Observability
Helicone monitoring
Helicone provides LLM API monitoring with cost tracking and quality analysis. Add SuperCompress metrics to your Helicone dashboards.
Helicone integration
import helicone
from supercompress import Compressor
comp = Compressor()
helicone.init(api_key="...")
@helicone.log
def compress_and_chat(context, query):
result = comp.compress(context, query)
# Helicone automatically logs the LLM call costs
# Add compression metrics as custom properties
helicone.set_property("original_tokens", result.original_tokens)
helicone.set_property("kept_tokens", result.kept_tokens)
return llm.chat(result.compressed_text, query)Frequently asked questions
Does Helicone show cost savings from compression?
Yes. Compare token costs before and after compression in the Helicone dashboard.
Can I set alerts for compression ratio changes?
Yes. Helicone supports alerting on custom properties.
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.