For trying the API and small scripts.
- Fixed prepaid balance
- Full live OpenRouter catalog
- OpenAI-compatible endpoint
- Transparent 20% markup
Vlad mirrors OpenRouter's live model catalog every five minutes. Buy a fixed balance and use new models as they appear, at upstream cost plus a clear 20% service markup.
curl https://vlad.unicornco.fun/api/v1/chat/completions \
-H "Authorization: Bearer $VLAD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-4.1-mini",
"messages": [{"role": "user", "content": "Ship it."}],
"max_tokens": 512
}'The newest catalog entries are pulled directly from OpenRouter. Customer rates below include Vlad's 20% service markup.
* Per-million-token customer rates calculated from OpenRouter's current per-token prices × 1.20. Provider pricing and availability can change.
$10 purchases $10 of Vlad balance. Each call deducts 120% of OpenRouter's reported cost. Example: $1.00 upstream usage deducts $1.20.
For trying the API and small scripts.
For prototypes and regular development.
For measured production beta traffic.
Non-streaming onlyStreaming requests are rejected during beta.
4,096 output token capSpend is bounded per call; body size is capped at 1 MB.
Upstream availability appliesModels follow OpenRouter's live catalog and can change or become temporarily unavailable.
Single-instance ledgerStripe metadata is the beta balance ledger; concurrent requests with one key are not supported.