diff --git a/api-reference/openapi.json b/api-reference/openapi.json
index 72e5e2cc..a18d236b 100644
--- a/api-reference/openapi.json
+++ b/api-reference/openapi.json
@@ -9683,7 +9683,7 @@
       },
       "TranslationMemoryThreshold": {
         "type": "integer",
-        "description": "The minimum matching percentage required for a translation memory segment to be applied (recommended to be 75% or higher).",
+        "description": "The minimum matching percentage required for a translation memory segment to be applied (recommended to be 75% or higher). A value below 50 is treated as 50.",
         "minimum": 0,
         "maximum": 100,
         "default": 75,
diff --git a/api-reference/openapi.yaml b/api-reference/openapi.yaml
index 8fe39562..03dede5e 100644
--- a/api-reference/openapi.yaml
+++ b/api-reference/openapi.yaml
@@ -7053,7 +7053,7 @@ components:
           example: 12
     TranslationMemoryThreshold:
       type: integer
-      description: The minimum matching percentage required for a translation memory segment to be applied (recommended to be 75% or higher).
+      description: The minimum matching percentage required for a translation memory segment to be applied (recommended to be 75% or higher). A value below 50 is treated as 50.
       minimum: 0
       maximum: 100
       default: 75
diff --git a/docs/customize/using-translation-memories.mdx b/docs/customize/using-translation-memories.mdx
index 7c10354f..44472d89 100644
--- a/docs/customize/using-translation-memories.mdx
+++ b/docs/customize/using-translation-memories.mdx
@@ -100,7 +100,7 @@ Notice that we didn't need to specify `source_lang` — language auto-detection
 
 ## Step 3: Adjust the matching threshold
 
-By default, a stored segment is applied when it matches at least **75%** of the source text. This means translation memory segments can match even when the source text isn't identical — which is useful for catching typos and minor variations.
+By default, a stored segment is applied when it matches at least **75%** of the source text. This means translation memory segments can match even when the source text isn't identical — which is useful for catching typos and minor variations. The lowest supported threshold is 50, and a lower value is treated as 50.
 
 Let's see this in action. Imagine we make a typo and send "Halloo Welt!" instead of "Hallo Welt!":