Getting started with the model API
To connect to the MyGPTLife model API, have your platform token, base URL and the name of a model enabled for your account ready.
Base URL
The original connection guide lists https://api4.mygptlife.com/v1 as the compatible base URL. If your client appends /v1 automatically, check that the final URL contains it only once.
Your first request
Store your token in a server-side environment variable. Copy a model name from your account’s model list and send a short prompt. Find the request in your logs and check the time, model, input tokens and output tokens.
Troubleshooting
For an authentication error, check which account owns the token and confirm its balance. For a model error, check its full name and billing group. If you reach a rate limit, lower concurrency and allow time between retries.
