Repository Public
1# Data controls in the OpenAI platform23> For the complete documentation index, see [llms.txt](/llms.txt). Markdown versions of documentation pages are available by appending `.md` to the page URL.45Understand how OpenAI uses your data, and how you can control it.67Your data is your data. As of March 1, 2023, data sent to the OpenAI API is not used to train or improve OpenAI models (unless you explicitly opt in to share data with us).89## Types of data stored with the OpenAI API1011When using the OpenAI API, data may be stored as:1213- **Abuse monitoring logs:** Logs generated from your use of the platform, necessary for OpenAI to enforce our [Usage Policies](https://openai.com/policies/usage-policies) and agreements and mitigate harmful uses of AI.14- **Application state:** Data persisted from some API features in order to fulfill the task or request.1516## Data retention controls for abuse monitoring1718Abuse monitoring logs may contain certain customer content, such as prompts and responses, as well as metadata derived from that customer content, such as classifier outputs. By default, abuse monitoring logs are generated for all API feature usage and retained for up to 30 days, unless longer retention is required by law, or is reasonably necessary to protect our services or any third party from harm.1920Eligible customers may have their customer content excluded from these abuse monitoring logs, subject to the limitations below, by getting approved for the [Zero Data Retention](#zero-data-retention) or [Modified Abuse Monitoring](#modified-abuse-monitoring) controls. Currently, these controls are subject to prior approval by OpenAI and acceptance of additional requirements. Approved customers may select between Modified Abuse Monitoring or Zero Data Retention for their API Organization or project.2122Customers who enable Modified Abuse Monitoring or Zero Data Retention are responsible for ensuring their users abide by OpenAI's policies for safe and responsible use of AI and complying with any moderation and reporting requirements under applicable law.2324Get in touch with our [sales team](https://openai.com/contact-sales) to learn more about these offerings and inquire about eligibility.2526### Modified Abuse Monitoring2728Modified Abuse Monitoring excludes customer content (other than image and file inputs in rare cases, as described [below](https://developers.openai.com/api/docs/guides/your-data#image-and-file-inputs)) from abuse monitoring logs across all API endpoints, while still allowing the customer to take advantage of the full capabilities of the OpenAI platform.2930### Zero Data Retention3132Zero Data Retention excludes customer content from abuse monitoring logs in the same way as Modified Abuse Monitoring.3334Additionally, Zero Data Retention changes some endpoint behavior: the `store` parameter for `/v1/responses` and `v1/chat/completions` will always be treated as `false`, even if the request attempts to set the value to `true`.3536Besides those specific behavior changes, the endpoints and capabilities listed as No for Zero Data Retention Eligible in the table below may still store application state, even if Zero Data Retention is enabled.3738### Eyes Off3940For customers approved for Zero Data Retention or Modified Abuse Monitoring, we reserve the right to make models ineligible for Zero Data Retention or Modified Abuse Monitoring for specific customers, as notified in advance to the impacted customers in writing. In this instance, customer content will be retained in abuse monitoring logs, but such content will be excluded from human review unless required by applicable law. For customers who have executed an OpenAI Business Associate and Healthcare Addendum, once your org ID is provisioned with Eyes Off, BAA-eligible endpoints can be used for processing PHI, even if data is retained.4142### Safety Retention4344For customers approved for Zero Data Retention or Modified Abuse Monitoring, we reserve the right to make models ineligible for Zero Data Retention or Modified Abuse Monitoring for specific customers if reasonably necessary to investigate or prevent severe risk activity, as notified in advance to the impacted customers in writing. In this instance, we may retain and human review customer content when using these models that our classifiers detect as potentially violating our [Usage Policies](https://openai.com/policies/usage-policies/) or your agreement. Otherwise retention will not be affected. For customers who have executed an OpenAI