add completion_image_pricing to Pricing Model + hardcoded values for Gemini Image models

routstr/payment/cost_calculation.py

@@ -5,7 +5,6 @@ from pydantic.v1 import BaseModel
 from ..core import get_logger
 from ..core.db import AsyncSession
 from ..core.settings import settings
-from .price import sats_usd_price
 
 logger = get_logger(__name__)
 
@@ -65,48 +64,13 @@ async def calculate_cost(  # todo: can be sync
         )
         return cost_data
 
-    usage_data = response_data["usage"]
-
-    if "cost" in usage_data and usage_data["cost"] is not None:
-        try:
-            usd_cost = float(usage_data["cost"])
-            sats_per_usd = 1.0 / sats_usd_price()
-            cost_in_sats = usd_cost * sats_per_usd
-            cost_in_msats = math.ceil(cost_in_sats * 1000)
-
-            logger.info(
-                "Using cost field from usage data",
-                extra={
-                    "usd_cost": usd_cost,
-                    "cost_in_sats": cost_in_sats,
-                    "cost_in_msats": cost_in_msats,
-                    "model": response_data.get("model", "unknown"),
-                },
-            )
-
-            return CostData(
-                base_msats=0,
-                input_msats=0,  # Cost field doesn't break down by token type
-                output_msats=0,
-                total_msats=cost_in_msats,
-            )
-        except Exception as e:
-            logger.warning(
-                "Error using cost field, falling back to token-based calculation",
-                extra={
-                    "error": str(e),
-                    "cost_value": usage_data.get("cost"),
-                    "model": response_data.get("model", "unknown"),
-                },
-            )
-            # Fall through to token-based calculation
-
     MSATS_PER_1K_INPUT_TOKENS: float = (
         float(settings.fixed_per_1k_input_tokens) * 1000.0
     )
     MSATS_PER_1K_OUTPUT_TOKENS: float = (
         float(settings.fixed_per_1k_output_tokens) * 1000.0
     )
+    MSATS_PER_1K_IMAGE_COMPLETION_TOKENS: float = 0.0
 
     if not settings.fixed_pricing:
         response_model = response_data.get("model", "")
@@ -141,11 +105,13 @@ async def calculate_cost(  # todo: can be sync
         try:
             mspp = float(model_obj.sats_pricing.prompt)
             mspc = float(model_obj.sats_pricing.completion)
+            mspci = float(getattr(model_obj.sats_pricing, "completion_image", 0.0))
         except Exception:
             return CostDataError(message="Invalid pricing data", code="pricing_invalid")
 
         MSATS_PER_1K_INPUT_TOKENS = mspp * 1_000_000.0
         MSATS_PER_1K_OUTPUT_TOKENS = mspc * 1_000_000.0
+        MSATS_PER_1K_IMAGE_COMPLETION_TOKENS = mspci * 1_000_000.0
 
         logger.info(
             "Applied model-specific pricing",
@@ -153,6 +119,7 @@ async def calculate_cost(  # todo: can be sync
                 "model": response_model,
                 "input_price_msats_per_1k": MSATS_PER_1K_INPUT_TOKENS,
                 "output_price_msats_per_1k": MSATS_PER_1K_OUTPUT_TOKENS,
+                "image_completion_price_msats_per_1k": MSATS_PER_1K_IMAGE_COMPLETION_TOKENS,
             },
         )
 
@@ -165,18 +132,44 @@ async def calculate_cost(  # todo: can be sync
             },
         )
         return cost_data
-
+    usage_data = response_data["usage"]
     input_tokens = usage_data.get("prompt_tokens", 0)
     output_tokens = usage_data.get("completion_tokens", 0)
 
     # added for response api
-    input_tokens = input_tokens if input_tokens != 0 else usage_data.get("input_tokens", 0)
-    output_tokens = output_tokens if output_tokens != 0 else usage_data.get("output_tokens", 0)
+    input_tokens = (
+        input_tokens if input_tokens != 0 else usage_data.get("input_tokens", 0)
+    )
+    output_tokens = (
+        output_tokens if output_tokens != 0 else usage_data.get("output_tokens", 0)
+    )
+
+    # Calculate image completion cost
+    image_completion_msats = 0.0
+    if MSATS_PER_1K_IMAGE_COMPLETION_TOKENS > 0:
+        completion_details = usage_data.get("completion_tokens_details", {})
+        image_tokens = completion_details.get("image_tokens", 0)
+
+        if image_tokens > 0:
+            if output_tokens >= image_tokens:
+                output_tokens -= image_tokens
+
+            image_completion_msats = round(
+                image_tokens / 1000 * MSATS_PER_1K_IMAGE_COMPLETION_TOKENS, 3
+            )
+
+            logger.info(
+                "Calculated image completion cost",
+                extra={
+                    "image_tokens": image_tokens,
+                    "image_completion_msats": image_completion_msats,
+                },
+            )
 
     input_msats = round(input_tokens / 1000 * MSATS_PER_1K_INPUT_TOKENS, 3)
 
