Documentation 2026-05-22 06:33 UTC to 2026-05-24 06:25 UTC

73 73 

74### Implement safety identifiers74### Implement safety identifiers

75 75 

76Sending safety identifiers in your requests can be a useful tool to help OpenAI monitor and detect abuse. This allows OpenAI to provide your team with more actionable feedback in the event that we detect any policy violations in your application.76Sending safety identifiers in your requests can help OpenAI monitor and detect abuse. This allows OpenAI to provide your team with more actionable feedback in the event that we detect any policy violations in your application.

77 

78Safety identifiers can also help your team respond to abuse faster. They create a stable way to trace activity back to an individual end user and reduce the chance that one user's misuse disrupts access for your broader organization.

77 79 

78A safety identifier should be a string that uniquely identifies each user. Hash the username or email address in order to avoid sending us any identifying information. If you offer a preview of your product to non-logged in users, you can send a session ID instead.80A safety identifier should be a string that uniquely identifies each user. Hash the username or email address in order to avoid sending us any identifying information. If you offer a preview of your product to non-logged in users, you can send a session ID instead.

79 81 

84- [Implement safety identifiers](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers) for products where individual users interact with a model. Safety identifiers are recommended but not required.84- [Implement safety identifiers](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers) for products where individual users interact with a model. Safety identifiers are recommended but not required.

85- If your use case depends on accessing a less restricted version of our services in order to engage in beneficial applications across the life sciences, read about our [special access program](https://help.openai.com/en/articles/11826767-life-science-research-special-access-program) to see if you meet criteria.85- If your use case depends on accessing a less restricted version of our services in order to engage in beneficial applications across the life sciences, read about our [special access program](https://help.openai.com/en/articles/11826767-life-science-research-special-access-program) to see if you meet criteria.

86 86 

87You likely don't need to provide a safety identifier if access to your product

88 is tightly controlled (for example, enterprise customers) or in cases where

89 users don't directly provide prompts, or are limited to use in narrow areas.

90 

91### Implementing safety identifiers for individual users87### Implementing safety identifiers for individual users

92 88 

93The `safety_identifier` parameter is available in both the [Responses API](https://developers.openai.com/api/docs/api-reference/responses/create) and older [Chat Completions API](https://developers.openai.com/api/docs/api-reference/chat/create). The Realtime API supports the same concept through the `OpenAI-Safety-Identifier` header. To use safety identifiers, provide a stable ID for your end user on each request. Hash user email or internal user IDs to avoid passing any personal information.89The `safety_identifier` parameter is available in both the [Responses API](https://developers.openai.com/api/docs/api-reference/responses/create) and older [Chat Completions API](https://developers.openai.com/api/docs/api-reference/chat/create). The Realtime API supports the same concept through the `OpenAI-Safety-Identifier` header. To use safety identifiers, provide a stable ID for your end user on each request. Hash user email or internal user IDs to avoid passing any personal information.