Mathis/llamactl
1
0
Fork 0
mirror of https://github.com/lordmathis/llamactl.git synced 2025-11-05 16:44:22 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
gh-pages
llamactl/v0.11.2/api-reference/index.html

2865 lines
84 KiB
HTML
Raw Permalink Blame History

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<meta name="description" content="User documentation for Llamatl - A management tool for Llama.cpp instances">
<meta name="author" content="Llamatl Team">
<link rel="canonical" href="https://llamactl.org/v0.11.2/api-reference/">
<link rel="prev" href="../managing-instances/">
<link rel="next" href="../troubleshooting/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.22">
<title>API Reference - Llamatl Documentation</title>
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style>
<link rel="stylesheet" href="../css/css-v1.1.3.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#llamactl-api-10" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<div data-md-color-scheme="default" data-md-component="outdated" hidden>
</div>
<header class="md-header md-header--shadow md-header--lifted" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="Llamatl Documentation" class="md-header__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
Llamatl Documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
API Reference
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="default" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to dark mode" type="radio" name="__palette" id="__palette_0">
<label class="md-header__button md-icon" title="Switch to dark mode" for="__palette_1" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a4 4 0 0 0-4 4 4 4 0 0 0 4 4 4 4 0 0 0 4-4 4 4 0 0 0-4-4m0 10a6 6 0 0 1-6-6 6 6 0 0 1 6-6 6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="indigo" data-md-color-accent="indigo" aria-label="Switch to light mode" type="radio" name="__palette" id="__palette_1">
<label class="md-header__button md-icon" title="Switch to light mode" for="__palette_0" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 18c-.89 0-1.74-.2-2.5-.55C11.56 16.5 13 14.42 13 12s-1.44-4.5-3.5-5.45C10.26 6.2 11.11 6 12 6a6 6 0 0 1 6 6 6 6 0 0 1-6 6m8-9.31V4h-4.69L12 .69 8.69 4H4v4.69L.69 12 4 15.31V20h4.69L12 23.31 15.31 20H20v-4.69L23.31 12z"/></svg>
</label>
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
<div class="md-header__source">
<a href="https://github.com/lordmathis/llamactl" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
lordmathis/llamactl
</div>
</a>
</div>
</nav>
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href=".." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../installation/" class="md-tabs__link">
Installation
</a>
</li>
<li class="md-tabs__item">
<a href="../quick-start/" class="md-tabs__link">
Quick Start
</a>
</li>
<li class="md-tabs__item">
<a href="../configuration/" class="md-tabs__link">
Configuration
</a>
</li>
<li class="md-tabs__item">
<a href="../managing-instances/" class="md-tabs__link">
Managing Instances
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="./" class="md-tabs__link">
API Reference
</a>
</li>
<li class="md-tabs__item">
<a href="../troubleshooting/" class="md-tabs__link">
Troubleshooting
</a>
</li>
</ul>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted md-nav--integrated" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="Llamatl Documentation" class="md-nav__button md-logo" aria-label="Llamatl Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
Llamatl Documentation
</label>
<div class="md-nav__source">
<a href="https://github.com/lordmathis/llamactl" title="Go to repository" class="md-source" data-md-component="source">
<div class="md-source__icon md-icon">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M439.6 236.1 244 40.5c-5.4-5.5-12.8-8.5-20.4-8.5s-15 3-20.4 8.4L162.5 81l51.5 51.5c27.1-9.1 52.7 16.8 43.4 43.7l49.7 49.7c34.2-11.8 61.2 31 35.5 56.7-26.5 26.5-70.2-2.9-56-37.3L240.3 199v121.9c25.3 12.5 22.3 41.8 9.1 55-6.4 6.4-15.2 10.1-24.3 10.1s-17.8-3.6-24.3-10.1c-17.6-17.6-11.1-46.9 11.2-56v-123c-20.8-8.5-24.6-30.7-18.6-45L142.6 101 8.5 235.1C3 240.6 0 247.9 0 255.5s3 15 8.5 20.4l195.6 195.7c5.4 5.4 12.7 8.4 20.4 8.4s15-3 20.4-8.4l194.7-194.7c5.4-5.4 8.4-12.8 8.4-20.4s-3-15-8.4-20.4"/></svg>
</div>
<div class="md-source__repository">
lordmathis/llamactl
</div>
</a>
</div>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../installation/" class="md-nav__link">
<span class="md-ellipsis">
Installation
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../quick-start/" class="md-nav__link">
<span class="md-ellipsis">
Quick Start
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../configuration/" class="md-nav__link">
<span class="md-ellipsis">
Configuration
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../managing-instances/" class="md-nav__link">
<span class="md-ellipsis">
Managing Instances
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
API Reference
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
API Reference
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#backends" class="md-nav__link">
<span class="md-ellipsis">
Backends
</span>
</a>
<nav class="md-nav" aria-label="Backends">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#get-apiv1backendsllama-cppdevices" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/backends/llama-cpp/devices
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1backendsllama-cpphelp" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/backends/llama-cpp/help
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1backendsllama-cppparse-command" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/backends/llama-cpp/parse-command
