⚡ Vella Quant

Sovereign, OpenAI-compatible inference — served from owned Apple-Silicon hardware.

Drop-in compatible with the OpenAI SDK. Pay per token in fiat or Lightning. No lock-in, no data resale, self-custodied.

$0.40

chat / 1M tokens

$0.02

embeddings / 1M tokens

$0.05

AI market briefing / call

Products

Chat — OpenAI-compatible /v1/chat/completions, served from Llama-3.2-3B-Instruct-4bit.
Embeddings — /v1/embeddings for search, RAG, clustering.
Hosted search / RAG — /v1/documents + /v1/search: private per-key vector store with semantic retrieval. No infra to run.
AI market briefings — /v1/briefing: live signals + an analyst narrative.

Quickstart

curl https://api.vellaquant.com/v1/chat/completions \
  -H "Authorization: Bearer $VELLA_KEY" \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"Hello"}]}'

curl https://api.vellaquant.com/v1/embeddings \
  -H "Authorization: Bearer $VELLA_KEY" \
  -d '{"input":"text to embed"}'

Get credit

Top up an API key (card via Stripe, or a Lightning invoice):

curl https://api.vellaquant.com/v1/checkout \
  -H "Content-Type: application/json" \
  -d '{"api_key":"vq-…","amount_usd":10}'

Request an API key →