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. When the cap is hit we return HTTP 402 before the upstream call is made — so you pay nothing for the blocked request.

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 spend cap is exceeded, before any upstream call:

HTTP/2 402

{
  "error": {
    "message": "api key spend cap exceeded: cap $5.00, spent $5.00",
    "type": "invalid_request_error"
  }
}

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. The SDK doesn’t know the difference.

Models & pricing

Pass-through pricing. We charge exactly what the upstream provider charges — no markup.

ModelProviderInput / 1M tokensOutput / 1M tokens
gpt-5.5OpenAI$6.00$36.00
claude-opus-5Anthropic$6.00$30.00
claude-sonnet-5Anthropic$2.64$13.20
claude-haiku-4-5Anthropic$1.20$6.00