Update faq.mdx

Author: rakeshjosh2003

docs/cody/faq.mdx

@@ -137,6 +137,19 @@ cody chat --model '$name_of_the_model' -m 'Hi Cody!'
 
 For example, to use Claude 3.5 Sonnet, you'd pass the following command in your terminal, `cody chat --model 'claude-3.5-sonnet' -m 'Hi Cody!'
 
+### Is it possible to set separate token usage just for programmatic access( via API) and not to be used via IDE?
+
+Yes, it's possible to set separate token usage for API but only for completions (not chat). To achieve this you need to use the custom [model configuration](https://sourcegraph.com/docs/cody/enterprise/model-configuration#model-overrides). You need to configure the below settings
+
+		maxInputTokens: Specifies the maximum number of tokens for the contextual data in the prompt (e.g., question, relevant snippets
+		
+		maxOutputTokens: Specifies the maximum number of tokens allowed in the response
+
+Also, remove the below setting in the site configuration under the model configuration.
+
+  "capabilities": ["autocomplete", "chat"]
+
+
 ## OpenAI o1
 
 ### What are OpenAI o1 best practices?