{% hint style="info" %}
**This screen shows your current available balance and options to buy one-time AI credits:**
{% endhint %}
***
**Your Balance:**\
Displays the number of AI credits remaining\
Example: `15000 credits` on `5/30/2025`
**Credit Usage Graph:**\
A sparkline visualizing your credit usage or refill history. A spike usually means a purchase or sudden increase in usage
**Buy One-Time Credits:**\
You can purchase additional credits if you run low:
* **500k credits** → **$5.00**
* **1M credits** → **$9.00**
## **How to** purchase Credits
After selecting the number of credits (500k / 1M) and clicking the "Continue" button, you purchase credits for the artificial intelligence chatbot:
it allows you to:
* Chat with the BigBeluga AI assistant
* Use longer conversations without limits
***
## **How the Credit System Works**
BigBeluga uses a **token-based AI system**, where credits are consumed based on how much data is sent to or from the chatbot (not just message count).
### **Key Points:**
One "credit" = roughly **1 token**.
Tokens are used **per message**, but also include:
* **Context/history** from previous messages
* **Your question**
* **The AI’s full response**
**More message history = more tokens used per request.**
***
## **How Much Do You Get?**
* **500,000 tokens (\~$5)** ≈ **250 AI messages**
* **1,000,000 tokens (\~$9)** ≈ **500 AI messages**
(*Assuming one message + reply consumes \~2,000 tokens on average*)
***
## **Summary for Users**
* Your credit balance shows how much AI interaction time you still have.
* When you're chatting with the AI, every message costs credits based on size + context.
* You can top up anytime with one-time purchases.
* 500k tokens should last an average user quite a while if they keep chats concise.
Let me know if you want this explanation written in a more casual or onboarding-friendly style for users.
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.bigbeluga.com/extension/bigbeluga-sonar-tm/credits.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.