Use TokenRex with API Integration

Connect your own application using HTTP or the OpenAI Python SDK.

These examples use TokenRex's documented Chat Completions endpoint. SDK and app-specific tool behavior should be tested separately.

Before you start

A TokenRex API key
An enabled model ID
A private server or local development environment

Setup methods

Direct HTTP request

1.
Create a TokenRex API key and store it privately in TOKENREX_API_KEY.
2.
Copy an enabled model ID from Models & Pricing and use the Chat Completions request below.
3.
Read choices[0].message.content and confirm the selected model in your usage. Do not put a private key in browser code or a public repository.

Configuration

bash

curl https://tokenrex.ai/api/public/v1/chat/completions \
  -H "Authorization: Bearer $TOKENREX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"openai/gpt-6-astra","messages":[{"role":"user","content":"Reply with a short greeting."}]}'

Setup reference

OpenAI Python SDK

1.
Install openai in your Python environment and set TOKENREX_API_KEY privately.
2.
Set base_url to the versioned TokenRex URL, then call chat.completions.create with an enabled model ID.
3.
Keep requests on your server or local environment; do not expose the key to visitors.

Configuration

python

import os
from openai import OpenAI

client = OpenAI(base_url="https://tokenrex.ai/api/public/v1", api_key=os.environ["TOKENREX_API_KEY"])
response = client.chat.completions.create(
    model="openai/gpt-6-astra",
    messages=[{"role": "user", "content": "Reply with a short greeting."}],
)
print(response.choices[0].message.content)

Setup reference

Verify the connection

Send a short message with the selected model, read its response, then confirm the exact model appears in your TokenRex usage. Test streaming and tool use separately before larger agent tasks.