Quickstart

Follow the steps below to complete registration and call your first AI API within five minutes.

Visit https://t.ato2.nodesms.com, complete registration, and log in to your account.

Create an API Key

Go to the Token Management page, click Create Token, set a name and quota for the Key, and save. Copy the API Key starting with sk- and keep it secure.

Send your first request

Open a terminal, copy the following cURL command, replace $API_KEY with your Key, and send your first chat request:

curl -X POST https://t.ato2.nodesms.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

If everything works, you will receive a JSON response containing the model reply.

Use in Code

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://t.ato2.nodesms.com/v1",
)

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-xxx",
  baseURL: "https://t.ato2.nodesms.com/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

Use in Third-Party Clients

The following clients all support OpenAI-compatible APIs. Simply fill in the API address and Key to use them:

Client	How to fill in the API address
Cherry Studio	Model Service -> Add Provider -> OpenAI, Base URL: `https://t.ato2.nodesms.com/v1`
LobeChat	Settings -> Language Model -> OpenAI, API proxy address: `https://t.ato2.nodesms.com/v1`
NextChat	Settings -> Custom Interface, interface address: `https://t.ato2.nodesms.com`, API Key: your Key

Some clients include the /v1 suffix when entering the address. If the connection fails, try switching between addresses with and without /v1.

The gpt-4o-mini in the examples is for demonstration only. For actual available models, query the Models endpoint.

Next Steps

View the Integration Guide to learn about endpoint addresses, authentication, and error handling.
Browse all APIs under “AI Model APIs” on the left and test them online on each page.

Last modified on October 28, 2026

Getting started

AI model APIs

Use in Code

Use in Third-Party Clients

Next Steps

​Use in Code

​Use in Third-Party Clients

​Next Steps

Use in Code

Use in Third-Party Clients

Next Steps