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1backendsllama-cppversion" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/backends/llama-cpp/version
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1backendsmlxparse-command" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/backends/mlx/parse-command
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1backendsvllmparse-command" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/backends/vllm/parse-command
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#instances" class="md-nav__link">
<span class="md-ellipsis">
Instances
</span>
</a>
<nav class="md-nav" aria-label="Instances">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#get-apiv1instances" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/instances
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#delete-apiv1instancesname" class="md-nav__link">
<span class="md-ellipsis">
DELETE /api/v1/instances/{name}
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1instancesname" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/instances/{name}
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1instancesname" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/instances/{name}
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#put-apiv1instancesname" class="md-nav__link">
<span class="md-ellipsis">
PUT /api/v1/instances/{name}
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1instancesnamelogs" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/instances/{name}/logs
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1instancesnameproxy" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/instances/{name}/proxy
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1instancesnameproxy" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/instances/{name}/proxy
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1instancesnamerestart" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/instances/{name}/restart
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1instancesnamestart" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/instances/{name}/start
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-apiv1instancesnamestop" class="md-nav__link">
<span class="md-ellipsis">
POST /api/v1/instances/{name}/stop
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#nodes" class="md-nav__link">
<span class="md-ellipsis">
Nodes
</span>
</a>
<nav class="md-nav" aria-label="Nodes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#get-apiv1nodes" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/nodes
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-apiv1nodesname" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/nodes/{name}
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#system" class="md-nav__link">
<span class="md-ellipsis">
System
</span>
</a>
<nav class="md-nav" aria-label="System">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#get-apiv1version" class="md-nav__link">
<span class="md-ellipsis">
GET /api/v1/version
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#llamacpp" class="md-nav__link">
<span class="md-ellipsis">
Llama.cpp
</span>
</a>
<nav class="md-nav" aria-label="Llama.cpp">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#get-llama-cppname" class="md-nav__link">
<span class="md-ellipsis">
GET /llama-cpp/{name}/
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnameapply-template" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/apply-template
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnamecompletion" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/completion
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnamedetokenize" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/detokenize
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnameembeddings" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/embeddings
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnameinfill" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/infill
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnamemetrics" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/metrics
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-llama-cppnameprops" class="md-nav__link">
<span class="md-ellipsis">
GET /llama-cpp/{name}/props
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnameprops" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/props
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnamereranking" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/reranking
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-llama-cppnameslots" class="md-nav__link">
<span class="md-ellipsis">
GET /llama-cpp/{name}/slots
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#post-llama-cppnametokenize" class="md-nav__link">
<span class="md-ellipsis">
POST /llama-cpp/{name}/tokenize
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#openai" class="md-nav__link">
<span class="md-ellipsis">
OpenAI
</span>
</a>
<nav class="md-nav" aria-label="OpenAI">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#post-v1" class="md-nav__link">
<span class="md-ellipsis">
POST /v1/
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#get-v1models" class="md-nav__link">
<span class="md-ellipsis">
GET /v1/models
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../troubleshooting/" class="md-nav__link">
<span class="md-ellipsis">
Troubleshooting
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<!--
This Markdown has been generated by essentials-openapi
https://github.com/Neoteroi/essentials-openapi
Most likely, it is not desirable to edit this file by hand!