Business Associate and Healthcare Addendum, once your org ID is provisioned with Safety Retention, BAA-eligible endpoints can be used for processing PHI, even if data is retained.4546### Configuring data retention controls4748Once your organization has been approved for data retention controls, you'll see a **Data Retention** tab within [Settings → Organization → Data controls](https://platform.openai.com/settings/organization/data-controls/data-retention). From that tab, you can configure data retention controls at both the organization and project level.4950- **Organization-level controls:** Choose between Zero Data Retention or Modified Abuse Monitoring for your entire organization.51- **Project-level controls:** For each project, select `default` to inherit the organization-level setting, explicitly pick Zero Data Retention or Modified Abuse Monitoring, or select **None** to disable these controls for that project.5253### Storage requirements and retention controls per endpoint5455The table below indicates when application state is stored for each endpoint. Zero Data Retention eligible endpoints do not retain any customer content for application state, subject to the limitations below. Zero Data Retention ineligible endpoints or capabilities may retain application state when used, even if you have Zero Data Retention enabled.5657| Endpoint | Data used for training | Abuse monitoring retention | Application state retention | Zero Data Retention eligible | Eyes Off and Safety Retention eligible |58| -------------------------- | :--------------------: | :------------------------: | :----------------------------: | :----------------------------: | :------------------------------------: |59| `/v1/chat/completions` | No | 30 days | None, see below for exceptions | Yes, see below for limitations | Yes, see below for limitations |60| `/v1/responses` | No | 30 days | None, see below for exceptions | Yes, see below for limitations | Yes, see below for limitations |61| `/v1/conversations` | No | Until deleted | Until deleted | No | No |62| `/v1/conversations/items` | No | Until deleted | Until deleted | No | No |63| `/v1/chatkit/threads` | No | Until deleted | Until deleted | No | No |64| `/v1/agents` | No | 30 days | Until deleted | No | No |65| `/v1/assistants` | No | 30 days | Until deleted | No | No |66| `/v1/threads` | No | 30 days | Until deleted | No | No |67| `/v1/threads/messages` | No | 30 days | Until deleted | No | No |68| `/v1/threads/runs` | No | 30 days | Until deleted | No | No |69| `/v1/threads/runs/steps` | No | 30 days | Until deleted | No | No |70| `/v1/vector_stores` | No | 30 days | Until deleted | No | No |71| `/v1/images/generations` | No | 30 days | None | Yes, see below for limitations | No |72| `/v1/images/edits` | No | 30 days | None | Yes, see below for limitations | No |73| `/v1/embeddings` | No | 30 days | None | Yes | No |74| `/v1/audio/transcriptions` | No | None | None | Yes | No |75| `/v1/audio/translations` | No | None | None | Yes | No |76| `/v1/audio/speech` | No | 30 days | None | Yes | No |77| `/v1/files` | No | 30 days | Until deleted\* | No | No |78| `/v1/fine_tuning/jobs` | No | 30 days | Until deleted | No | No |79| `/v1/evals` | No | 30 days | Until deleted | No | No |80| `/v1/batches` | No | 30 days | Until deleted | No | No |81| `/v1/moderations` | No | None | None | Yes | No |82| `/v1/completions` | No | 30 days | None | Yes | No |83| `/v1/live/sessions` | No | 30 days | None, or 30 days if stored | Yes, with limitations below | No |84| `/v1/realtime` | No | 30 days | None | Yes | No |85| `/v1/videos` | No | 30 days | None | No | No |8687#### `/v1/chat/completions`8889- Audio outputs application state is stored for 1 hour to enable [multi-turn conversations](https://developers.openai.com/api/docs/guides/audio).90- When Zero Data Retention is enabled for an organization, the `store` parameter will always be treated as `false`, even if the request attempts to set the value to `true`.91- See [image and file inputs](#image-and-file-inputs).92- Prompt caching may store encrypted key/value tensors in GPU-local storage as application state. This data is stored on the local GPU machines and is not retained after the 24-hour expiration. For `gpt-5.5` and `gpt-5.5-pro`, setting `prompt_cache_retention` to `in_memory` returns an error. For GPT-5.6 models and later model families, `prompt_cache_options.ttl` controls the minimum cache lifetime, not this maximum application-state retention period. To learn more, see