Shrink Input Tokens 2×
Keep the Facts,
Not the Bloat.

Drop the Telegrapher API in front of your current RAG stack.
It converts documents into compact Telegraph English, cutting vector storage and context spend by two-thirds and speeding GPT answers up to 55 %.
No model retraining, live before lunch.
Get Early Access
WHAT –
What Is Telegraph English?

Telegraph English (TE) is a symbol-rich compact text format that:

  • Shrinks tokens ≈ 55 % while keeping ≥ 98 % of the facts.
  • Writes one fact per line and semantically groups them in chunks.
  • Feeds any LLM - no prompts, no finetune, no weight hacks.
Quick Example
Original: 
"""Earnings per share (EPS) were $3.42 for the fourth quarter, 
exceeding analyst expectations of $3.25. The company reported 
a return on equity (ROE) of 21.8% for the fiscal year."""

TelegraphEnglish: 
"""EPS=USD3.42 Q4 VS EXPECTED=USD3.25
ROE=21.8% FISCAL-YEAR"""
WHY – The Token Drain


  • 60-70 % of a RAG bill is storage, embeddings, and context padding
  • Summaries lose citations; token masking drops recall.
  • Budgets explode as corpora, languages, and versions pile up.

TE kills the padding and keeps the facts,
compounding savings from ingest to inference.

HOW Telegraph English
API works

Seamless Integration, Powerful Results.
  • Compress - Transforms raw text into compact Telegraph English, reducing payload by 65%.
  • Embed - Delivers ready-made vector embeddings with no additional model hosting required.
  • Store - Provides ready-to-upsert JSONL for any vector database, cutting storage costs by 65%.
  • Retrieve - Requires only 35% of normal tokens, making LLM responses up to 55% faster.
  • Fidelity on Demand - Each chunk includes ID mapping for instant conversion back to original text.
  • Live in a Day - Simple batch API and wrappers let most teams implement and test before lunch.
Python Example
That’s it - compress, embed, and store in two lines of code.
import terag
from pinecone import Pinecone

# 1. Process document with Telegrapher (in Pinecone-compatible format)
result = terag.process_document("your-doc.pdf", dimension=1536)
pinecone_records = result.to_pinecone()

# 2. Initialize Pinecone client
pc = Pinecone(api_key="YOUR_API_KEY")
index = pc.Index("your-index-name")

# 3. Upsert directly to Pinecone
index.upsert(vectors=pinecone_records)
Five Chores vs One Call
See how Telegrapher replaces manual chunking, lossy compression, self-hosted embedding, and custom serializers with a single HTTPS endpoint that streams insert-ready JSONL.
PERFORMANCE SNAPSHOT


  • Token reduction: 65 % avg (LongBench + live corpora)
  • GPT latency: -40–55 % on long answers
  • Precision: F1 +8 % vs full-text baseline
USE CASES


  • RAG platforms – 2 - 3× more context, fewer hallucinations
  • Vector-DB ops – 65 % lower storage & write costs
  • API cost control – slice spend on GPT, Claude, Gemini endpoints
  • Long-context chat – fit richer history without model upgrades
PRICING –
Simple, Usage-Based
Pay per million tokens ingested. No upfront fees, no hidden tiers.
Tell us your monthly token volume;
we quote a per-million rate that drops as you grow.

Free pilot run, dedicated support & integration help
Compression is one-time—every retrieval and generation that follows is permanently cheaper.
What Early Testers Say
Ready to Compress Your Token Costs?
Join forward‑looking AI teams
already boosting their token efficiency.

Early‑access perks:
  • Priority onboarding support
  • Influence on feature roadmap
  • Preferred pricing at launch.
Made on
Tilda