-->
<h1 id="llamactl-api-10">llamactl API <span class="api-version">1.0</span><a class="headerlink" href="#llamactl-api-10" title="Permanent link">&para;</a></h1>
<p>llamactl is a control server for managing Llama Server instances. </p>
<hr />
<div class="license info-data">
<strong>License:</strong> <a href="https://opensource.org/license/mit/" target="_blank" rel="noopener noreferrer">MIT License</a>
</div>
<h2 id="backends"><span class="api-tag">Backends</span><a class="headerlink" href="#backends" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="get-apiv1backendsllama-cppdevices"><span class="http-get">GET</span> /api/v1/backends/llama-cpp/devices<a class="headerlink" href="#get-apiv1backendsllama-cppdevices" title="Permanent link">&para;</a></h3>
<p>List available devices for llama server </p>
<details class="note">
<summary>Description</summary>
<p>Returns a list of available devices for the llama server </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1backendsllama-cpphelp"><span class="http-get">GET</span> /api/v1/backends/llama-cpp/help<a class="headerlink" href="#get-apiv1backendsllama-cpphelp" title="Permanent link">&para;</a></h3>
<p>Get help for llama server </p>
<details class="note">
<summary>Description</summary>
<p>Returns the help text for the llama server command </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1backendsllama-cppparse-command"><span class="http-post">POST</span> /api/v1/backends/llama-cpp/parse-command<a class="headerlink" href="#post-apiv1backendsllama-cppparse-command" title="Permanent link">&para;</a></h3>
<p>Parse llama-server command </p>
<details class="note">
<summary>Description</summary>
<p>Parses a llama-server command string into instance options </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>request</code></td>
<td>body</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Command to parse</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1backendsllama-cppversion"><span class="http-get">GET</span> /api/v1/backends/llama-cpp/version<a class="headerlink" href="#get-apiv1backendsllama-cppversion" title="Permanent link">&para;</a></h3>
<p>Get version of llama server </p>
<details class="note">
<summary>Description</summary>
<p>Returns the version of the llama server command </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1backendsmlxparse-command"><span class="http-post">POST</span> /api/v1/backends/mlx/parse-command<a class="headerlink" href="#post-apiv1backendsmlxparse-command" title="Permanent link">&para;</a></h3>
<p>Parse mlx_lm.server command </p>
<details class="note">
<summary>Description</summary>
<p>Parses MLX-LM server command string into instance options </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>request</code></td>
<td>body</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Command to parse</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1backendsvllmparse-command"><span class="http-post">POST</span> /api/v1/backends/vllm/parse-command<a class="headerlink" href="#post-apiv1backendsvllmparse-command" title="Permanent link">&para;</a></h3>
<p>Parse vllm serve command </p>
<details class="note">
<summary>Description</summary>
<p>Parses a vLLM serve command string into instance options </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>request</code></td>
<td>body</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Command to parse</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<h2 id="instances"><span class="api-tag">Instances</span><a class="headerlink" href="#instances" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="get-apiv1instances"><span class="http-get">GET</span> /api/v1/instances<a class="headerlink" href="#get-apiv1instances" title="Permanent link">&para;</a></h3>
<p>List all instances </p>
<details class="note">
<summary>Description</summary>
<p>Returns a list of all instances managed by the server </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="delete-apiv1instancesname"><span class="http-delete">DELETE</span> /api/v1/instances/<span class="route-param">{name}</span><a class="headerlink" href="#delete-apiv1instancesname" title="Permanent link">&para;</a></h3>
<p>Delete an instance </p>
<details class="note">
<summary>Description</summary>
<p>Stops and removes a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-204">204</span>&nbsp;<span class="status-phrase">No Content</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1instancesname"><span class="http-get">GET</span> /api/v1/instances/<span class="route-param">{name}</span><a class="headerlink" href="#get-apiv1instancesname" title="Permanent link">&para;</a></h3>
<p>Get details of a specific instance </p>
<details class="note">
<summary>Description</summary>
<p>Returns the details of a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1instancesname"><span class="http-post">POST</span> /api/v1/instances/<span class="route-param">{name}</span><a class="headerlink" href="#post-apiv1instancesname" title="Permanent link">&para;</a></h3>
<p>Create and start a new instance </p>
<details class="note">
<summary>Description</summary>
<p>Creates a new instance with the provided configuration options </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
<tr>
<td class="parameter-name"><code>options</code></td>
