> ## Documentation Index
> Fetch the complete documentation index at: https://docs.uncensoredgpt.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Send your first request to the UncensoredGPT API in about two minutes.

This quickstart gets you from zero to your first response from the UncensoredGPT API.

**1. Create an API key**

Sign in to the [UncensoredGPT Console](https://console.uncensoredgpt.ai), open the **Keys** page, and create a key. Copy it — it is shown only once.

**2. Point your code at the gateway**

The base URL is:

```
https://api.uncensoredgpt.ai
```

Every endpoint follows the OpenAI API specification, so any OpenAI-compatible SDK works unchanged — set the base URL and your key.

**3. Make a request**

```bash theme={null}
curl -X POST https://api.uncensoredgpt.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $UNCENSOREDGPT_API_KEY" \
  -d '{
    "model": "uncensoredgpt/qwen3.8-27b-uncensored",
    "messages": [
      {"role": "user", "content": "Hello, what can you do?"}
    ]
  }'
```

You get a normal chat completion response:

```json theme={null}
{
  "id": "chatcmpl-abc123",
  "model": "uncensoredgpt/qwen3.8-27b-uncensored",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hi! I can answer anything you ask..."
      }
    }
  ],
  "usage": {"prompt_tokens": 17, "completion_tokens": 42, "total_tokens": 59}
}
```

## What's next?

* See every model in the [catalog](https://docs.uncensoredgpt.ai/api-reference/models.md) — switch models by changing the `model` field.
* Connect a coding agent: [OpenCode](https://docs.uncensoredgpt.ai/api-reference/agents/opencode.md), [Pi](https://docs.uncensoredgpt.ai/api-reference/agents/pi.md), [Claude Code](https://docs.uncensoredgpt.ai/api-reference/agents/claude-code.md), or [any other](https://docs.uncensoredgpt.ai/api-reference/agents.md).
* Turn on [streaming](https://docs.uncensoredgpt.ai/api-reference/endpoints/chat/create-chat-completion.md) for real-time responses.
* Check your tokens and costs on the Console's [Usage](https://docs.uncensoredgpt.ai/console/usage.md) page.

> [!TIP]
>
> Prefer a web UI? [UncensoredGPT Chat](https://chat.uncensoredgpt.ai) runs on the same models — see the [Getting Started](https://docs.uncensoredgpt.ai/interface/getting-started.md) guide. Your API usage and your chat share the same platform.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.