Deployment guide
Google Cloud deployment
Google Cloud Run provides a managed container platform. Deploy SuperCompress as a stateless container that auto-scales to zero when not in use.
Cloud Run setup
FROM python:3.11-slim
RUN pip install supercompress fastapi uvicorn
COPY server.py .
CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8080"]Frequently asked questions
What is the cold start time?
Cloud Run cold starts are ~200ms. Subsequent requests are sub-100ms.
How many concurrent requests can it handle?
Cloud Run auto-scales. Each container handles ~100 concurrent compression requests.
Build with less context
Put compression in front of your next LLM call.
Use the hosted API or run SuperCompress locally. Keep the evidence, drop the token waste, and measure the savings before it reaches your model.