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

# Overview

> Serve a model behind an OpenAI-compatible endpoint

A deployment serves a checkpoint or a base model behind an OpenAI-compatible endpoint. It runs in Monte Cloud, or in the team's own account with BYOC.

```bash theme={null}
monte deployment create support-triage/train-07 --name support-triage
```

Each deployment has replicas that scale with traffic, on a schedule, or to zero, and it keeps versions for traffic splits and rollback. Many LoRA adapters can share one base deployment. Callers send an API key, and the endpoint takes chat completions with streaming and tool calls. A deployment is billed until it is deleted or scaled to zero.

A deployment also collects each request and response as a trace for [continual learning](https://docs.trymonte.ai/continual-learning/overview.md). `--traces off` keeps no content.

## In This Section

| Page | Covers |
| - | - |
| [Hosting Options](https://docs.trymonte.ai/hosting.md) | Monte Cloud or BYOC |
| [Deployments](https://docs.trymonte.ai/serving/deploy.md) | Create a deployment, and add adapters to a base |
| [Endpoints](https://docs.trymonte.ai/serving/endpoints.md) | Call a deployment |
| [Scaling and Versions](https://docs.trymonte.ai/serving/scaling-versions.md) | Replicas, traffic splits, and rollback |


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