Merge 5c2c6d312c into 40be7fa1a8

litellm/cost_calculator.py

@@ -2051,6 +2051,7 @@ def completion_cost(
                         call_type=call_type,
                         model_info=_deployment_model_info(litellm_logging_obj, custom_pricing, router_model_id),
                         vertex_location=vertex_location,
+                        data_residency=data_residency,
                     )
                 elif call_type in _VIDEO_CALL_TYPES:
                     ### VIDEO GENERATION COST CALCULATION ###

litellm/litellm_core_utils/llm_cost_calc/utils.py

@@ -2287,6 +2287,7 @@ class CostCalculatorUtils:
         call_type: str | None = None,
         model_info: ModelInfo | None = None,
         vertex_location: str | None = None,
+        data_residency: str | None = None,
     ) -> float:
         """
         Route the image generation cost calculator based on the custom_llm_provider
@@ -2398,6 +2399,8 @@ class CostCalculatorUtils:
                     image_response=completion_response,
                     custom_llm_provider=custom_llm_provider,
                     model_info=pricing,
+                    data_residency=data_residency,
+                    optional_params=optional_params,
                 )
             # Fall through to default for DALL-E models
             return default_image_cost_calculator(

litellm/llms/openai/image_generation/cost_calculator.py

@@ -21,6 +21,8 @@ def cost_calculator(
     image_response: ImageResponse,
     custom_llm_provider: str | None = None,
     model_info: ModelInfo | None = None,
+    data_residency: str | None = None,
+    optional_params: dict | None = None,
 ) -> float:
     """Calculate cost for OpenAI gpt-image models (token-based pricing)."""
     provider: Final = custom_llm_provider or "openai"
@@ -38,7 +40,12 @@ def cost_calculator(
     # A chat Usage with an explicit output breakdown: cost via generic_cost_per_token.
     if isinstance(usage, Usage) and usage.completion_tokens_details is not None:
         prompt_cost, completion_cost = generic_cost_per_token(
-            model=model, usage=usage, custom_llm_provider=provider, model_info=price_table
+            model=model,
+            usage=usage,
+            custom_llm_provider=provider,
+            model_info=price_table,
+            data_residency=data_residency,
+            optional_params=optional_params,
         )
         return prompt_cost + completion_cost
 
@@ -48,7 +55,12 @@ def cost_calculator(
     # does not itemize output and splitting text/image when it does.
     if getattr(usage, "input_tokens", None) is not None:
         token_based_cost: Final = calculate_image_response_cost_from_usage(
-            model=model, image_response=image_response, custom_llm_provider=provider, model_info=price_table
+            model=model,
+            image_response=image_response,
+            custom_llm_provider=provider,
+            model_info=price_table,
+            data_residency=data_residency,
+            optional_params=optional_params,
         )
         if token_based_cost is not None:
             return token_based_cost
@@ -57,7 +69,12 @@ def cost_calculator(
     # cost via generic_cost_per_token (text rate) instead of returning 0.0.
     if isinstance(usage, Usage):
         prompt_cost, completion_cost = generic_cost_per_token(
-            model=model, usage=usage, custom_llm_provider=provider, model_info=price_table
+            model=model,
+            usage=usage,
+            custom_llm_provider=provider,
+            model_info=price_table,
+            data_residency=data_residency,
+            optional_params=optional_params,
         )
         return prompt_cost + completion_cost