# Quickstart

Get an API key and send your first request with curl, Python or Node.js.

## 1. Get an API key

Sign in with your Nodul account, create a Router space and an API key in it. The key is shown once: save it in an environment variable.

```bash
export NODUL_ROUTER_API_KEY="sk-nr-..."
```

Requests are billed in PnP to the payer of the space: make sure the payer's Nodul space has a positive PnP balance.

## 2. Send a request

Pick a model in the [catalog](/models) and send a chat completion. Choose a model below to update the examples.

```bash
curl https://router.nodul.ru/api/v1/chat/completions \
  -H "Authorization: Bearer $NODUL_ROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-3-4b-it",
    "messages": [{"role": "user", "content": "Say hello in one short sentence."}]
  }'
```

```python
import os
from openai import OpenAI

client = OpenAI(base_url="https://router.nodul.ru/api/v1", api_key=os.environ["NODUL_ROUTER_API_KEY"])
completion = client.chat.completions.create(
    model="google/gemma-3-4b-it",
    messages=[{"role": "user", "content": "Say hello in one short sentence."}],
)
print(completion.choices[0].message.content)
```

```js
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://router.nodul.ru/api/v1", apiKey: process.env.NODUL_ROUTER_API_KEY });
const completion = await client.chat.completions.create({
  model: "google/gemma-3-4b-it",
  messages: [{ role: "user", content: "Say hello in one short sentence." }],
});
console.log(completion.choices[0].message.content);
```

## 3. Read the response

The response is an OpenAI chat completion. Two fields matter for the router:

- `id` is the generation id (`gen-…`): look the request up with `GET /api/v1/generation?id=…` or in the cabinet logs.
- `usage.cost` is the amount charged for the request, in PnP.

```json
{
  "id": "gen-5d0c3b6e-…",
  "object": "chat.completion",
  "model": "google/gemma-3-4b-it",
  "provider": "Google",
  "choices": [{ "index": 0, "finish_reason": "stop", "message": { "role": "assistant", "content": "Hello there!" } }],
  "usage": { "prompt_tokens": 14, "completion_tokens": 4, "total_tokens": 18, "cost": 0.000012 }
}
```

> **Warning:** Without `max_tokens` the answer is limited to 4096 tokens and a longer one ends with `finish_reason: "length"`. Set `max_tokens` when you expect long answers.