First API request

Use the API shape you already have. Point it at the production API and choose a chat or reasoning model id from the live model catalog.

OpenAI — Node.js

import OpenAI from "openai";
 
const client = new OpenAI({
  apiKey: process.env.TOKENER_API_KEY,
  baseURL: "https://api.tokener.ai/v1",
});
 
const completion = await client.chat.completions.create({
  model: "YOUR_MODEL_ID",
  messages: [
    { role: "user", content: "Summarize Tokener.ai in one sentence." },
  ],
});
 
console.log(completion.choices[0]?.message.content);

OpenAI — Python

import os
 
from openai import OpenAI
 
client = OpenAI(
    api_key=os.environ["TOKENER_API_KEY"],
    base_url="https://api.tokener.ai/v1",
)
 
completion = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Summarize Tokener.ai in one sentence."}],
)
 
print(completion.choices[0].message.content)

Anthropic — Messages

curl https://api.tokener.ai/v1/messages \
  -H "x-api-key: $TOKENER_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"YOUR_MODEL_ID","max_tokens":256,"messages":[{"role":"user","content":"Summarize Tokener.ai in one sentence."}]}'