> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ironlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Quickstart
> Make your first routed call in under 5 minutes.
**Renamed to `ironlabs` (June 15, 2026).** Both Node and Python packages are now `ironlabs`.
Migrating from `ironaai` / `ironlabsai`? Update your install + import. Your existing API key keeps working —
the SDK accepts `IRONLABS_API_KEY` (preferred), and falls back to `IRONLABS_AI_API_KEY` / `IRONAAI_API_KEY`
with a one-time deprecation warning.
## 1. Get your IronLabs API key
[Create an account](https://app.ironlabs.ai) or [log in](https://app.ironlabs.ai), then grab your API key from the **Settings → API Keys** page.
Treat your API key like a password. Never commit it to source control or expose it in client-side code.
## 2. Install the SDK
```bash Python theme={null}
pip install ironlabs
```
```bash Node.js theme={null}
npm install ironlabs
```
## 3. Make your first routed call
```python Python theme={null}
from ironlabs import IronLabs
client = IronLabs(api_key="your_ironlabs_api_key")
response = client.completions.create(
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Explain the golden ratio in two sentences."},
],
models=[
"openai/gpt-4o",
"anthropic/claude-3-5-sonnet-20240620",
"google/gemini-1.5-pro-latest",
],
tradeoff="latency",
)
print("Provider:", response.provider)
print("Model: ", response.model)
print("Output: ", response.content)
```
```typescript Node.js theme={null}
import { IronLabs } from 'ironlabs';
const client = new IronLabs({
apiKey: process.env.IRONLABS_API_KEY,
});
const result = await client.completions.create({
messages: [{ role: 'user', content: 'What is the golden ratio?' }],
llmProviders: [
{ provider: 'openai', model: 'gpt-4o-2024-05-13' },
{ provider: 'anthropic', model: 'claude-3-5-sonnet-20240620' },
{ provider: 'google', model: 'gemini-1.5-pro-latest' },
],
tradeoff: 'latency',
});
console.log('Provider:', result.provider);
console.log('Model: ', result.model);
console.log('Output: ', result.content);
```
### What you should see
```text theme={null}
Provider: anthropic
Model: claude-3-5-sonnet-20240620
Output: The golden ratio (≈1.618) is...
```
If `provider` and `model` are populated, the router worked — IronLabs picked a candidate from your `models` list, called it, and returned the response in one round trip.
## 4. Try a different tradeoff
Change `tradeoff` and watch the selected model change:
| Tradeoff | What it optimizes | Typical picks |
| ----------- | ------------------- | ------------------------------------------- |
| `"latency"` | Time-to-first-token | Smaller, faster models (Haiku, Flash, Mini) |
| `"cost"` | \$ per 1K tokens | Cheapest model that satisfies your task |
| `"quality"` | Benchmark score | Largest, most capable model |
## Next steps
See exactly what happens between request and response.
Train a router on your own data instead of using a pre-trained one.
Configure automatic retries across providers.
Every endpoint, every field.