the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).9394#### `/v1/responses`9596- Except as noted below, the Responses API has a 30 day Application State retention period by default, or when the `store` parameter is set to `true`. In those cases, response data will be stored for at least 30 days.97- When Zero Data Retention is enabled for an organization, the `store` parameter will always be treated as `false`, even if the request attempts to set the value to `true`.98- Background mode stores response data to disk for roughly 10 minutes to enable polling. For projects using [Modified Abuse Monitoring](#modified-abuse-monitoring), including enhanced Modified Abuse Monitoring, foreground requests follow standard retention when `store` is omitted or set to `true`. Background responses follow the standard retention period only when the request explicitly sets `store=true`. If `store` is omitted or set to `false` for a background request, the response is deleted after the temporary polling period.99- Audio outputs application state is stored for 1 hour to enable [multi-turn conversations](https://developers.openai.com/api/docs/guides/audio).100- See [image and file inputs](#image-and-file-inputs).101- MCP servers (used with the [remote MCP server tool](https://developers.openai.com/api/docs/guides/tools-connectors-mcp)) are third-party services, and data sent to an MCP server is subject to their data retention policies.102- Hosted containers used by [Hosted Shell](https://developers.openai.com/api/docs/guides/tools-shell#hosted-shell-quickstart) and [Code Interpreter](https://developers.openai.com/api/docs/guides/tools-code-interpreter) may write temporary application state to the container filesystem (backed by ephemeral block storage) while the container is active. Container data is deleted when the container expires or is explicitly deleted.103- Prompt caching may store encrypted key/value tensors in GPU-local storage as application state. This data is stored on the local GPU machines and is not retained after the 24-hour expiration. For `gpt-5.5` and `gpt-5.5-pro`, setting `prompt_cache_retention` to `in_memory` returns an error. For GPT-5.6 models and later model families, `prompt_cache_options.ttl` controls the minimum cache lifetime, not this maximum application-state retention period. To learn more, see the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).104- When Zero Data Retention is not enabled for an organization, all queries use extended prompt caching for all supported models.105- For server-side compaction, no data is retained when `store="false"`.106- We support [Skills](https://developers.openai.com/api/docs/guides/tools-skills) in two form factors, both local execution and hosted container-based execution. Hosted skills follow the same container lifecycle as hosted shell: mounted skills and container files remain available while the container is active and are discarded when the container expires or is deleted.107- Data transmitted to third-party services over network connections is subject to their data retention policies.108109#### `/v1/assistants`, `/v1/threads`, and `/v1/vector_stores`110111- Objects related to the Assistants API are deleted from our servers 30 days after you delete them via the API or the dashboard. Objects that are not deleted via the API or dashboard are retained indefinitely.112113#### `/v1/images`114115- Image generation is Zero Data Retention compatible when using `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2`, `gpt-image-1.5`, `gpt-image-1`, and `gpt-image-1-mini`.116117#### `/v1/files`118119- Files can be manually deleted via the API or the dashboard, or can be automatically deleted by setting the `expires_after` parameter. See [here](https://developers.openai.com/api/reference/resources/files/methods/create#files_create-expires_after) for more information.120121#### `/v1/videos`122123- The `v1/videos` API includes a workflow that saves data to disk while processing and retains it for 48 hours to allow the caller to download the produced video and then for 30 days for abuse monitoring. `v1/videos` is currently blocked for MAM or ZDR requests. If your organization has data retention controls enabled, configure a project with its retention setting set to **None** as described in [Configuring data retention controls](#configuring-data-retention-controls) to use `/v1/videos` with that project.124125#### Image and file inputs126127Images and files may be uploaded as inputs to `/v1/responses` (including when using the Computer Use tool), `/v1/chat/completions`, and `/v1/images`. Image and file inputs are scanned for CSAM content upon submission. If the classifier detects potential CSAM content, the image will be retained for manual review, even if Zero Data Retention, Modified Abuse Monitoring, or Eyes Off is enabled.128129#### Web Search130131Web Search with live internet access is not HIPAA eligible and is not covered by a BAA. Web Search in offline/cache-only mode (`external_web_access: false`) is eligible to be covered by a BAA when used with an API key from a ZDR-enabled project within a ZDR organization. This HIPAA/BAA guidance applies only to the Responses API `web_search` tool. Note: Preview variants (`web_search_preview`) ignore this parameter and behave as if `external_web_access` is `true`. We recommend using `web_search`.132133## Data residency controls134135Data residency controls are a project configuration option that allow you to configure the location of infrastructure OpenAI uses to provide services.136137Contact our [sales team](https://openai.com/contact-sales) to see if you're eligible for using data residency controls. Data residency endpoints are charged a [10% uplift](https://developers.openai.com/api/docs/pricing) for models released on or after March 5, 2026, that are eligible for data residency.138139### How does data residency work?140141When data residency is enabled on your account, you can set a region for new projects you create in your account from the available regions listed below. If you use the supported endpoints, models, and snapshots listed below, your customer content (as defined in your services agreement) for that project will be stored at rest in the selected region to the extent the endpoint requires data persistence to function (such as /v1/batches).142143If you select a region that supports regional processing, as specifically identified below, the services will perform inference for your Customer Content in the selected region as well.144145Data residency does not apply to system data, which may be processed and stored outside the selected region. System data means account data, metadata, and usage data that do not contain Customer Content, which are collected by the services and used to manage and operate the services, such as account information or profiles of end users that directly access the services (for example, your personnel), analytics, usage statistics, billing information, support requests, and structured output schema.146147### Sub-processors and regional request processing148149OpenAI uses [sub-processors](https://openai.com/policies/sub-processor-list/) to provide its services. For requests sent to `us.api.openai.com` or `eu.api.openai.com`, OpenAI uses [Cloudflare Regional Services](https://developers.cloudflare.com/data-localization/regional-services/) so that TLS termination and HTTPS decryption occur within the selected processing region.150151### Limitations152153Data residency does not apply to: (1) any transmission or storage of Customer Content outside of the selected region caused by the location of an End User or Customer’s infrastructure when accessing the services; (2) products, services, or content offered by parties other than OpenAI through the Services; or (3) any data other than Customer Content, such as system data.154155If your selected Region does not support regional processing, as identified below, OpenAI may also process and temporarily store Customer Content outside of the Region to deliver the services.156157### Additional requirements for non-US regions158159To use data residency with any region other than the United States, you must be approved for abuse monitoring controls, and execute a Modified Retention amendment.160161Selecting the United Arab Emirates region requires additional approval. Contact [sales](https://openai.com/contact-sales) for assistance.162163### How to use data residency164165Data residency is configured per-project within your API Organization.166167To configure data residency for regional storage, select the appropriate region from the dropdown when creating a new project.168169For requests to projects with data residency configured, add the domain prefix as defined in the table below to each request.170171#### Select a processing region per request172173As an alternative to creating a region-specific project, you can select regional processing for an individual request by using the prefixed domain with an API key from a project having Global geography.174175Existing eligibility and data retention control requirements still