---
title: "ezgh inference"
description: "Inference: the Model Catalog and your project's limits."
---

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

# ezgh inference

{/* Generated by ezgh-cli's internal/tools/clidocs from the ezgh command tree. Don't edit: change the command's help in ezgh-cli and regenerate. */}

```sh
ezgh inference <command>
```

EZGH Inference serves models behind an OpenAI-compatible API: the stock OpenAI SDKs work with their base URL set to a project's

```text
https://inference-api.<domain>/v1/organizations/<org>/projects/<project>/openai/v1
```

and an EZGH API key as the API key. The CLI doesn't call models; it reads the Model Catalog (every model EZGH serves, in any product, which needs no login) and a project's limits.

## Flags

This command also takes the [global flags](/cli/reference#global-flags).

## Subcommands

| Command | Description |
| --- | --- |
| [`ezgh inference limits`](/cli/reference/inference-limits) | Show a project's inference limits |
| [`ezgh inference models`](/cli/reference/inference-models) | The Model Catalog: every model EZGH serves |

Source: https://docs.ezghcloud.com/cli/reference/inference/index.mdx