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

# Quickstart

Choose your path. You can use Decentral as a user, a developer, or a provider. All three are available from day one with no account required beyond a Solana wallet.

***

## As a user: get your first inference

**What you need:** Any Solana wallet (Phantom, Backpack, Solflare) with a small USDC balance.

**Time required:** Under 5 minutes.

**1. Connect your wallet**

Go to [usedecentral.org/app](https://usedecentral.org/app) and click "Connect wallet." No email, no sign-up form, nothing else.

**2. Buy credits**

Credits are the unit of account for inference jobs. One credit equals $0.01 USDC. You can fund as little as $1 to start.

Click "Add credits," choose an amount, and approve the USDC transaction from your wallet. Credits are immediately available.

**3. Choose a model and start chatting**

Pick a model from the list. If you are not sure, start with **Qwen3 8B** (Standard tier, 8 credits per request). It is fast, capable, and available across multiple worker nodes at all times.

Type a message and submit. Your prompt is encrypted before it leaves your browser. The job routes to an available worker, runs inference, and streams the response back to you.

That is the complete flow. Nothing was logged. The job payment settled on Solana.

***

## As a developer: call the API

**What you need:** A Solana wallet with USDC, and an API key from the dashboard.

**Time required:** Under 10 minutes.

**1. Get an API key**

Sign in at [usedecentral.org/app](https://usedecentral.org/app), go to Settings, and generate an API key. Keys are in the format `dcntrl_live_...` and are linked to your wallet's credit balance.

**2. Make your first request**

The Decentral API is OpenAI-compatible. If you are already using the OpenAI SDK, change one line:

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.usedecentral.org/v1",
    api_key="dcntrl_live_your_key_here"
)

response = client.chat.completions.create(
    model="llama-3.3-70b",
    messages=[{"role": "user", "content": "Explain Solana's proof of history in plain terms."}],
    stream=True
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="", flush=True)
```

```typescript
import OpenAI from "openai"

const client = new OpenAI({
    baseURL: "https://api.usedecentral.org/v1",
    apiKey: "dcntrl_live_your_key_here"
})

const stream = await client.chat.completions.create({
    model: "qwen3-8b",
    messages: [{ role: "user", content: "What is a Solana PDA?" }],
    stream: true
})

for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content ?? "")
}
```

**3. Check your on-chain receipt**

Every API call generates a Solana transaction. The response headers include `x-decentral-job-id` and `x-decentral-tx-signature`. You can verify the payment on any Solana explorer.

***

## As a provider: start earning

**What you need:** A WebGPU-capable browser (Chrome 113+) and a Solana wallet. No USDC required to start as a browser worker.

**Time required:** Under 5 minutes.

**Browser worker (zero friction)**

1. Go to [usedecentral.org/app](https://usedecentral.org/app) and click "Earn."
2. Connect your wallet.
3. The page detects your browser's WebGPU support and available VRAM.
4. Select a compatible model from the list.
5. Click "Start Earning."

Jobs begin routing to you within seconds. USDC is credited to your wallet after each completed job. You can close the tab at any time.

**Native worker (higher earnings)**

See the full \[Native Worker guide]\(

) for installation and configuration. Native workers earn more per job, support larger models, and qualify for the staking multiplier that raises your payout share from 75% to 85%.

***

## Available models at launch

| Model         | Tier     | Cost per request   | VRAM required |
| ------------- | -------- | ------------------ | ------------- |
| Llama 3.3 70B | Max      | 40 credits ($0.40) | 48GB+         |
| DeepSeek R1   | Max      | 40 credits ($0.40) | 48GB+         |
| Qwen3 8B      | Standard | 8 credits ($0.08)  | 8GB+          |
| Mistral 7B    | Standard | 8 credits ($0.08)  | 8GB+          |
| Llama 3.2 3B  | Lite     | 2 credits ($0.02)  | 4GB+          |
| Qwen3 1.7B    | Lite     | 2 credits ($0.02)  | 3GB+          |

Long-form completions billed over approximately 500 output tokens are charged per 1,000 output tokens rather than per request.

***

## Next steps

* \[Core Concepts]\() to understand how the network works end to end
* \[API Reference]\() for endpoint documentation
* \[Providers: Browser Worker]\() for browser setup details
* \[Providers: Native Worker]\() for the full native setup guide
* \[Staking]\() to unlock the 85% payout multiplier


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.usedecentral.org/quickstart.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.