OpenAI API Access — No OpenAI Account, Pay-as-You-Go
Access the OpenAI API through LLMsRelay with a Codex-group key, OpenAI-compatible endpoints, the latest OpenAI models, and pay-as-you-go billing.
Base URL: https://api.llmsrelay.com/v1. Endpoints: /v1/chat/completions, /v1/responses. API key: sk-cs4-* (Codex group). Billing: Pay-as-you-go credits.
TL;DR
LLMsRelay gives you OpenAI API access through the same account and credits you use for Claude. Select the Codex group on the key and call the OpenAI-compatible endpoints at
https://api.llmsrelay.com/v1.Choose the correct key group
Use a key in the Codex group for OpenAI/GPT models and
/v1/chat/completions or /v1/responses. Use Basic or Profor Claude/Anthropic models. The balance is shared by the account, but the key's active group controls which model family it can call.Why LLMsRelay for the OpenAI API
- No OpenAI account — no separate signup, no organization verification, no waitlist.
- Latest OpenAI models — request the current models (e.g.
gpt-5.5); callGET /v1/modelsfor the live list. - Correct routing — use Basic/Pro keys for Claude and Codex keys for OpenAI/GPT models.
- Fully OpenAI-compatible — Chat Completions and Responses APIs, OpenAI SDK, Codex CLI, and OpenAI-compatible IDEs.
- Shared billing — use one-time credits across Claude and OpenAI-compatible models.
Quick start
OpenAI SDK against LLMsRelaypython
from openai import OpenAI
client = OpenAI(
api_key="sk-cs4-your-key",
base_url="https://api.llmsrelay.com/v1",
)
resp = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Write a haiku about TCP."}],
)
print(resp.choices[0].message.content)Where to go next
- Codex CLI & Extension — Responses API setup.
- OpenAI-Compatible IDEs — Cline, Roo, Continue.
- OpenAI & Codex API Reference — endpoints, models, billing.