apply. The selected endpoint and model must also support regional processing, as shown in the table below.176177The following example reuses one client and an API key from a Global project for global, US, and EU requests:178179```python180from openai import OpenAI181182client = OpenAI()183184# No processing constraint.185response = client.responses.create(186 model="gpt-5.6-terra",187 input="Reply with OK.",188)189print(response.output_text)190191# US processing and storage.192response = client.with_options(193 base_url="https://us.api.openai.com/v1",194).responses.create(195 model="gpt-5.6-terra",196 input="Reply with OK.",197)198print(response.output_text)199200# EU processing and storage.201response = client.with_options(202 base_url="https://eu.api.openai.com/v1",203).responses.create(204 model="gpt-5.6-terra",205 input="Reply with OK.",206)207print(response.output_text)208```209210```ruby211require "openai"212213client = OpenAI::Client.new214215response = client.responses.create(216 model: "gpt-5.6-terra",217 input: "Reply with OK."218)219puts(response.output_text)220221response = client.with_options(data_residency: :us).responses.create(222 model: "gpt-5.6-terra",223 input: "Reply with OK."224)225puts(response.output_text)226227response = client.with_options(data_residency: :eu).responses.create(228 model: "gpt-5.6-terra",229 input: "Reply with OK."230)231puts(response.output_text)232```233234235### Which models and features are eligible for data residency?236237The following models and API services are eligible for data residency today for the regions specified below.238239Use **Support by region** to compare regional capabilities and expand the services available in each region. Use **API Endpoint, tool and model support** for complete model lists and a detailed service view. Support for regional storage does not imply support for regional processing.240241#### Support by region242243The complete, unfiltered regional support table follows. Model snapshots for each service are listed in **API Endpoint, tool and model support**. When regional processing supports only a subset of snapshots, that subset is included in the processing-services cell.244245| Region | Domain prefix | Regional storage | Regional processing | MAM or ZDR required | Supported modes | Storage services | Processing services |246| -------------------------- | ------------------- | :--------------: | :-----------------: | :-----------------: | --------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |247| United States | `us.api.openai.com` | Yes | Yes | No | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/evals`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/live/sessions`<br />`/v1/realtime`<br />`/v1/realtime/transcription_sessions`<br />`/v1/realtime/translations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/evals`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/live/sessions`<br />`/v1/realtime`<br />`/v1/realtime/transcription_sessions`<br />`/v1/realtime/translations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`Code Interpreter tool`<br />`File Search`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` |248| Europe (EEA + Switzerland) | `eu.api.openai.com` | Yes | Yes | Yes\*\* | Text, Audio, Voice, Image\* | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/evals`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/live/sessions`<br />`/v1/realtime`<br />`/v1/realtime/transcription_sessions`<br />`/v1/realtime/translations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/evals`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/live/sessions`<br />`/v1/realtime`<br />`/v1/realtime/transcription_sessions`<br />`/v1/realtime/translations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`Code Interpreter tool`<br />`File Search`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` |249| Australia\* | `au.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |250| Canada\* | `ca.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |251| Japan\* | `jp.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |252| India\* | `in.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |253| Singapore\* | `sg.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |254| South Korea\* | `kr.