Simple pricing
Start free. Choose continued hosted compression or more API throughput.
TokenShrink Free
No credit card. No expiry.
- Web compressor and open-source SDK
- API keys and usage dashboard
- 500 full-compression API calls/month when signed in
- Basic compression after the monthly allowance
- No sign-up required to try
TokenShrink Advanced
$36/year — save 40% ($3/mo)
- Everything in Free
- Full hosted compression beyond 500 calls/month
- Usage history and estimated savings dashboard
- 30 requests/minute; 100,000 words/request
- Cancel through your billing portal
TokenShrink Pro
One individual account. Billed monthly.
- Everything in Advanced
- 60 requests/minute across your account
- Twice the Advanced request rate
- Same 100,000-word request limit
- Cancel through your billing portal
Working with a team?
Tell us about your workflow. Shared workspaces and seat billing are in development; Teams is not available to purchase yet.
Explore an illustrative savings scenario
Savings calculator
See what 22% prompt compression is worth
Illustration only: assumes $5 per 1M input tokens, 22% savings, and 30 days. These are not measured savings or a current provider price.
Tokens saved
11,000
Per day at the assumed 22% reduction
Illustrative input cost
$7.50
Before TokenShrink compression
Illustrative payback
91 days
$1.65 saved per month
Frequently asked questions
Is Free really free forever?
Yes. Phrase compression, API access, and the usage dashboard stay free with no credit card and no expiry. We mean it.
What does Advanced add on top of Free?
Advanced keeps full hosted compression available after 500 signed-in API calls per month. The SDK remains free; local codebook experiments are not a paid hosted feature.
Does compression affect AI response quality?
It can. Compression rewrites text, so evaluate answer quality on your own tasks. Detected code and quoted literals are left unchanged. Savings are estimates unless you provide the matching tokenizer.
What AI providers does it work with?
All of them. OpenAI, Anthropic, Google, Mistral, Llama, Cohere — any LLM that accepts text prompts. Pass the returned text to your provider and evaluate the result.
Do you store my prompts?
No. We never store your prompt text. We only store word counts, compression ratios, and usage statistics. Your prompts are processed in memory and immediately discarded.
Can I cancel a paid plan at any time?
Yes. Cancel from the billing portal in your dashboard. You keep your paid features until the end of your billing period, then drop back to Free automatically.