# APIKO

> APIKO is an OpenAI-compatible AI gateway: one API key calls many AI models across providers, with automatic retry/failover, usage-based billing from real token counts, and automatic refunds for failed calls.

## Quickstart

1. Create an account and an API key at /settings/apikeys (the full `sk-...` key is shown once).
2. Point your OpenAI SDK at the gateway:
   - base URL: `https://api.gateway.example/v1`
   - auth header: `Authorization: Bearer <your APIKO_API_KEY>`
3. Call `POST /chat/completions` with any model from /models. Streaming is supported via `"stream": true` (+ `"stream_options": {"include_usage": true}` for usage in the final chunk).

Example:

```bash
curl https://api.gateway.example/v1/chat/completions \
  -H "Authorization: Bearer $APIKO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "gpt-4o-mini", "messages": [{"role": "user", "content": "Hello"}]}'
```

## Billing

- New accounts receive trial credit automatically on signup — no credit card required.
- Usage-based: each request settles from the provider's real input/output token counts at the per-model prices listed on /pricing.
- A pre-hold is taken when a request starts and adjusted at settlement; failed upstream calls are refunded automatically.
- Common error code: `insufficient_user_quota` → add credit in Console → Billing.

## Pages

- /models — live model catalog with per-1M-token prices
- /pricing — billing explainer + full price table
- /status — real-time model availability
- /docs — full API reference and quickstart
- /blog — articles and release notes
- /settings — developer console (keys, usage logs, playground, billing)