<td>body</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance configuration options</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-201">201</span>&nbsp;<span class="status-phrase">Created</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="put-apiv1instancesname"><span class="http-put">PUT</span> /api/v1/instances/<span class="route-param">{name}</span><a class="headerlink" href="#put-apiv1instancesname" title="Permanent link">&para;</a></h3>
<p>Update an instance's configuration </p>
<details class="note">
<summary>Description</summary>
<p>Updates the configuration of a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
<tr>
<td class="parameter-name"><code>options</code></td>
<td>body</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance configuration options</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1instancesnamelogs"><span class="http-get">GET</span> /api/v1/instances/<span class="route-param">{name}</span>/logs<a class="headerlink" href="#get-apiv1instancesnamelogs" title="Permanent link">&para;</a></h3>
<p>Get logs from a specific instance </p>
<details class="note">
<summary>Description</summary>
<p>Returns the logs from a specific instance by name with optional line limit </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>lines</code></td>
<td>query</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Number of lines to retrieve (default: all lines)</td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1instancesnameproxy"><span class="http-get">GET</span> /api/v1/instances/<span class="route-param">{name}</span>/proxy<a class="headerlink" href="#get-apiv1instancesnameproxy" title="Permanent link">&para;</a></h3>
<p>Proxy requests to a specific instance, does not autostart instance if stopped </p>
<details class="note">
<summary>Description</summary>
<p>Forwards HTTP requests to the llama-server instance running on a specific<br />
port </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-503">503</span>&nbsp;<span class="status-phrase">Service Unavailable</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1instancesnameproxy"><span class="http-post">POST</span> /api/v1/instances/<span class="route-param">{name}</span>/proxy<a class="headerlink" href="#post-apiv1instancesnameproxy" title="Permanent link">&para;</a></h3>
<p>Proxy requests to a specific instance, does not autostart instance if stopped </p>
<details class="note">
<summary>Description</summary>
<p>Forwards HTTP requests to the llama-server instance running on a specific<br />
port </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-503">503</span>&nbsp;<span class="status-phrase">Service Unavailable</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1instancesnamerestart"><span class="http-post">POST</span> /api/v1/instances/<span class="route-param">{name}</span>/restart<a class="headerlink" href="#post-apiv1instancesnamerestart" title="Permanent link">&para;</a></h3>
<p>Restart a running instance </p>
<details class="note">
<summary>Description</summary>
<p>Restarts a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1instancesnamestart"><span class="http-post">POST</span> /api/v1/instances/<span class="route-param">{name}</span>/start<a class="headerlink" href="#post-apiv1instancesnamestart" title="Permanent link">&para;</a></h3>
<p>Start a stopped instance </p>
<details class="note">
<summary>Description</summary>
<p>Starts a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-apiv1instancesnamestop"><span class="http-post">POST</span> /api/v1/instances/<span class="route-param">{name}</span>/stop<a class="headerlink" href="#post-apiv1instancesnamestop" title="Permanent link">&para;</a></h3>
<p>Stop a running instance </p>
<details class="note">
<summary>Description</summary>
<p>Stops a specific instance by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<h2 id="nodes"><span class="api-tag">Nodes</span><a class="headerlink" href="#nodes" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="get-apiv1nodes"><span class="http-get">GET</span> /api/v1/nodes<a class="headerlink" href="#get-apiv1nodes" title="Permanent link">&para;</a></h3>
<p>List all configured nodes </p>
<details class="note">
<summary>Description</summary>
<p>Returns a map of all nodes configured in the server (node name -&gt; node<br />
config) </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-apiv1nodesname"><span class="http-get">GET</span> /api/v1/nodes/<span class="route-param">{name}</span><a class="headerlink" href="#get-apiv1nodesname" title="Permanent link">&para;</a></h3>
<p>Get details of a specific node </p>
<details class="note">
<summary>Description</summary>
<p>Returns the details of a specific node by name </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Node Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-404">404</span>&nbsp;<span class="status-phrase">Not Found</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<h2 id="system"><span class="api-tag">System</span><a class="headerlink" href="#system" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="get-apiv1version"><span class="http-get">GET</span> /api/v1/version<a class="headerlink" href="#get-apiv1version" title="Permanent link">&para;</a></h3>
<p>Get llamactl version </p>
<details class="note">
<summary>Description</summary>
