myopenai
DocsSign inGet started

OpenAI-compatible API gateway
with hard spend caps.

Point any OpenAI SDK at https://myopenai.site/v1, use an mo_live_ key, and set a dollar cap per key. A request that could push the key past its cap is refused with HTTP 402 before the upstream model is called — so the blocked request costs nothing.

Create an accountRead the docs

The 402 promise

A standard request through the gateway:

curl https://myopenai.site/v1/chat/completions \
  -H "Authorization: Bearer mo_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [
      {"role":"user","content":"Hello"}
    ]
  }'

When the request could exceed the key’s cap, before any upstream call:

HTTP/2 402

{
  "error": {
    "message": "api key spend cap exceeded: cap_micros=5000000 spent_micros=4990000 required_micros=57036 cap_window=month",
    "type": "cap_exceeded",
    "code": "cap_exceeded"
  }
}

How it works

01

Buy prepaid credit

Credit is purchased up front and consumed per token. It never expires. No subscription, no monthly minimum.

02

Create a key with a cap

Each API key has its own dollar cap — daily, monthly, or total. Multiple keys means multiple isolated budgets.

03

Point your SDK and ship

Change one line: set base_url to https://myopenai.site/v1. Chat completions, streaming, tool calling and model listing work with the standard OpenAI SDKs.

Models & pricing

What you pay per million tokens, in US dollars, deducted from your prepaid credit using the token counts the model reports. See the docs for how holds and spend caps work.

Loading current models and prices…