ziptoken Documentation
ziptoken compresses AI prompts before you send them to any LLM — reducing token usage by 25–55% with no measurable quality loss.
Base URL
https://api.ziptoken.aiQuickstart
Make your first API call in 2 minutes
API Reference
Full reference for all endpoints and parameters
Integration Guides
OpenAI, Anthropic SDK, LangChain, and more
Changelog
What's new in each release
How it works
- 1
Obtain an API key
Create a free account and generate an API key from your dashboard.
- 2
POST to /api/v1/compress
Send your prompt text. Receive a compressed version — typically 25–55% shorter.
- 3
Forward to your LLM
Use the compressed text with Claude, GPT-4, Gemini, or any LLM. Same quality, fewer tokens.
Authentication
All API requests must include your key in the Authorization header:
Authorization: Bearer zt_live_xxxxxxxxxxxxExample request
curl -X POST https://api.ziptoken.ai/api/v1/compress
-H "Content-Type: application/json"
-H "Authorization: Bearer zt_live_xxxx"
-d '{"text": "Your prompt here", "mode": "balanced"}'{
"data": {
"compressed": "Your prompt here",
"originalTokens": 312,
"compressedTokens": 134,
"ratio": 0.57,
"qualityScore": 4.8
}
}API Tester
Test the API directly from your browser — no setup needed.
Rate limits
| Plan | Tokens / month | Rate limit |
|---|---|---|
| Free | 50,000 | 60 req / min |
| Starter | 2,000,000 | 300 req / min |
| Pro | 10,000,000 | 1,000 req / min |
| Enterprise | Unlimited | Custom |