> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Quickstart

> Make your first Electron chat completion in under 60 seconds - point the OpenAI SDK at Smallest AI and go.

Electron is **OpenAI-compatible**. If you can call the OpenAI Chat Completions API, you can call Electron - change the base URL and the API key, and your existing code works.

## Step 1: Get Your API Key

In the [Smallest AI Console](https://app.smallest.ai/dashboard/api-keys?utm_source=documentation\&utm_medium=llm), go to **Settings → API Keys** and click **Create API Key**. Copy it and export:

```bash
export SMALLEST_API_KEY="your-api-key-here"
```

> **Tip**
>
> New to Smallest AI? [Sign up here](https://app.smallest.ai?utm_source=documentation\&utm_medium=llm) first.

## Step 2: Make Your First Call

Paste this cURL - no install required:

```bash
curl -X POST "https://api.smallest.ai/waves/v1/chat/completions" \
  -H "Authorization: Bearer $SMALLEST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "electron",
    "messages": [
      {"role": "user", "content": "Write one sentence about why the sky is blue."}
    ]
  }'
```

You'll get back the standard OpenAI chat-completion shape:

```json
{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "electron",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The sky appears blue because shorter blue wavelengths of sunlight scatter more than longer wavelengths when they pass through Earth's atmosphere."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 24,
    "total_tokens": 41
  }
}
```

## Step 3: Use the OpenAI SDK

Because Electron speaks the OpenAI wire format, you can use the official OpenAI SDKs verbatim - just override `base_url` (or `baseURL`) and `api_key`.

Install the SDK if you don't already have it:

```bash
pip install openai          # Python
# or
npm install openai          # Node.js
```

**`Python`**

```python Python
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.smallest.ai/waves/v1",
    api_key=os.environ["SMALLEST_API_KEY"],
)

response = client.chat.completions.create(
    model="electron",
    messages=[
        {"role": "user", "content": "Write one sentence about why the sky is blue."}
    ],
)

print(response.choices[0].message.content)
```

**`JavaScript`**

```javascript JavaScript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.smallest.ai/waves/v1",
  apiKey: process.env.SMALLEST_API_KEY,
});

const response = await client.chat.completions.create({
  model: "electron",
  messages: [
    { role: "user", content: "Write one sentence about why the sky is blue." },
  ],
});

console.log(response.choices[0].message.content);
```

**`cURL`**

```bash cURL
curl -X POST "https://api.smallest.ai/waves/v1/chat/completions" \
  -H "Authorization: Bearer $SMALLEST_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "electron",
    "messages": [
      {"role": "user", "content": "Write one sentence about why the sky is blue."}
    ]
  }'
```

## What's next

#### [Streaming](/models/llm/streaming)

Get tokens as they're generated. Set `stream: true` for SSE.

#### [Tool Calling](/models/llm/tool-function-calling)

Use Electron for agents - it returns OpenAI-style `tool_calls` and is trained to handle voice-agent flows.

#### [Prefix Caching](/models/llm/prefix-caching)

Cached input tokens are billed at a discounted rate. Structure your prompts to hit the cache.

#### [Migrate from OpenAI](/models/llm/migrate-from-open-ai)

Side-by-side diff: what changes when you switch from `api.openai.com`.

> Make your first Electron chat completion in under 60 seconds - point the OpenAI SDK at Smallest AI and go.