Invalid credentials
"The per-token pricing model is going to look ridiculous in hindsight. Imagine paying per-word to read a book or search your own notes. That's where we are with embeddings and generation right now." — Andrej Karpathy @karpathy Paraphrased from 2024–2025 commentary on embedding economics
Switch from OpenAI to Cohere? Migrate your RAG from one model to another? Merge datasets embedded by different teams?
82D is the consensus space where ALL models agree. Project any embedding model's output to 82 dimensions. Your vectors become model-agnostic, permanent, and 18.7x smaller.
One API call: your vectors in → 82D consensus coordinates out. Works with OpenAI, Cohere, mxbai, nomic, and any other embedding model.
Proven: mxbai (1024D) ↔ nomic (768D) → identical 82D coordinates. 100% cross-model retrieval at convergence. Patents pending.
Every AI company charges you rent on your own knowledge.
Documents, code, conversations, research. Years of accumulated knowledge.
Pay OpenAI $0.13/1M tokens. Now you have 1536D vectors.
Pay again. Every query. Forever. Or store locally and hope they don't change the model.
text-embedding-ada-002 → deprecated. Re-embed everything. Pay again.
Project your embeddings from any model to 82D in one API call.
from eightytwo import Client
client = Client(api_key="your-key-here")
# Works with ANY embedding model
# OpenAI 1536D, Cohere 1024D, nomic 768D, etc.
vectors_1536d = openai_client.embeddings.create(...).data
vectors_82d = client.project(vectors_1536d)
# → model auto-detected from dimension
# Or specify the model explicitly
vectors_1024d = mxbai_client.embed(texts)
vectors_82d = client.project(vectors_1024d, model="mxbai-embed-large")
# Both land in the SAME 82D consensus space
# → directly comparable, permanently yours
print(f"Size: {1536*4}B → {82*4}B per vector = 18.7x smaller")Sign up to get your API key and endpoint URL.
# Project vectors to 82D consensus space
curl -X POST https://api.82d.ai/project \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"vectors": [[0.01, -0.02, ...1536 dims...]],
"model": "openai-3-small"
}'
# Response:
{
"vectors": [[0.04, 0.10, ...82 floats]],
"count": 1,
"input_dim": 1536,
"output_dim": 82,
"processing_time_ms": 0.3
}
# List supported models
curl https://api.82d.ai/modelsPaste 1536-dimensional vectors (from OpenAI, Cohere, etc.) to project to 82D.
Sign in above to enable live demo
$2.00 per GB sent. No subscriptions, no hidden fees.
First 10MB free. No subscription required.
Switch from OpenAI to Cohere: zero re-embedding. Your 82D vectors just work.
HIPAA-compliant. PHI never leaves your infrastructure.
SOX/PCI ready. Trade secrets stay secret.
Combine vectors from different teams and models into one searchable index.