GC4.AI
Convert a card
Developers

Change one line.
Keep your code.

The endpoint is OpenAI-compatible: point your existing SDK at api.gc4.ai and your gift-card balance pays for every model.

Email-only account · No credit card · Ever
Get a keyQuickstart
api.gc4.ai
-base_url="https://api.openai.com/v1"+base_url="https://api.gc4.ai/v1"
That's the whole migration. 39 models, one balance,per-token prices mirrored from openrouter.ai.
Quickstart

200 on the first paste.

The snippets below carry a placeholder key. Grab a real one — it's email-only, no card — then paste it in and run.

Get a key
gc4_sk_live_xxxxxxxxxxxxxxxxxxxxxxxx
quickstart.gc4.ai
1from openai import OpenAI
2 
3client = OpenAI(
4    base_url="https://api.gc4.ai/v1",
5    api_key="gc4_sk_live_xxxxxxxxxxxxxxxxxxxxxxxx",  # replace with your key
6)
7 
8r = client.chat.completions.create(
9    model="anthropic/claude-haiku-4.5",
10    messages=[{"role": "user", "content": "Say hi in 5 words."}],
11)
12print(r.choices[0].message.content)
Copy the Python snippet
Expected response
{
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hi there, five words exactly."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 8,
    "cost_usd": 0.000053
  }
}
First request detected21 tokens · $0.000053 · ledgered in your account
Errors

Every error you'll meet.

An empty balance is a hard stop: there is no overdraft and no negative balance, ever. Limits are 60 requests a minute per key. Upstream provider errors pass through unchanged in OpenAI-compatible format.

401Bad or revoked key
{ "error": { "code": "invalid_key", "message": "Key not recognized. Check for whitespace." } }
404Model id not on the ledger (typo'd slug)
{ "error": { "code": "model_not_found", "message": "No model anthropic/claude-haiku-45. Did you mean anthropic/claude-haiku-4.5?" } }
402Balance empty: hard stop, never overdraft
{ "error": { "code": "balance_empty", "message": "Balance is $0.00. Convert a card at gc4.ai/convert.", "convert_url": "https://gc4.ai/convert" } }
429Rate limited: 60 req/min per key
{ "error": { "code": "rate_limited", "message": "60 requests/min exceeded. Retry after 2.1s.", "retry_after": 2.1 } }