$ claw.zip v1.0
> compress your ai spend
The closed-loop token optimizer for OpenClaw. Hand us your credentials — we compact your queries, route to the optimal model, and cut your bill by up to 93%.
npx claw-zipWorks with any OpenClaw setup · No config required
// see the difference
Lossless compression for prompts
Same semantics. Fewer tokens. Your output stays identical — your bill doesn’t.
// how it works
Three steps. Zero config.
A closed loop between you and your models. We sit in the middle and make everything cheaper.
01 — Compact
Compress
Queries are semantically compacted — redundant tokens stripped, intent preserved. Same output, smaller input.
02 — Route
Route
Each query is scored by complexity and routed to the cheapest model that can handle it. GPT-4 when you need it, Haiku when you don’t.
03 — Save
Save
Compaction + routing = compound savings. Most users see 80–93% reduction in monthly spend from day one.
// features
What’s in the box
Everything you need to stop overpaying for AI. Nothing you don’t.
Query compaction
Lossless prompt compression that preserves semantic meaning. Same model output, significantly fewer input tokens.
Model routing
Automatically route each query to the cheapest model that can handle its complexity. No manual switching.
Encrypted at rest
Your API credentials are encrypted with AES-256-GCM before storage. Decrypted in memory only when proxying your request — never stored in plaintext.
Transparent savings
Every response includes headers showing your original token count, compressed count, and exact savings percentage. No guessing — see what you saved on every request.
Safe fallback
If compression ever fails, your request goes through untouched. Smart falls back to algorithmic, algorithmic falls back to passthrough. Zero downtime risk.
// quick start
Up and running in 60 seconds
Pick your install method. Run one command. Start saving.
npx claw-zip init curl -sSL https://claw.zip/install | sh// pricing
Simple pricing. No surprises.
Start free. Upgrade when claw.zip has already paid for itself.
Free
$0 /mo
Get started and see the savings for yourself.
- 1 API key
- 500 requests/mo
- Up to $50/mo in savings
- Basic compaction
- Basic model routing
- Community support
Pro
$29 /mo
Unlimited savings. Pays for itself on day one.
- 3 API keys
- 10,000 requests/mo
- Unlimited savings
- Advanced compaction engine
- Priority model routing
- Analytics dashboard
- Priority support
Enterprise
Custom
For teams that need dedicated support and unlimited scale.
- Unlimited API keys
- Unlimited requests
- Unlimited savings
- Advanced compaction engine
- Priority model routing
- Analytics dashboard
- Dedicated support + SSO
// faq
Frequently Asked Questions
Quick answers to common questions.
How do I get started with claw.zip?
Run npx claw-zip init in your terminal. It will walk you through credential setup and configuration. You can also sign up at claw.zip and create your first API key from the dashboard.
Will compression change my model outputs?
Our compression is designed to preserve semantic meaning. For most use cases, outputs are identical. If you need guaranteed verbatim passthrough, you can disable compression per-key from the dashboard.
What happens if claw.zip goes down?
claw.zip runs on Cloudflare Workers across 300+ global edge locations. In the unlikely event of an outage, you can point your config back to the Anthropic API directly — no data is locked in our system.
Can I use claw.zip with non-Anthropic models?
Currently, claw.zip is optimized for the Anthropic API (Claude models). Support for additional providers is on our roadmap.