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |255| United Kingdom\* | `gb.api.openai.com` | Yes | No | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | None |256| United Arab Emirates\* | `ae.api.openai.com` | Yes | Yes | Yes | Text, Audio, Voice, Image | `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech`<br />`/v1/batches`<br />`/v1/chat/completions`<br />`/v1/embeddings`<br />`/v1/files`<br />`/v1/fine_tuning/jobs`<br />`/v1/images/edits`<br />`/v1/images/generations`<br />`/v1/moderations`<br />`/v1/responses`<br />`/v1/responses File Search`<br />`/v1/responses Web Search`<br />`/v1/vector_stores`<br />`Code Interpreter tool`<br />`File Search`<br />`File Uploads`<br />`Remote MCP server tool`<br />`Scale Tier`<br />`Structured Outputs (excluding schema)`<br />`Supported input modalities` | `/v1/chat/completions` (`gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11`)<br />`/v1/embeddings` (`text-embedding-3-large`)<br />`/v1/responses` (`gpt-5.5-pro-2026-04-23`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11`) |257258\* Image support in these regions requires approval for enhanced Zero Data Retention or enhanced Modified Abuse Monitoring.259260\*\* Requires Zero Data Retention, Modified Abuse Monitoring, Eyes Off, or Safety Retention.261262#### API Endpoint, tool and model support263264| Endpoint or feature | Service | Storage regions | Processing regions | Supported models and snapshots | Regional processing snapshot exceptions | Notes |265| -------------------------------------------------------------------- | ---------------- | ----------------------------------------- | --------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------- |266| `/v1/audio/transcriptions, /v1/audio/translations, /v1/audio/speech` | Audio | All listed regions | United States, Europe (EEA + Switzerland) | `tts-1`, `whisper-1`, `gpt-4o-tts`, `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, `gpt-transcribe` | None | — |267| `/v1/batches` | Batches | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-6-astra`, `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | None | — |268| `/v1/chat/completions` | Chat Completions | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-6-astra`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-2025-08-07`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-mini-2025-01-31`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11` | — |269| `/v1/embeddings` | Embeddings | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `text-embedding-3-small`, `text-embedding-3-large`, `text-embedding-ada-002` | United Arab Emirates: `text-embedding-3-large` | — |270| `/v1/evals` | Evals | United States, Europe (EEA + Switzerland) | United States, Europe (EEA + Switzerland) | Service-level support | None | — |271| `/v1/files` | Files | All listed regions | None | Service-level support | None | — |272| `/v1/fine_tuning/jobs` | Fine-tuning | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14` | None | — |273| `/v1/images/edits` | Images | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2`, `gpt-image-1`, `gpt-image-1.5`, `gpt-image-1-mini` | None | — |274| `/v1/images/generations` | Images | All listed regions | United States, Europe (EEA + Switzerland) | `gpt-image-2.5-sunburst`, `gpt-image-2.5-sunburst-2026-09-08`, `gpt-image-2.5-flare`, `gpt-image-2.5-flare-2026-09-08`, `gpt-image-2`, `gpt-image-1`, `gpt-image-1.5`, `gpt-image-1-mini` | None | — |275| `/v1/moderations` | Moderation | All listed regions | United States, Europe (EEA + Switzerland) | `omni-moderation-latest` | None | — |276| `/v1/live/sessions` | GPT-Live | United States, Europe (EEA + Switzerland) | United States, Europe (EEA + Switzerland) | `gpt-live-1` | None | — |277| `/v1/realtime` | Realtime | United States, Europe (EEA + Switzerland) | United States, Europe (EEA + Switzerland) | `gpt-realtime`, `gpt-realtime-1.5`, `gpt-realtime-mini`, `gpt-realtime-2`, `gpt-realtime-2.1`, `gpt-realtime-2.1-mini` | None | — |278| `/v1/realtime/transcription_sessions` | Realtime | United States, Europe (EEA + Switzerland) | United States, Europe (EEA + Switzerland) | `gpt-realtime-whisper`, `gpt-live-transcribe`, `gpt-transcribe` | None | — |279| `/v1/realtime/translations` | Realtime | United States, Europe (EEA + Switzerland) | United States, Europe (EEA + Switzerland) | `gpt-realtime-translate` | None | — |280| `/v1/responses` | Responses | All listed regions | United States, Europe (EEA + Switzerland), United Arab Emirates | `gpt-6-astra`, `gpt-5.5-pro-2026-04-23`, `gpt-5.4-pro-2026-03-05`, `gpt-5.2-pro-2025-12-11`, `gpt-5-pro-2025-10-06`, `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.4-2026-03-05`, `gpt-5-2025-08-07`, `gpt-5.4-mini-2026-03-17`, `gpt-5.4-nano-2026-03-17`, `gpt-5.2-2025-12-11`, `gpt-5.1-2025-11-13`, `gpt-5-mini-2025-08-07`, `gpt-5-nano-2025-08-07`, `gpt-4.1-2025-04-14`, `gpt-4.1-mini-2025-04-14`, `gpt-4.1-nano-2025-04-14`, `o3-2025-04-16`, `o4-mini-2025-04-16`, `o1-pro`, `o1-pro-2025-03-19`, `o3-mini-2025-01-31`, `o1-2024-12-17`, `gpt-4o-2024-11-20`, `gpt-4o-2024-08-06`, `gpt-4o-mini-2024-07-18`, `gpt-4-turbo-2024-04-09`, `gpt-4-0613`, `gpt-3.5-turbo-0125` | United Arab Emirates: `gpt-5.5-pro-2026-04-23`, `gpt-5.6-luna`, `gpt-5.5-2026-04-23`, `gpt-5.2-2025-12-11` | — |281| `/v1/responses File Search` | Responses | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |282| `/v1/responses Web Search` | Responses | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |283| `/v1/vector_stores` | Vector stores | All listed regions | None | Service-level support | None | — |284| `Code Interpreter tool` | Tools | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |285| `File Search` | Tools | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |286| `File Uploads` | Files | All listed regions | None | Service-level support | None | Supported when used with base64 file uploads. |287| `Remote MCP server tool` | Tools | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | MCP servers are third-party services. Data sent to an MCP server is subject to its data residency policies. |288| `Scale Tier` | Other | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |289| `Structured Outputs (excluding schema)` | Other | All listed regions | United States, Europe (EEA + Switzerland) | Service-level support | None | — |290| `Supported input modalities` | Other | All listed regions | United States, Europe (EEA + Switzerland) | `Text`, `Image`, `Audio/Voice` | None | — |291292293294### Endpoint limitations295296#### /v1/chat/completions297298- Cannot set store=true in non-US regions.299- [Extended prompt caching](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention) in regions that do not support Regional processing may require that OpenAI process and temporarily store Customer Content outside of the Region to deliver the services.300301#### /v1/responses302303- Cannot set background=True in EU region.304- [Extended prompt caching](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention) in regions that do not support Regional processing may require that OpenAI process and temporarily store Customer Content outside of the Region to deliver the services.305306#### /v1/live/sessions307308GPT-Live sessions are eligible for Zero Data Retention. With Zero Data Retention enabled, `store` is treated as `false`, even if a request sets it to `true`.309310Session storage is disabled by default. For projects with session storage enabled, `store: true` retains the completed session recording for 30 days so that it can be downloaded or used to start a forked session. Stored sessions and their index expire after 30 days. Recording downloads and forking require a data policy that permits persistence and are not available with Zero Data Retention.311312Setting `store: false` on a fork prevents storage of the new session; it does not delete the source recording or remove the authorization required to read it. The API does not provide a public stored-session deletion endpoint.313314GPT-Live supports data residency in the United States and Europe. Delegated backend models and tools have their own data controls; check the applicable endpoint and feature entries on this page.315316#### /v1/realtime317318Tracing is not currently EU data residency compliant for `/v1/realtime`.319320## Enterprise Key Management (EKM)321322Enterprise Key Management (EKM) allows you to encrypt your customer content at OpenAI using keys managed by your own external Key Management System (KMS).323324Once configured, EKM applies to any [application state](#types-of-data-stored-with-the-openai-api) created during your use of the platform. See the [EKM help center article](https://help.openai.com/en/articles/20000943-openai-enterprise-key-management-ekm-overview) for more information about how EKM works, and how to integrate with your KMS provider.325326### EKM limitations327328OpenAI supports Bring Your Own Key (BYOK) encryption with external accounts in AWS KMS, Google Cloud (GCP), and Azure Key Vault. If your organization leverages a different key management service, those keys need to be synced to one of the supported cloud KMS providers for use with OpenAI.329330EKM does not support the following products. An attempt to use these endpoints in a project with EKM enabled will return an error.331332- Assistants (/v1/assistants)333- Vision fine tuning