Blog
Engineering deep-dives, product updates, and integration tutorials.
Product4 min read
Rule-Based vs. Neural Compression: When to Use Each
LLMLingua and similar neural approaches achieve higher compression, but at a cost. We explain the trade-offs and when each mode is the right choice.
ziptoken
Engineering
Tutorial3 min read
Integrating ziptoken with LangChain in 10 Lines
A step-by-step guide to wrapping ziptoken compression into a LangChain Runnable, so every chain automatically compresses prompts before calling the LLM.
ziptoken
Developer Relations
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.
ziptoken
Product
More articles coming soon