> For the complete documentation index, see [llms.txt](https://docs.nebulablock.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nebulablock.com/getting-started/get-started/quickstart.md).

# Quickstart

Create an account, add credit, get an API key, and make your first inference call in about five minutes.

Make your first inference call in about five minutes.

## 1. Create an account

[Sign up](https://console.nebulablock.com/register) and confirm your email address. See [Account](/getting-started/get-started/account.md) for details on activation, profile settings, and password resets.

## 2. Add credit

Serverless inference is pay-as-you-go, and **Tier 1 (free) accounts have a daily request cap of 0 on most models**. A $5 deposit moves you to Tier 2 and opens up the catalog; $10 also unlocks GPU instances.

Add credit under [Billing](https://console.nebulablock.com/billing) in the console. See [Tiers and Rate Limits](/account/tiers-and-limits.md) for exactly what each tier unlocks.

## 3. Create an API key

Go to [API Keys](https://console.nebulablock.com/apiKeys) in the console and create a key, then copy it. You can reveal and copy it again later from the same page, but treat it like a password all the same.

```bash
export NEBULA_API_KEY="sk-..."
```

See [API Keys](/account/api-keys.md) for rotation and team keys.

## 4. Make your first call

The Inference API is OpenAI-compatible, so any OpenAI SDK works by changing the base URL.

### Using cURL

```bash
curl https://inference.nebulablock.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NEBULA_API_KEY" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V3.2",
    "messages": [{"role": "user", "content": "Explain what an inference endpoint is, in two sentences."}]
  }'
```

### Using Python

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://inference.nebulablock.com/v1",
    api_key=os.environ["NEBULA_API_KEY"],
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",
    messages=[{"role": "user", "content": "Explain what an inference endpoint is, in two sentences."}],
)
print(response.choices[0].message.content)
```

### Using JavaScript

```javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://inference.nebulablock.com/v1",
  apiKey: process.env.NEBULA_API_KEY,
});

const response = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V3.2",
  messages: [{ role: "user", content: "Explain what an inference endpoint is, in two sentences." }],
});
console.log(response.choices[0].message.content);
```

Swap `model` for any ID from the [Model Catalog](/products/serverless-inference/model-catalog.md).

## Where to go next

| Goal                                       | Guide                                                                                                                                           |
| ------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------- |
| Stream responses, use tools, tune sampling | [Text Generation](/products/serverless-inference/text-generation.md)                                                                            |
| Send images to a model                     | [Vision](/products/serverless-inference/vision.md)                                                                                              |
| Generate images or video                   | [Image Generation](/products/serverless-inference/image-generation.md) · [Video Generation](/products/serverless-inference/video-generation.md) |
| Build RAG                                  | [Embeddings](/products/serverless-inference/embeddings.md) · [Reranking](/products/serverless-inference/reranking.md)                           |
| Rent a GPU                                 | [GPU Cloud Quickstart](/products/gpu-cloud/quickstart.md)                                                                                       |
| Store datasets                             | [Object Storage Quickstart](/products/object-storage/quickstart.md)                                                                             |

## See also

* [Products](/getting-started/get-started/products.md)
* [API Reference](/api-reference/api-reference.md)
* [FAQ](/resources/faq.md)