diff --git a/app.py b/app.py
index 1fdeddd..910f6e5 100644
--- a/app.py
+++ b/app.py
@@ -4623,6 +4623,52 @@ def chat_send_message(conversation_id):
# Get model from request or session (flash = default, pro = premium)
model_choice = data.get('model') or session.get('chat_model', 'flash')
+ # Check Pro model limits (Flash is free - no limits)
+ if model_choice == 'pro':
+ # Users without limits (admins)
+ UNLIMITED_USERS = ['maciej.pienczyn@inpi.pl', 'artur.wiertel@waterm.pl']
+
+ if current_user.email not in UNLIMITED_USERS:
+ # Check daily and monthly limits for Pro
+ from database import AIApiCost
+ db_check = SessionLocal()
+ try:
+ # Daily limit: $2.00
+ today_start = datetime.now().replace(hour=0, minute=0, second=0, microsecond=0)
+ daily_costs = db_check.query(AIApiCost).filter(
+ AIApiCost.user_id == current_user.id,
+ AIApiCost.timestamp >= today_start,
+ AIApiCost.model_name.like('%pro%')
+ ).all()
+ daily_total = sum(c.total_cost_usd or 0 for c in daily_costs)
+
+ if daily_total >= 2.0:
+ return jsonify({
+ 'success': False,
+ 'error': 'Osiągnięto dzienny limit Pro ($2.00). Spróbuj jutro lub użyj darmowego modelu Flash.',
+ 'limit_exceeded': 'daily',
+ 'daily_used': round(daily_total, 2)
+ }), 429
+
+ # Monthly limit: $20.00
+ month_start = datetime.now().replace(day=1, hour=0, minute=0, second=0, microsecond=0)
+ monthly_costs = db_check.query(AIApiCost).filter(
+ AIApiCost.user_id == current_user.id,
+ AIApiCost.timestamp >= month_start,
+ AIApiCost.model_name.like('%pro%')
+ ).all()
+ monthly_total = sum(c.total_cost_usd or 0 for c in monthly_costs)
+
+ if monthly_total >= 20.0:
+ return jsonify({
+ 'success': False,
+ 'error': 'Osiągnięto miesięczny limit Pro ($20.00). Użyj darmowego modelu Flash.',
+ 'limit_exceeded': 'monthly',
+ 'monthly_used': round(monthly_total, 2)
+ }), 429
+ finally:
+ db_check.close()
+
# Map model choice to actual model name
model_map = {
'flash': '3-flash',
diff --git a/gemini_service.py b/gemini_service.py
index 57e588c..36e99a7 100644
--- a/gemini_service.py
+++ b/gemini_service.py
@@ -58,13 +58,14 @@ THINKING_LEVELS = {
}
# Pricing per 1M tokens (USD) - updated 2026-01-29
+# Note: Flash on Free Tier = $0.00, Pro on Paid Tier = paid pricing
GEMINI_PRICING = {
'gemini-2.5-flash': {'input': 0.30, 'output': 2.50, 'thinking': 0},
'gemini-2.5-flash-lite': {'input': 0.10, 'output': 0.40, 'thinking': 0},
'gemini-2.5-pro': {'input': 1.25, 'output': 10.00, 'thinking': 0},
'gemini-2.0-flash': {'input': 0.10, 'output': 0.40, 'thinking': 0},
- 'gemini-3-flash-preview': {'input': 0.50, 'output': 3.00, 'thinking': 1.00},
- 'gemini-3-pro-preview': {'input': 2.00, 'output': 12.00, 'thinking': 4.00},
+ 'gemini-3-flash-preview': {'input': 0.00, 'output': 0.00, 'thinking': 0.00}, # Free tier!
+ 'gemini-3-pro-preview': {'input': 2.00, 'output': 12.00, 'thinking': 4.00}, # Paid tier
}
@@ -82,12 +83,24 @@ class GeminiService:
Initialize Gemini service.
Args:
- api_key: Google AI API key (reads from GOOGLE_GEMINI_API_KEY env if not provided)
+ api_key: Google AI API key (reads from env if not provided)
model: Model to use ('flash', 'flash-lite', 'pro', '3-flash', '3-pro')
thinking_level: Reasoning depth ('minimal', 'low', 'medium', 'high')
include_thoughts: Whether to include thinking process in response (for debugging)
+
+ API Keys (auto-selected by model):
+ - GOOGLE_GEMINI_API_KEY_FREE: Free tier for Flash models (no cost)
+ - GOOGLE_GEMINI_API_KEY: Paid tier for Pro models
"""
- self.api_key = api_key or os.getenv('GOOGLE_GEMINI_API_KEY')
+ # Auto-select API key based on model (Free tier for Flash, Paid for Pro)
+ if api_key:
+ self.api_key = api_key
+ elif model in ('3-pro', 'pro'):
+ # Pro models use paid tier
+ self.api_key = os.getenv('GOOGLE_GEMINI_API_KEY')
+ else:
+ # Flash models prefer free tier, fallback to paid
+ self.api_key = os.getenv('GOOGLE_GEMINI_API_KEY_FREE') or os.getenv('GOOGLE_GEMINI_API_KEY')
# Debug: Log API key (masked)
if self.api_key:
diff --git a/templates/chat.html b/templates/chat.html
index 77d1c3b..7e5d276 100755
--- a/templates/chat.html
+++ b/templates/chat.html
@@ -733,6 +733,16 @@
background: linear-gradient(135deg, #f59e0b 0%, #d97706 100%);
}
+ .thinking-option-badge.free {
+ background: linear-gradient(135deg, #10b981 0%, #059669 100%);
+ }
+
+ .thinking-option-price.free {
+ color: #10b981;
+ font-weight: 500;
+ font-style: normal;
+ }
+
.thinking-option-price {
display: block;
font-size: 11px;
@@ -1247,10 +1257,10 @@
- Szybki i ekonomiczny. Dla prostych pytań o firmy, kontakty, wydarzenia.
- ~$0.05/pytanie
+ Szybki i skuteczny. Dla większości pytań o firmy, kontakty, wydarzenia.
+ Bez opłat
-
Głęboka analiza. Dla złożonych pytań, strategii, rekomendacji.
-
~$0.20/pytanie
+
Głęboka analiza i rozumowanie. Dla złożonych pytań, strategii, rekomendacji.
+
~$0.20/pytanie · limit: $2/dzień