Simple, transparent pricing
Start free. Upgrade when you're saving money.
All plans include a 14-day free trial. No credit card required to start.
What's the ROI?
At 40% average compression, every $100 in LLM costs becomes $60. At 1,000 calls/day, that's thousands in monthly savings.
At $100/mo/mo LLM spend
$40
saved/mo
Free plan
At $500/mo/mo LLM spend
$200
saved/mo
Starter plan
At $2,500/mo/mo LLM spend
$1,000
saved/mo
Pro plan
Frequently asked questions
Do I need a credit card to get started?
No. The free plan requires no credit card. You get 500K tokens/month and 10 playground compressions per day, forever.
What counts as a "token"?
We count tokens using tiktoken (cl100k_base), the same tokenizer used by GPT-4o and Claude. Roughly 1 token ≈ 4 characters of English text.
What is the quality score?
Every compression response includes a quality score (0–5). It measures semantic similarity between the original and compressed text. A score of 4+ means excellent meaning preservation.
What's the difference between Conservative, Balanced, and Aggressive modes?
Conservative removes only obvious redundancies (typical 15–25% savings). Balanced removes filler phrases and restructures for conciseness (30–45% savings). Aggressive maximises compression using LLMLingua — may slightly alter phrasing (40–60% savings, available on paid plans).
Can I cancel anytime?
Yes. Cancel from the billing portal at any time. You retain access until the end of your billing period.
Is there a free trial for paid plans?
Yes — Starter and Pro include a 14-day free trial. No credit card required to start.
Do you store my prompts?
No. We process your prompts in memory and never store them. Your prompts go in, the compressed version comes out — nothing is persisted.
What LLMs does ziptoken work with?
Any LLM. We compress the text before you send it to your provider. Claude, GPT-4, Gemini, Mistral, Llama — if it takes text input, ziptoken works with it.