update

mrbullwinkle · mrbullwinkle · commit 0855211873ef · 2024-10-18T03:24:27.000-04:00
diff --git a/articles/ai-services/openai/how-to/prompt-caching.md b/articles/ai-services/openai/how-to/prompt-caching.md
@@ -36,7 +36,6 @@ For a request to take advantage of prompt caching the request must be:
 
 When a match is found between a prompt and the current content of the prompt cache it is referred to a cache hit. Cache hits will show up as [`cached_tokens`](/azure/ai-services/openai/reference-preview#cached_tokens) under [`prompt_token_details`](/azure/ai-services/openai/reference-preview#properties-for-prompt_tokens_details) in the chat completions response.
 
-
 ```json
 {
   "created": 1729227448,
@@ -57,7 +56,7 @@ When a match is found between a prompt and the current content of the prompt cac
       "cached_tokens": 1408
     }
   }
-  
+}
 ```
 
 After the first 1024 tokens cache hits will occur for every 128 additional identical tokens.

Original file line number	Diff line number	Diff line change
`@@ -36,7 +36,6 @@ For a request to take advantage of prompt caching the request must be:`
`36`	`36`
`37`	`37`	When a match is found between a prompt and the current content of the prompt cache it is referred to a cache hit. Cache hits will show up as [`cached_tokens`](/azure/ai-services/openai/reference-preview#cached_tokens) under [`prompt_token_details`](/azure/ai-services/openai/reference-preview#properties-for-prompt_tokens_details) in the chat completions response.
`38`	`38`
`39`		`-`
`40`	`39`	```json
`41`	`40`	`{`
`42`	`41`	`"created": 1729227448,`
`@@ -57,7 +56,7 @@ When a match is found between a prompt and the current content of the prompt cac`
`57`	`56`	`"cached_tokens": 1408`
`58`	`57`	`}`
`59`	`58`	`}`
`60`		`-`
	`59`	`+}`
`61`	`60`	```
`62`	`61`
`63`	`62`	`After the first 1024 tokens cache hits will occur for every 128 additional identical tokens.`