Step 1
Get the delivered credentials
After checkout, wait for manual provisioning. Your setup email includes the base URL, API key, setup files, and model IDs.
Integration
Swap base URL and keep the OpenAI-style SDK pattern.
unlimitedcodex is designed for OpenAI-compatible clients: keep familiar request shapes, set the delivered base URL and key, then validate models, chat, embeddings, and image endpoints.
- OpenAI-compatible client pattern
- Base URL and API key delivered after checkout
- Chat/completions, embeddings, model-list, images where supported
- Flat weekly or monthly access
Setup steps
Step 2
Change the SDK base URL
Keep your OpenAI-compatible request shape and change the client base URL to the delivered unlimitedcodex endpoint.
Step 3
Change the API key
Replace the direct provider key with your delivered unlimitedcodex key. Store it server-side and avoid exposing it in browser code.
Step 4
Run endpoint checks
Test /models, chat/completions, embeddings, image generation where supported, and retry behavior before a production-like run.
Example configuration
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.UNLIMITEDCODEX_API_KEY,
baseURL: process.env.UNLIMITEDCODEX_BASE_URL
});
const response = await client.chat.completions.create({
model: process.env.UNLIMITEDCODEX_MODEL!,
messages: [{ role: "user", content: "Run a small smoke test." }]
});FAQ
Do I need to rewrite my SDK calls?
Usually no. The normal migration pattern is to swap the API key, base URL, and model ID while keeping the OpenAI-compatible request shape.
What should I test first?
Test /models, chat/completions, embeddings, image generation where supported, streaming if your app uses it, and retry behavior under the 4 concurrent connection limit.
Does flat access mean no limits at all?
No. The package includes unlimited token consumption with a concrete operational limit of 4 concurrent connections.