Skip to main content
Released November 2026. Search takes safety_mode to remove unsafe results before they reach your agent. Send moderate or strict, and results that a safety model judges unsafe at that level don’t come back. Use it when your agent shows results to people, for example in a consumer chat app.

Values

Removed results aren’t replaced. A query can return fewer than max_results results, or none. This request searches without an API key and removes results judged unsafe at the moderate level. It leaves mode out, so the search runs in pro, the default:
You get the usual search response, with up to 5 results. With an API key, send the same body to https://api.keenable.ai/v1/search with an X-API-Key header instead of X-Keenable-Title. The SDKs, the CLI and the MCP server’s search_web_pages tool don’t take safety_mode yet. Call the Search API over HTTP to use it.

Requests that fail

safety_mode set to moderate or strict works only on an ordinary pro or realtime search. Otherwise the request returns 400 with the code invalid_parameter and param set to safety_mode. The most common cases are below; the safety_mode field lists every one: safety_mode: "off" never fails. A value that differs from a supported one only in case or spaces, such as "Strict", gets a message that asks did you mean "strict"?. The failed request returns a body like this excerpt:
If you send safesearch or safe_search instead, the API returns unknown_parameter, and did_you_mean maps the name to safety_mode. See 400 Invalid request parameters.