All posts
Announcement2 min read
Announcing the Batch API: Compress 100 Prompts in One Call
The new /api/v1/batch endpoint lets you compress up to 100 texts in a single round-trip — perfect for RAG pipelines and document processing.
z
ziptoken
Product
Starting today, the ziptoken Batch API is available to all Starter and Pro users.
Why batch?
If you're running a RAG pipeline that retrieves 50 context chunks before each LLM call, making 50 separate compression requests adds unnecessary latency and HTTP overhead. With the Batch API, you send one request and get all 50 back compressed — typically in <100ms total.
Limits
- Up to 100 texts per request
- Each text obeys your plan's max token limit
- Available on Starter ($19/mo) and above
See the API Reference for the full schema.
Start compressing your prompts
Free tier — 50,000 tokens/month, no credit card required.