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

# LLM Access

RelytONE provides seamless access to OpenAI's latest language models including GPT-4o-mini and GPT-5-mini through a simple, OpenAI-compatible API proxy. Use your existing OpenAI integrations by simply pointing to RelytONE's base URL and authenticating with your Personal API Key.

## Quick Example

<CodeGroup>
  ```bash curl theme={null}
  curl -X POST https://relytone.data.cloud/api/v1/llm-proxy/v1/chat/completions \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "gpt-4o-mini",
      "messages": [
          {
              "role": "system",
              "content": "You are a helpful assistant."
          },
          {
              "role": "user",
              "content": "Introduce yourself."
          }
      ]
  }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="<token>",
      base_url="https://relytone.data.cloud/api/v1/llm-proxy/v1/"
  )

  response = client.chat.completions.create(
      model="gpt-4o-mini",
      messages=[
          {
              "role": "system",
              "content": "You are a helpful assistant."
          },
          {
              "role": "user",
              "content": "Introduce yourself."
          }
      ]
  )

  print(response.choices[0].message.content)
  ```
</CodeGroup>

## Base URL

```
https://relytone.data.cloud/api/v1/llm-proxy/v1/
```

## Authentication

Use your Personal API Key as the bearer token. See [Manage API Key](/api/api-key) for details.

## Available Models

* `gpt-4o-mini` - GPT-4 Optimized Mini
* `gpt-5-mini` - GPT-5 Mini

More models will be released progressively to expand your options.

## Pricing & Usage Limits

The LLM API is **free for all users** with daily usage limits. We're committed to enhancing your experience by gradually increasing usage limits over time.