DrAI API Quickstart

Create your account & get an API key

Sign in to the DrAI dashboard with your email. Open API Keys and click Create key. Copy the key — it is shown only once.

Send your first request with curl

Open a terminal and run:

curl https://api.dr-ai.top/v1/chat/completions \
  -H "Authorization: Bearer $DRAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "messages": [
      {"role": "system", "content": "You are a concise assistant."},
      {"role": "user", "content": "Say hello in one sentence."}
    ],
    "max_tokens": 200
  }'

You should get a JSON response back in a second or two:

{
  "id": "chatcmpl-9xK2mQ7r...",
  "object": "chat.completion",
  "model": "gpt-5-mini",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! I'm here to help."
    },
    "finish_reason": "stop"
  }],
  "usage": {"prompt_tokens": 24, "completion_tokens": 9, "total_tokens": 33}
}

That is your first AI response. 🎉 Every other endpoint works the same way — see the API Reference.

Python SDK

The official openai package works unchanged — only the base_url changes.

pip install openai

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.dr-ai.top/v1",
)

resp = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is 12 * 12?"},
    ],
    temperature=0.7,
)
print(resp.choices[0].message.content)

Use env-style configuration in production: client = OpenAI(base_url="https://api.dr-ai.top/v1") with OPENAI_API_KEY exported — the SDK reads it automatically.

JavaScript / Node.js

The same one-line change applies to the official Node SDK:

npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-api-key",
  baseURL: "https://api.dr-ai.top/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-5-mini",
  messages: [{ role: "user", content: "Hello from Node.js!" }],
});
console.log(resp.choices[0].message.content);

Streaming is just as easy: add stream: true and iterate for await (const chunk of resp).

Next steps

• Pick the right model — browse the model catalog
• Stream responses — SSE streaming reference
• Handle errors properly — error code table
• Estimate costs — model price index