Overview

Compresr reduces LLM token costs by up to 90% through intelligent context compression.

Quick Start

  1. Get your API Key
  2. Install the SDK: pip install compresr
  3. Start compressing

Compression Ratios

Set your target compression ratio to specify the percentage of context to filter out. Our model is trained to match your target, but slight variations are possible.

0.7–0.9 Aggressive, max savings
0.4–0.6 Balanced (recommended)
0.1–0.3 Conservative, minimal loss

Integration

Python SDK: pip install compresr
REST API: Use X-API-Key header with any HTTP client