Usage Limits & Balance¶

To ensure fair access for all university members, uniGPT uses a token-based balance system.

For a comparison of available internal and external models, see Available Models.

How It Works¶

• Every user receives a token balance.
• Each prompt and response consumes tokens from your balance.
• Your balance resets every 4 hours.

Checking Your Balance¶

Click on your username in the chat interface to see your current balance.

Tips for Saving Tokens¶

1. Use internal models: They consume fewer resources and cost the university less (e.g., Mistral Small, Llama-3.3-70B, gemma-3-27b-it, medgemma-1.5-4b-it, Qwen3.5-35B-A3B).
2. Avoid expensive models for simple tasks: Use Mistral Small or Llama instead of Claude Opus for basic questions.
3. Prefer Gemini if you need an external model — it is more cost-effective than Claude Opus or GPT-5.
4. Lower thinking level: For supported models, select a lower "thinking" setting to reduce token consumption.

Related Information¶

• See Available Models for model descriptions, privacy guidance, and relative input/output credit costs.

Balance Not Resetting?¶

If your balance appears stuck at zero after 4 hours, try logging out and logging back in. This usually resolves the issue.