---
title: Compresr: context compression for LLMs
url: https://compresr.ai/
description: Your prompts carry far more tokens than the model actually reads. Compresr drops the rest: up to 90% fewer tokens, so you cut cost and latency.
---

# Stop paying for context your model doesn’t need.

> Your prompts carry far more tokens than the model actually reads. Compresr drops the rest: up to 90% fewer tokens, so you cut cost and latency. At light compression it matches or beats full-context accuracy on public benchmarks.

> Human-readable page: https://compresr.ai/

## See it on your own file in 60 seconds
- Works in Claude Code, Cursor, or any agent harness.
- Open full demo

## Stop overpaying.
- If you’re paying full price for your tokens, you’re leaving real money on the table.
- Feed us the query and the context. We return only the tokens that actually move the answer. You pay less, the LLM responds faster, and answers get sharper.
- Question-aware: we compress for the task.
- At light ~2× compression, accuracy matches or beats full context.
- SDK or on-prem. Your call.

## Get started in minutes
- Drop-in addition to your current context management workflow.
- Get Your API Key. Create an API key from your console.
- Install the SDK. Install the official SDK. Works with Python 3.8+ or Node.js 18+.
- Compress with a Query (latte_v2). Question-specific compression: keeps tokens relevant to the user query. Required when passing a query.

## Two ways to deploy
- Pick the one that fits your stack.
- Drop-in SDK. One API key. Install, grab a key, compress any prompt or document before it hits your LLM. Pay per million tokens, no surprise bills.
- $10 in free credits on sign-up, no credit card required
- TypeScript & Python clients
- Question-aware compression
- Transparent per-million-token pricing
- Runs inside your VPC. Your data never leaves your network. We deploy Compresr to your infrastructure, tune it for your workload, and support you directly.
- Private deployment in your cloud or data center
- Custom throughput & latency SLAs
- Tailored to your business needs
- Dedicated support

## Related machine surfaces
- [/docs/quick-start.md: first call](/docs/quick-start.md)
- [/contact.md: talk to us](/contact.md)
- [/llms.txt: machine site map](/llms.txt)