Sign in Subscribe

Brainbox: Token Usage and Managing Your Allowance

Last updated on 

Tokens are the units that AI models use to process text. Think of them as the building blocks of language — each token represents roughly 0.75 words. Whether you're typing a short question or uploading a long document, everything is converted into tokens before the AI processes it.

Your Free Token Allowance

Every Wavebox Pro subscription includes 1 million free OpenAI tokens per month. This allowance resets on the 1st of each month, and unused tokens do not carry over to the next month.

The free tokens cover API calls to GPT-5 Mini model tiers. If you want to use more tokens, switch to different models, or continue beyond your monthly allowance, you can add your own API key.

What Uses Tokens?

Tokens are consumed in two places:

  • Your messages — every message you send to Brainbox counts toward your token usage
  • Brainbox responses — every response Brainbox generates also uses tokens

Longer conversations consume more tokens because both your prompts and the generated responses are counted. Attaching page content, files, or screenshots also adds to your overall token count, since that content must be processed by the model.

How to Check Your Token Usage

  1. Open the Brainbox panel in the main Wavebox window (robot icon in the toolbar)
  2. Click the cog icon (⚙️) in the top-right corner
  3. Select the Usage tab

You'll see a breakdown of your current month's token consumption and how much of your allowance remains.

Adding Your Own API Key

To extend your token allowance or use different models, add your own OpenAI or Anthropic API key:

  1. Open the Brainbox panel
  2. Click the cog icon (⚙️)
  3. Navigate to API Keys
  4. Enter your API key for OpenAI, Anthropic, or both
  5. Save your changes

When you use your own API key, usage is billed directly by OpenAI or Anthropic according to their pricing — it is separate from your Wavebox Pro subscription and not deducted from your free monthly allowance.

Tips for Managing Tokens

Be Specific in Your Prompts

Vague or overly long prompts use more tokens without improving results. Focus your questions:

  • Instead of: "Tell me everything about content marketing"
  • Try: "What are the top 3 strategies for B2B SaaS content marketing?"

Choose the Right Model Tier for the Task

Different tasks require different model capabilities:

  • Use GPT-5 Mini for everyday tasks (covered by your free monthly allowance)
  • Use Claude Haiku 4.5 for fast, token-efficient responses (requires API key)
  • Use Claude Sonnet 4.5 for moderately complex analysis (requires API key)
  • Use Claude Opus 4.5 or GPT 5.2 for highly complex or creative work (requires API key)

Start New Conversations Rather Than Extending Long Ones

Very long conversation threads consume more tokens with each new message because the entire history is reprocessed. If you're moving to a different topic, start a fresh conversation to save tokens.

Monitor Usage Regularly

Check your Usage tab monthly to stay aware of your consumption patterns. If you're approaching your limit, consider:

  • Switching to a more token-efficient model tier
  • Adding your own API key to continue working beyond the monthly allowance
  • Breaking complex tasks into multiple focused conversations