The first dedicated compression-as-a-service API for AI conversation contexts. Drop into any AI app, reduce token usage, preserve what matters.
Paste a conversation and see the compression in real-time
Start free, scale as you grow. No hidden fees.
Drop our single endpoint into any AI application. One call reduces context size while preserving what matters.
# Compress context with a single API call
curl -X POST https://api.contextcompressor.io/v1/compress \
-H "Authorization: Bearer cc_your_api_key" \
-H "Content-Type: application/json" \
-d '{
"messages": [
{"role": "system", "content": "You are a helpful assistant"},
{"role": "user", "content": "I prefer bullet points"}
],
"max_tokens": 4000,
"preserve": ["recent_turns", "preferences"]
}'
# Response
{
"compressed_messages": [...],
"original_tokens": 450,
"compressed_tokens": 180,
"savings_percent": 60,
"metadata": {
"extracted_facts": [...],
"preserved_turns": 4
}
}Track usage, visualize savings, and manage API keys from your dashboard
Usage over time chart will appear here