Early accessGnani Evon v3.5 is now available as an API to early access registrants.
Overview
Every request goes through safety filters, with or without streaming:
You do not need to turn anything on.
Blocked requests
A request is refused when a user message or a tool result tries to:- override, replace or cancel the assistant’s instructions (“ignore your previous instructions…”);
- get the assistant to reveal, list, repeat or summarise its own system prompt, instructions or hidden configuration;
- make the assistant drop its safety rules through role-play, “developer mode”, or similar tricks;
- disguise new instructions as system, developer or tool content.
What is not blocked: asking how prompt injection or jailbreaks work in general, asking for help writing your own prompts, quoting an example to discuss it, and ordinary requests, even unusual or rude ones.
Your
system message is not screened. It is yours, so it can contain any instructions you like.When your request is blocked
- Do not retry it unchanged. It is refused again.
- Tell your user plainly that the request could not be processed, and let them rephrase.
- Check tool results. If you pass web pages, emails or documents to the model as
toolmessages, text inside them that gives the model instructions can block the request. - Contact support with the
X-API-Request-IDof the request if you think it was blocked by mistake.
Personal data in replies
Personal identifiers in the model’s reply are replaced with a placeholder that names the type. This applies tocontent and to the thinking in reasoning, with or without streaming.
For example, a reply that would have been “Call the customer on 98450 12345” arrives as “Call the customer on [REDACTED_PHONE]”.
Names and postal addresses are not detected and are returned as written.
Personal data in your requests
Personal data that you send is not changed and not refused. The model receives your messages exactly as you sent them, so it can use the details to answer. Only the reply is masked.Withheld replies
Replies are also checked for unsafe content. If a reply is withheld,finish_reason is content_filter, and without streaming content is replaced with:
finish_reason and show your own message when it is content_filter.
Related errors
Related
Errors
Every error code, and how to retry safely.
Tool calling
Tool results are screened like user messages.
JSON output
Masking applies to values inside JSON replies.
Limits
Request size and the text that can be screened.