fix: correct account stats pricing priority order

Priority was wrong:
- Before: custom rules → LiteLLM (when ApplyPricingToAccountStats) → nil
- After:  custom rules → totalCost (when ApplyPricingToAccountStats) → LiteLLM → nil

When ApplyPricingToAccountStats is enabled, use the request's actual
client billing cost (before multiplier) as account_stats_cost, instead
of recalculating from LiteLLM per-token prices which produced incorrect
values for per-request billing mode.

LiteLLM model pricing is now the final fallback (priority 3), used only
when neither custom rules nor ApplyPricingToAccountStats apply.

backend/internal/service/openai_gateway_service.go

@@ -4582,7 +4582,7 @@ func (s *OpenAIGatewayService) RecordUsage(ctx context.Context, input *OpenAIRec
 		usageLog.AccountStatsCost = resolveAccountStatsCost(
 			ctx, s.channelService, s.billingService,
 			account.ID, *apiKey.GroupID, statsModel,
-			tokens, 1,
+			tokens, 1, cost.TotalCost,
 		)
 	}