DEV Community

lili hami
lili hami

Posted on Originally published at apiclan.us

Point the OpenAI SDK at an OpenAI-compatible gateway in 3 steps

#openai #devops #api #ai

Most teams don't need a new SDK for every model. They need a single OpenAI-compatible endpoint and a clean baseURL.

The 3 steps

  1. Create an API key on your gateway.
  2. Point the OpenAI SDK at the gateway base URL (usually ending in /v1).
  3. Keep the rest of your code β€” chat completions, streaming, tools. Swap the model string when you want GPT, Claude, or Grok. 
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_KEY",
    base_url="https://YOUR_GATEWAY/v1",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",  # or a Claude / Grok id your gateway exposes
    messages=[{"role": "user", "content": "ping"}],
)
print(resp.choices[0].message.content)
Enter fullscreen mode Exit fullscreen mode

Footgun: Claude Code vs OpenAI clients

  • OpenAI SDK / most OpenAI-compatible clients want the base URL with /v1.
  • Claude Code / Anthropic-style clients often want the base URL without /v1 (they append /v1/messages themselves).

If Claude Code 404s on /v1/v1/messages, you double-prefixed the path β€” not an auth bug.

Longer walkthrough: OpenAI-compatible API guide and the short getting started guide.

What to actually test

Don't only hit chat completions. Check streaming, tool/function calls, long context, and the clients you really use (Claude Code, Codex, Cherry Studio). If those break, "compatible" is marketing.

Cost framing for agents

List $/1M tokens is a vanity metric. Retries, timeouts, and tool failures dominate. Measure cost per successful task.

If you want a managed OpenAI-compatible gateway for GPT / Claude / Grok: APICLAN β€” signup auto-credits $0.20 so you can make a real call, not a fake demo. USDT wallet top-ups; no card data stored.

Top comments (0)