Key Concepts
Models API
An OpenAI-compatible REST API athttps://api.runcrate.ai/v1 that gives you access to 200+ AI 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 |
Projects
The top-level organizational unit. Each project has its own resources (instances, storage), billing (credit balance, transactions), team members, and audit logs. Use projects to separate workloads, clients, or environments.Roles
| Role | Resources | Billing | Members | Delete Project |
|---|---|---|---|---|
| Owner | Full | Full | Full | Yes |
| Admin | Full | Full | Full | No |
| Member | 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 project 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. Created per-project in the dashboard. The full key is shown only once at creation. Format:rc_live_...