WaxFrame
What Are Tokens?
Tokens are the unit of measurement AI models use to read and write text. Roughly speaking, 1 token ≈ ¾ of a word. A typical paragraph is about 100 tokens. A full-page document might be 500–800 tokens.
Every time WaxFrame runs a round, your Builder AI reads your entire document plus the full prompt, then writes back the updated version. That is a lot of tokens — both in and out — every single round.
Free-tier AI accounts have token limits — a cap on how much they can read and write per minute, per hour, or per day. If your Builder hits that limit mid-session, it will either fail or make you wait before it can continue.
Worker Bees only send numbered suggestions, so they use far fewer tokens. Free-tier AIs work fine as Worker Bees. The Builder is the one that needs headroom.
WaxFrame — open source, no server, no tracking. Learn more →
💡 Billing rates are subject to change. Check each provider's billing page at least monthly to stay current with pricing.
| AI | Token limits | Cost | Verdict | Billing |
|---|---|---|---|---|
| Claude | Large context window, generous API limits | Pay-as-you-go | Excellent Builder | Check rates → |
| ChatGPT | Large context, reliable at high volume | Pay-as-you-go | Excellent Builder | Check rates → |
| Gemini | Very large context window, generous free tier | Free tier available | Excellent — free option | Check rates → |
| DeepSeek | Large context, very low cost per token | Pay-as-you-go (cheap) | Great — best value Builder | Check rates → |
| Grok | Good context, API limits vary | Pay-as-you-go | Fine with API key | Check rates → |
| Perplexity | Smaller context, search-focused model | Pay-as-you-go | Better as a Worker Bee | Check rates → |
Say you are working on a 2,000-word report. That is roughly 2,700 tokens. Your Builder reads the full document plus the prompt (~500 tokens) = about 3,200 tokens in, then writes back the updated version at roughly the same length. That is ~6,000 tokens per round.
Over 5 rounds, that is ~30,000 tokens from your Builder alone. With a paid API key this costs a few cents. On a free tier with strict limits, this could hit the cap by round 2 or 3.
Bottom line: use a paid API key for your Builder, or use Gemini's free tier which is genuinely generous. Keep cost-conscious or free-tier AIs as Worker Bees where the token load is light.
Keep your document focused. The longer your document, the more tokens your Builder uses every round. Trim content that is no longer relevant as the document improves.
Switch Builders if a round fails. DeepSeek is the best value for most documents. If a round fails with a missing output structure error — especially on a large or complex document — try switching to ChatGPT or Gemini as your Builder and retrying. Some AIs are less consistent at following strict formatting instructions under heavy load. This is a behavioral difference between models, not a hard size limit.
Use Worker Bees wisely. You can disable individual AIs per session from the work screen. If an AI is consistently unhelpful, turn it off — fewer Worker Bees means less input for the Builder to process.
Start small. For your first session, try a shorter document or a simpler goal. Once you understand how the rounds work you can take on larger projects confidently.
WaxFrame is fully open source under the AGPL-3.0 license. Every line of code is public and auditable.
💡 Your API keys go directly from your browser to each AI provider. WaxFrame never sees them. Read the source on GitHub →