-learning/ai-endpoints-capabilities) · OVHcloud Public Cloud Special Conditions, Annex 10 — AI Endpoints (28 April 2025) · [AI Code of Conduct](https://contract.eu.ovhapis.com/1.0/pdf/AI_Code-FR.pdf) · [Model licences](https://endpoints.ai.cloud.ovh.net/models/licences/opensource)
### Mistral La Plateforme
**Default.** No ZDR. Inputs and outputs are kept for **30 rolling days** for abuse monitoring, then deleted (*"unless zero data retention is activated"*). Data from the **paid API tiers is not used for model training** (contractual).
**ZDR.** Available **only on the Scale plan** and **only for stateless API calls**. It does **not** apply to stateful APIs/products — the documentation lists *agents, batch processing files, conversations, libraries, `/v1/files`, Vibe Work, and Chat*.
**Residency.** *"By default, your data is hosted in the European Union."* You may explicitly use the **US API endpoint**, in which case data is hosted in the United States.
**Subprocessors** (Mistral Trust Center, as of 26 June 2026). Cloud infrastructure: **Microsoft — Sweden, Norway** (Le Chat, La Plateforme, Mistral Code) and **Google — Netherlands, United States** (Le Chat, La Plateforme US API). Billing: **Stripe** (United States) and **Lago** (Ireland) for paid subscriptions. This confirms the EU-by-default route via Microsoft and the US-endpoint route via Google US. Certifications: **ISO 27001, ISO 27701, SOC 2 Type II** (GDPR is a regulation the policy complies with, not a certificate). Subscribe to Trust Center notifications to track subprocessor changes.
**Sources:** [Privacy policy](https://legal.mistral.ai/terms/privacy-policy) · [ZDR (help)](https://help.mistral.ai/en/articles/347612-can-i-activate-zero-data-retention-zdr) · [Where data is stored](https://help.mistral.ai/en/articles/347629-where-do-you-store-my-data-or-my-organization-s-data) · [Subprocessors (help)](https://help.mistral.ai/en/articles/455208-who-are-your-subprocessors-and-how-can-i-stay-updated-on-changes) · [Trust Center](https://trust.mistral.ai/) · [DPA](https://legal.mistral.ai/terms/data-processing-addendum)
### Anthropic (direct API)
**Default.** No contractual ZDR by default, but retention is already minimal: *"Conversation content (your prompts and Claude's outputs) is not retained by default."* Standard backend deletion happens **within 30 days**; safety-flagged data is kept longer (documented as up to **2 years** for flagged inputs/outputs and up to **7 years** for classifier scores). *"Retained data is never used for model training without your express permission."*
**ZDR.** Available **on approval** for the Claude Platform (API) and **Claude Code for Enterprise**. It applies to the **Messages API** and **Token Counting API**, and to Claude Code when used with Commercial organization API keys or via Claude Enterprise.
Two caveats. (1) **User Safety classifier results are retained even under ZDR**, to enforce the Usage Policy. (2) **Claude Fable 5** and **Claude Mythos 5** are designated *Covered Models* requiring **30-day data retention** — ZDR is **not available** for them, and requests from an org whose configuration does not meet this requirement return a `400 invalid_request_error`. HIPAA BAA is available for the **Claude API only** (Console/Workbench, Claude Code, Bedrock and Google Cloud are excluded).
A blanket "United States hosting" statement is **not asserted on these pages**; they describe a configurable **data residency / geographic routing** feature instead — confirm the routing for your account.
**Sources:** [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention) · [ZDR product scope](https://privacy.claude.com/en/articles/8956058-i-have-a-zero-data-retention-agreement-with-anthropic-what-products-does-it-apply-to) · [How long data is stored](https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data)
### AWS Bedrock
**Default.** Bedrock uses a **zero data retention** security model: *"by default, Amazon Bedrock does not store model inputs or outputs"*, alongside a **zero operator access** model (*"no operators of the service can access model input or output"*).
**Modes.** The `data_retention_mode` setting has **four values**, not two: `default`, `none`, `provider_data_share`, and `inherit` (the default for new accounts/projects). `none` is **strict ZDR** (nothing written to durable storage, nothing shared); `provider_data_share` **retains and shares** inference data with the model provider; the `default` mode may retain data for safety/abuse purposes.
**Locking.** Configurable at **account or project level via API/CLI** (no console UI at launch). Org-wide enforcement is possible via an **SCP** using the condition key **`bedrock-mantle:DataRetentionMode`**. Each Region has **one Model Deployment Account per model provider**; for AWS-sold models the provider has **no access** to data.
**Claude Fable 5** and **Claude Mythos 5** require `provider_data_share` (`allowed_modes: ["provider_data_share"]`) — under `none` or `default` they are **unavailable**. When shared, prompts/completions are retained up to **30 days** by Anthropic for trust & safety; eligible customers may request full per-model ZDR via their AWS account team. **Cross-region inference** can move processing/storage to the destination region. EU region availability is **not stated** on the cited pages — **confirm your region**.
**Who sells the model matters.** On Bedrock, models such as Amazon Nova, AI21, and Qwen are **sold by AWS** — the model provider has no access to the deployment accounts. **Anthropic (Claude) models are *sold by Anthropic***, governed by Anthropic's *Commercial Terms of Service* (version 18 August 2025) and its **Data Processing Addendum**, with the EEA/UK/Switzerland contracting entity being Anthropic Ireland, Limited. Those terms state Anthropic **does not train on Customer Content**, but when `provider_data_share` is used (required for Claude Fable 5 / Mythos 5) inputs and outputs **are shared with Anthropic** and retained up to 30 days. So the "provider has no data access" guarantee applies to **AWS-sold** models, not to Anthropic-sold ones.
