Documentation 2026-10-23 23:58 UTC to 2026-10-24 23:02 UTC

1115 1115 

1116 1116 

1117Yes. Cached input tokens still count toward tokens-per-minute limits. Prompt caching does not change how [rate limits](https://developers.openai.com/api/docs/guides/rate-limits) are calculated.1117Yes. Cached input tokens still count toward tokens-per-minute limits. Prompt caching does not change how [rate limits](https://developers.openai.com/api/docs/guides/rate-limits) are calculated.

1118 

1119 

1120 

1121 

1122 

1123## Data retention

1124 

1125All prompt caching features are compatible with [Zero Data Retention (ZDR)](https://developers.openai.com/api/docs/guides/your-data#zero-data-retention).

1126 

1127The prompt cache stores key-value (KV) tensors rather than the original prompt text. These tensors may be stored as encrypted application state in GPU-local storage, with a maximum retention period of 24 hours. See [Cache lifetime](#cache-lifetime) for model-specific cache lifetimes and refresh behavior.

1128 

1129Caches are not shared across organizations and cannot be reused across [regional processing boundaries](https://developers.openai.com/api/docs/guides/your-data#data-residency-controls). For details about data handling and ZDR eligibility across API features, see [Your data](https://developers.openai.com/api/docs/guides/your-data).

115- 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.115- 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.

116- 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.116- 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.

117- 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).117- 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).

118- When Zero Data Retention is not enabled for an organization, all queries use extended prompt caching for all supported models.

119- For server-side compaction, no data is retained when `store="false"`.118- For server-side compaction, no data is retained when `store="false"`.

120- 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.119- 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.

121- Data transmitted to third-party services over network connections is subject to their data retention policies.120- Data transmitted to third-party services over network connections is subject to their data retention policies.