IntroductionQuickstartTTC RouterAbout CompressionOpenAIVercel AI SDKAnthropicOpenRouterCompression StatisticsAdvanced AggressivenessApp IDProtect TextData RetentionTroubleshooting

Introduction

Compress LLM prompts to cut costs and improve accuracy.

What is The Token Company LLM input compression?

Compression middleware for cutting out low signal tokens bloating LLM context.

Backed by the Founders of

Dropbox
Hugging Face
Slack
Supercell
AMD Silo AI

Why compress?

  • Fit more context
  • Faster inference
  • Improve long context accuracy
  • Cut costs by 10-40%

Quick example

from thetokencompany import TheTokenCompany

client = TheTokenCompany(api_key="ttc-...")
result = client.compress("Your long prompt text...")

print(result.output)         # compressed text
print(result.tokens_saved)   # tokens removed
print(result.compression_ratio)  # e.g. 3.2x

How it works

  1. Send your prompt to the TTC compression API
  2. Receive compressed text back
  3. Pass the compressed text to any LLM (OpenAI, Claude, Gemini, etc.)

Next steps