     output_msats = round(output_tokens / 1000 * MSATS_PER_1K_OUTPUT_TOKENS, 3)
-    token_based_cost = math.ceil(input_msats + output_msats)
+    token_based_cost = math.ceil(input_msats + output_msats + image_completion_msats)
 
     logger.info(
         "Calculated token-based cost",
@@ -185,6 +178,7 @@ async def calculate_cost(  # todo: can be sync
             "output_tokens": output_tokens,
             "input_cost_msats": input_msats,
             "output_cost_msats": output_msats,
+            "image_completion_msats": image_completion_msats,
             "total_cost_msats": token_based_cost,
             "model": response_data.get("model", "unknown"),
         },

routstr/payment/models.py

@@ -31,6 +31,7 @@ class Pricing(BaseModel):
     completion: float
     request: float = 0.0
     image: float = 0.0
+    completion_image: float = 0.0
     web_search: float = 0.0
     internal_reasoning: float = 0.0
     input_cache_read: float = 0.0
@@ -40,6 +41,13 @@ class Pricing(BaseModel):
     max_cost: float = 0.0  # in sats not msats
 
 
+PRICING_OVERRIDES = {
+    "gemini-3-pro-image-preview": {"completion_image": 0.00012},
+    "gemini-2.5-flash-image": {"completion_image": 0.00003},
+    "gemini-2.0-flash": {"completion_image": 0.00003},
+}
+
+
 class TopProvider(BaseModel):
     context_length: int | None = None
     max_completion_tokens: int | None = None
@@ -116,6 +124,16 @@ async def async_fetch_openrouter_models(source_filter: str | None = None) -> lis
                 if not _has_valid_pricing(model):
                     continue
 
+                # Apply manual pricing overrides
+                if model_id in PRICING_OVERRIDES:
+                    pricing = model.get("pricing", {})
+                    if pricing:
+                        for k, v in PRICING_OVERRIDES[model_id].items():
+                            pricing[k] = str(
+                                v
+                            )  # OpenRouter API returns strings for pricing
+                        model["pricing"] = pricing
+
                 models_data.append(model)
 
             return models_data
@@ -148,6 +166,12 @@ def _row_to_model(
     if isinstance(pricing, dict) and float(pricing.get("request", 0.0)) <= 0.0:
         pricing["request"] = max(pricing.get("request", 0.0), 0.0)
 
+    # Apply defaults for missing fields from manual overrides
+    if row.id in PRICING_OVERRIDES and isinstance(pricing, dict):
+        for k, v in PRICING_OVERRIDES[row.id].items():
+            if k not in pricing:
+                pricing[k] = v
+
     parsed_pricing = Pricing.parse_obj(pricing)
     model = Model(
         id=row.id,
@@ -507,6 +531,7 @@ def _pricing_matches(
         "completion",
         "request",
         "image",
+        "completion_image",
         "web_search",
         "internal_reasoning",
     ]
@@ -528,5 +553,4 @@ async def models(session: AsyncSession = Depends(get_session)) -> dict:
     from ..proxy import get_unique_models
 
     items = get_unique_models()
-    print(items)
     return {"data": items}

routstr/payment/price.py

@@ -85,7 +85,6 @@ async def _fetch_btc_usd_price() -> float:
                 _binance_btc_usdt(client),
             )
             valid_prices = [price for price in prices if price is not None]
-            print(valid_prices)
             if not valid_prices:
                 logger.error("No valid BTC prices obtained from any exchange")
                 raise ValueError("Unable to fetch BTC price from any exchange")
@@ -103,26 +102,14 @@ async def _update_prices() -> None:
     global BTC_USD_PRICE, SATS_USD_PRICE
     try:
         btc_price = await _fetch_btc_usd_price()
-        BTC_USD_PRICE = btc_price
-        SATS_USD_PRICE = btc_price / 100_000_000
-        logger.info(
-            "Updated BTC/SATS prices successfully",
-            extra={"btc_usd": btc_price, "sats_usd": SATS_USD_PRICE},
-        )
     except Exception as e:
         logger.warning(
-            "Failed to fetch live prices, using fallback if available",
+            "Skipping price update; unable to fetch BTC price",
             extra={"error": str(e), "error_type": type(e).__name__},
         )
-        # Use fallback price if no price is set
-        if BTC_USD_PRICE is None or SATS_USD_PRICE is None:
-            fallback_btc_price = getattr(settings, "fallback_btc_usd_price", 50000.0)
-            BTC_USD_PRICE = fallback_btc_price
-            SATS_USD_PRICE = fallback_btc_price / 100_000_000
-            logger.info(
-                "Using fallback BTC price",
-                extra={"fallback_btc_usd": fallback_btc_price, "sats_usd": SATS_USD_PRICE},
-            )
+        return
+    BTC_USD_PRICE = btc_price
+    SATS_USD_PRICE = btc_price / 100_000_000
 
 
 def btc_usd_price() -> float: