chore(docs): add new filter costs by token type docs (#108)

Author: avivhalfon

api-reference/costs/property_costs.mdx

@@ -23,6 +23,26 @@ Query your LLM costs broken down by a specific association property. This helps
   List of environments to include in the calculation. Separated by comma.
 </ParamField>
 
+<ParamField query="selected_token_types" type="string">
+  <span style={{backgroundColor: '#10b981', color: 'white', padding: '2px 6px', borderRadius: '4px', fontSize: '12px', fontWeight: 'bold'}}>NEW</span> Filter costs by specific token types. Separate multiple types with commas.
+  
+  **Supported token types:**
+  - `input_tokens` or `prompt_tokens` (automatically normalized to `prompt_tokens`)
+  - `output_tokens` or `completion_tokens` (automatically normalized to `completion_tokens`)
+  - `cache_read_input_tokens`
+  - `cache_creation_input_tokens`
+  - Other token types as they appear in your data
+  
+  **Note:** `total_tokens` cannot be used as a filter.
+  
+  **Examples:**
+  - `selected_token_types=input_tokens,output_tokens`
+  - `selected_token_types=prompt_tokens,cache_read_input_tokens`
+  - `selected_token_types=completion_tokens`
+  
+  When this parameter is omitted, costs for all token types are included.
+</ParamField>
+
 ## Response
 
 <ResponseField name="property_name" type="string">