Thanks to player "좋아하는게임을반영한닉네임을사용하세요" for the feedback. The token consumption issue you reported has been identified and fixed.
What's new:
1. Token efficiency fix
Timestamps were previously injected into the system prompt on every message, defeating the model's context caching and inflating input costs. With caching working now, cached input costs about 1/30 of before — the same quota goes much further.
2. Token Packs
Settings → Account now includes a Token Packs section, purchasable through the Steam Item Store:
• 1M Tokens — $3.99
• 3M Tokens — $10.99
• 10M Tokens — $34.99
• 30M Tokens — $99.99
Click a pack to open the Steam store. After purchase, your balance is credited automatically when you return to the app — no restart needed. Regional prices are shown in the Steam store.
3. Other improvements
• Balance auto-syncs when you return to the app window; a manual Refresh button is also available
• UI text completed across 10 languages
Thank you to everyone sharing feedback — every report shapes Selby directly.