**Sources:** [Data retention](https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html) · [Abuse detection](https://docs.aws.amazon.com/bedrock/latest/userguide/abuse-detection.html) · [Data protection](https://docs.aws.amazon.com/bedrock/latest/userguide/data-protection.html) · [Serverless third-party model EULAs](https://aws.amazon.com/legal/bedrock/third-party-models/) · [Security & compliance](https://aws.amazon.com/bedrock/security-compliance/)
### Google Vertex AI / Gemini Enterprise Agent Platform
**Default.** No ZDR. Published Gemini models cache data **in-memory only** (not at rest), **isolated per project**, with a **24-hour TTL**, respecting the project's data-residency selection. Prompts may be **logged for abuse monitoring** (retained **up to 90 days** in the customer-selected region/multi-region). Logged data is **not used to train or fine-tune** models.
**ZDR.** Requires **two actions**: (1) **disable the data cache** at project level (PATCH the `cacheConfig` endpoint with `disableCache: true`) and (2) **opt out of abuse logging** (request form, or switch to invoiced billing).
*"Zero data retention may not be possible when using some Advanced AI features."* In the current docs this ties to an **Advanced AI Safety Addendum** for certain higher-risk/dual-use scenarios — clarify with your Google account team. Residency is configurable per project (region pinning).
**Sources:** [Zero data retention](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention) · [Abuse monitoring (Vertex AI)](https://docs.cloud.google.com/vertex-ai/generative-ai/docs/learn/abuse-monitoring)
### Azure AI Foundry / Azure OpenAI
**Default.** No ZDR. A **sample** of prompts and completions may be selected for **human review** in a logically separated, per-resource abuse-monitoring store. Reviewers are *"authorized Microsoft employees"* accessing data via point-wise request-ID queries, **Secure Access Workstations (SAWs)** and **Just-In-Time (JIT)** approval. Inputs/outputs are *"NOT used to train any generative AI foundation models without your permission or instruction."*
**ZDR.** Obtained via the **Modified abuse monitoring** program (**Limited Access**) — no self-service toggle; managed customers apply via a form and approval. Once approved, the **`ContentLogging`** capability shows as `false` on the resource (visible in the portal JSON, or via `az cognitiveservices account show -n -g `).
A specific **"30 days"** retention figure is **not present on the current Azure pages** (26 June 2026); it appeared in older revisions — confirm the current period. The pages describe eligibility as *"managed customers"* meeting *"Limited Access"* criteria — the **EA / MCA** qualifier is a reasonable inference, **not** stated verbatim. **Residency:** prompts/responses are processed in the customer-specified geography *unless* a **Global** or **DataZone** deployment is used; data at rest stays in the customer-designated geography.
**Third-party models.** For **"Models sold by Azure"** (which includes Azure OpenAI models), the page states data **stays in Microsoft's Azure environment** and these models do not interact with the model providers' services. Partner / community models offered as **Models-as-a-Service** are governed by **separate terms** — verify residency and retention **per model** there; do not assume the "sold by Azure" guarantees apply.
**Sources:** [Data, privacy & security (Foundry)](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy) · [Abuse monitoring](https://learn.microsoft.com/en-us/azure/foundry/openai/concepts/abuse-monitoring)
## Cross-cutting pitfalls
As soon as a feature stores data to function (memory, agents, persistent conversations, Files/batch APIs, fine-tuning), ZDR does not apply. This holds across all providers.
Frontier / "Covered" models can force retention regardless of your setting. Example: Claude Fable 5 and Claude Mythos 5 require 30-day retention — each platform sets its own rule.
No retention on the provider side does not remove the need to trace what was sent, by whom, and what came back. That responsibility sits with the customer or the orchestration layer.
The same provider can host in the EU, the US or elsewhere depending on region, deployment type and subprocessors. Fix it explicitly per requirement.
Several providers present an opt-out of training as if it were ZDR. For strong requirements, require a signed ZDR arrangement and a SOC 2 Type II or ISO 27001 report auditing the retention policy.
Program names, mode names and retention periods change. Confirm against the official page and your signed terms at the time of deployment.
## Reference sources
* OVHcloud AI Endpoints — [ovhcloud.com — AI Endpoints](https://www.ovhcloud.com/en/public-cloud/ai-endpoints/)
* Mistral privacy policy — [legal.mistral.ai — privacy policy](https://legal.mistral.ai/terms/privacy-policy) · [Trust Center](https://trust.mistral.ai/)
* Anthropic API & data retention — [platform.claude.com — API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention)
* AWS Bedrock data retention — [docs.aws.amazon.com — Bedrock data retention](https://docs.aws.amazon.com/bedrock/latest/userguide/data-retention.html)
* Google Zero Data Retention — [docs.cloud.google.com — Zero Data Retention](https://docs.cloud.google.com/gemini-enterprise-agent-platform/resources/zero-data-retention)
* Azure Foundry data privacy — [learn.microsoft.com — Foundry data privacy](https://learn.microsoft.com/en-us/azure/foundry/responsible-ai/openai/data-privacy)
Last verified against official sources on **26 June 2026**. Provider terms change frequently — re-check the linked pages and your contract before relying on any specific figure.