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

# Key Concepts

> Core terminology and concepts on Runcrate.

export const RuncrateStyles = () => {
  if (typeof document !== 'undefined' && !document.getElementById('runcrate-overrides')) {
    const s = document.createElement('style');
    s.id = 'runcrate-overrides';
    s.textContent = `
      /* Match Runcrate's rounding scale (--radius: 0.75rem) */
      .rounded-sm { border-radius: 0.5rem !important; }   /* 8px */
      .rounded-md { border-radius: 0.625rem !important; } /* 10px */
      .rounded-lg { border-radius: 0.75rem !important; }  /* 12px */
      .rounded-l-sm { border-top-left-radius: 0.5rem !important; border-bottom-left-radius: 0.5rem !important; }
      .rounded-r-sm { border-top-right-radius: 0.5rem !important; border-bottom-right-radius: 0.5rem !important; }
      .rounded-l-md { border-top-left-radius: 0.625rem !important; border-bottom-left-radius: 0.625rem !important; }
      .rounded-r-md { border-top-right-radius: 0.625rem !important; border-bottom-right-radius: 0.625rem !important; }
      .rounded-l-lg { border-top-left-radius: 0.75rem !important; border-bottom-left-radius: 0.75rem !important; }
      .rounded-r-lg { border-top-right-radius: 0.75rem !important; border-bottom-right-radius: 0.75rem !important; }

      /* Cards: never pure white in light mode */
      .card { background-color: #fcfcfc !important; border-radius: 0.75rem !important; }
      html.dark .card { background-color: #141414 !important; }

      /* Docs hero box */
      .rc-hero { background-color: #fcfcfc; border: 1px solid #e0e0e0; }
      html.dark .rc-hero { background-color: #141414; border-color: #242424; }
      html.dark .rc-hero h1 { color: #f5f5f5; }

      /* Runcrate scrollbar — thin, transparent track, hide-until-hover thumb */
      ::-webkit-scrollbar { width: 6px; height: 6px; background-color: transparent; }
      ::-webkit-scrollbar-track { background-color: transparent; }
      ::-webkit-scrollbar-thumb { background-color: rgba(155, 155, 155, 0.5); border-radius: 10px; transition: opacity 0.3s ease; opacity: 0; }
      ::-webkit-scrollbar-thumb:hover { background-color: rgba(155, 155, 155, 0.7); }
      *:hover::-webkit-scrollbar-thumb,
      *:focus::-webkit-scrollbar-thumb,
      *:active::-webkit-scrollbar-thumb { opacity: 1; }
      * { scrollbar-width: thin; scrollbar-color: rgba(155, 155, 155, 0.5) transparent; }
    `;
    document.head.appendChild(s);
  }
  return null;
};

<RuncrateStyles />

## Models API

An OpenAI-compatible REST API at `https://api.runcrate.ai/v1` that gives you access to 140+ open-source models. Use the same OpenAI SDKs you already know — just change the base URL and API key.

### Model Categories

| Category      | Endpoint                   | Description                                  |
| ------------- | -------------------------- | -------------------------------------------- |
| **Chat**      | `/v1/chat/completions`     | Conversational AI and instruction following  |
| **Reasoning** | `/v1/chat/completions`     | Chain-of-thought models with thinking output |
| **Code**      | `/v1/chat/completions`     | Code generation, analysis, and debugging     |
| **Vision**    | `/v1/chat/completions`     | Image understanding via multimodal input     |
| **Image**     | `/v1/images/generations`   | Text-to-image generation                     |
| **Video**     | `/v1/videos`               | Text-to-video generation (async)             |
| **TTS**       | `/v1/audio/speech`         | Text-to-speech synthesis                     |
| **ASR**       | `/v1/audio/transcriptions` | Speech-to-text transcription                 |

### Model Playground

An interactive testing environment in the dashboard. Each model has its own playground where you can chat, generate images, create videos, or test audio — with auto-generated code examples.

## GPU Instances

Full Linux containers with dedicated NVIDIA GPUs and root shell access via SSH. Configure CPU, memory, storage, and GPU type/count. Billed hourly while running.

### Available GPUs

| GPU          | VRAM     | Best For                                   |
| ------------ | -------- | ------------------------------------------ |
| **RTX 4090** | 24 GB    | Development, small models, fine-tuning     |
| **A100**     | 40/80 GB | Training, large model inference            |
| **H100**     | 80 GB    | Maximum performance training and inference |
| **L40S**     | 48 GB    | Inference, image/video generation          |

## Workspaces

The top-level organizational unit. Each workspace has its own resources (instances, storage), billing (credit balance, transactions), team members, and audit logs. Use workspaces to separate workloads, clients, or teams.

## Environments

Resource containers inside a workspace. Every workspace has one or more environments (the default is called `main`). Deployments, storage instances, and API keys belong to an environment — money belongs to the workspace. All environments draw from the same credit balance. Use environments to separate staging from production, or to isolate different projects within one workspace.

## Roles

| Role          | Resources | Billing | Members | Delete Workspace |
| ------------- | :-------: | :-----: | :-----: | :--------------: |
| **Owner**     |    Full   |   Full  |   Full  |        Yes       |
| **Manager**   |    Full   |   Full  |   Full  |        No        |
| **Developer** |    Full   |    No   |    No   |        No        |

## Credits

Prepaid billing currency. **1 credit = \$1 USD**. Credits are consumed by model API calls (per token/per generation) and GPU instance hours. Each workspace has its own balance.

## Storage

Persistent cloud volumes (Wasabi, AWS S3, Backblaze B2) that mount to GPU instances. Data survives instance termination. Includes a built-in file explorer in the dashboard. Billed at \$0.03/GB/month.

## API Keys

Authentication tokens for the Models API and Infrastructure API. Created per-workspace in the dashboard. The full key is shown only once at creation. Format: `rc_live_...`