Quickstart
Send your first GPT or Codex API request after setup delivery.
Create a workspace, choose Unlimited Weekly or Unlimited Monthly, complete payment, wait for manual delivery of your API key, base URL, setup files, and access dates, then send an OpenAI-compatible request.
Last updated: July 6, 2026. Example code uses a placeholder environment variable and assumes setup has already been delivered.
Before you start
Manual setup delivery begins after Stripe payment is complete.
Keep API keys in environment variables, not source code.
Use separate keys for development, staging, and production.
Plan for unlimited token consumption with 4 concurrent connections.
Review billing ownership before customer-facing rollout.
Setup path
Five steps from account to usage review.
Step 1
Create an account
Create your workspace, choose Unlimited Weekly or Unlimited Monthly, and complete Stripe payment before manual setup delivery begins.
Step 2
Receive API setup
After payment, admin prepares your OpenAI-compatible API key, base URL, setup files, activation date, start date, and end date for delivery in 10 minutes to 5 hours.
Step 3
Send the first request
Call the delivered unlimitedcodex base URL with a GPT-5.5 or Codex-style model value and keep the API key in an environment variable.
Step 4
Check usage
Review request logs, latency, status, unlimited token usage, 4-connection pressure, and rate-limit signals before traffic grows.
Step 5
Choose the next package
Use Unlimited Weekly for short access windows or Unlimited Monthly for ongoing work with a $59 first Monthly payment using reward code UNLIMITED59 when configured in Stripe.
Migration
Coming from OpenAI, Azure, or OpenRouter?
Keep your SDK and request bodies. After manual setup delivery, swap the base URL and API key, then use the GPT-5.5 and Codex model IDs from your setup email.
First request
Use the familiar chat completions shape.
Store the delivered key in `UCX_API_KEY`, send it as a Bearer token, and use the delivered base URL from trusted server-side code. Swap the model value between `gpt-5.5` and `codex` depending on the workload.
GPT-5.5 chat example
General reasoning, summarization, and product-facing chat flows.
const response = await fetch("https://unlimitedcodex.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.UCX_API_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "gpt-5.5",
messages: [
{
role: "user",
content: "Summarize the onboarding checklist in three bullets."
}
]
})
});
const result = await response.json();Codex coding example
Code generation, refactors, and agent workflows with a lower temperature default.
const response = await fetch("https://unlimitedcodex.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.UCX_API_KEY}`,
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "codex",
messages: [
{
role: "system",
content: "You are a precise coding assistant. Return only the code change."
},
{
role: "user",
content: "Write a TypeScript function that validates an OpenAI-compatible API key prefix."
}
],
temperature: 0.2
})
});
const completion = await response.json();Usage review
Open the dashboard to confirm status codes, latency, unlimited token usage, 4-connection pressure, and rate-limit signals after your first calls.
Launch guardrails
Use separate environment keys and rate-state checks before customer-facing traffic grows.
Billing next step
Move from Weekly to Monthly when access needs become ongoing, or request a walkthrough for unusual rollout needs.
Free tools
Try these before your first live request
Client-side helpers for migration, validation, quota planning, and 429 troubleshooting.
Migration Generator
Generate or transform OpenAI SDK snippets to unlimitedcodex base URL, keys, and scopes.
Request Validator
Validate chat, embeddings, and image JSON payloads against unlimitedcodex OpenAI-compatible rules.
429 Decoder
Paste a 429 response body and headers to classify rate-limit vs quota pressure and see retry guidance.
Scope Configurator
Select workloads and output least-privilege scopes, .env.example, and a rotation checklist.
Rate Limit Planner
Plan backoff settings and quota monitoring checklist from expected RPS and team size.
Preparing for production?
Move from first request to a controlled rollout.
Review usage visibility, 4 concurrent connections, package fit, billing ownership, and security posture before customer-facing traffic grows.