<p>Returns the version of the llamactl command </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<h2 id="llamacpp"><span class="api-tag">Llama.cpp</span><a class="headerlink" href="#llamacpp" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="get-llama-cppname"><span class="http-get">GET</span> /llama-cpp/<span class="route-param">{name}</span>/<a class="headerlink" href="#get-llama-cppname" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp UI for the instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the llama.cpp UI for the specified instance </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>query</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnameapply-template"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/apply-template<a class="headerlink" href="#post-llama-cppnameapply-template" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnamecompletion"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/completion<a class="headerlink" href="#post-llama-cppnamecompletion" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnamedetokenize"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/detokenize<a class="headerlink" href="#post-llama-cppnamedetokenize" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnameembeddings"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/embeddings<a class="headerlink" href="#post-llama-cppnameembeddings" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnameinfill"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/infill<a class="headerlink" href="#post-llama-cppnameinfill" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnamemetrics"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/metrics<a class="headerlink" href="#post-llama-cppnamemetrics" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-llama-cppnameprops"><span class="http-get">GET</span> /llama-cpp/<span class="route-param">{name}</span>/props<a class="headerlink" href="#get-llama-cppnameprops" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnameprops"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/props<a class="headerlink" href="#post-llama-cppnameprops" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnamereranking"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/reranking<a class="headerlink" href="#post-llama-cppnamereranking" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-llama-cppnameslots"><span class="http-get">GET</span> /llama-cpp/<span class="route-param">{name}</span>/slots<a class="headerlink" href="#get-llama-cppnameslots" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="post-llama-cppnametokenize"><span class="http-post">POST</span> /llama-cpp/<span class="route-param">{name}</span>/tokenize<a class="headerlink" href="#post-llama-cppnametokenize" title="Permanent link">&para;</a></h3>
<p>Proxy requests to llama.cpp server instance </p>
<details class="note">
<summary>Description</summary>
<p>Proxies requests to the specified llama.cpp server instance, starting it on-<br />
demand if configured </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
<tr>
<td class="parameter-name"><code>name</code></td>
<td>path</td>
<td>None</td>
<td></td>
<td>No</td>
<td>Instance Name</td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<h2 id="openai"><span class="api-tag">OpenAI</span><a class="headerlink" href="#openai" title="Permanent link">&para;</a></h2>
<hr class="operation-separator" />
<h3 id="post-v1"><span class="http-post">POST</span> /v1/<a class="headerlink" href="#post-v1" title="Permanent link">&para;</a></h3>
<p>OpenAI-compatible proxy endpoint </p>
<details class="note">
<summary>Description</summary>
<p>Handles all POST requests to /v1/*, routing to the appropriate instance<br />
based on the request body. Requires API key authentication via the<br />
<code>Authorization</code> header. </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-400">400</span>&nbsp;<span class="status-phrase">Bad Request</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr class="operation-separator" />
<h3 id="get-v1models"><span class="http-get">GET</span> /v1/models<a class="headerlink" href="#get-v1models" title="Permanent link">&para;</a></h3>
<p>List instances in OpenAI-compatible format </p>
<details class="note">
<summary>Description</summary>
<p>Returns a list of instances in a format compatible with OpenAI API </p>
</details>
<p><strong>Input parameters</strong> </p>
<table>
<thead>
<tr>
<th>Parameter</th>
<th>In</th>
<th>Type</th>
<th>Default</th>
<th>Nullable</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr>
<td class="parameter-name"><code>ApiKeyAuth</code></td>
<td>header</td>
<td>string</td>
<td>N/A</td>
<td>No</td>
<td></td>
</tr>
</tbody>
</table>
<p class="response-title">
<strong>Response <span class="response-code code-200">200</span>&nbsp;<span class="status-phrase">OK</span></strong>
</p>
<p class="response-title">
<strong>Response <span class="response-code code-500">500</span>&nbsp;<span class="status-phrase">Internal Server Error</span></strong>
</p>
<hr />
<aside class="md-source-file">
<span class="md-source-file__fact">
<span class="md-icon" title="Last update">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M21 13.1c-.1 0-.3.1-.4.2l-1 1 2.1 2.1 1-1c.2-.2.2-.6 0-.8l-1.3-1.3c-.1-.1-.2-.2-.4-.2m-1.9 1.8-6.1 6V23h2.1l6.1-6.1zM12.5 7v5.2l4 2.4-1 1L11 13V7zM11 21.9c-5.1-.5-9-4.8-9-9.9C2 6.5 6.5 2 12 2c5.3 0 9.6 4.1 10 9.3-.3-.1-.6-.2-1-.2s-.7.1-1 .2C19.6 7.2 16.2 4 12 4c-4.4 0-8 3.6-8 8 0 4.1 3.1 7.5 7.1 7.9l-.1.2z"/></svg>
</span>
<span class="git-revision-date-localized-plugin git-revision-date-localized-plugin-date" title="October 26, 2025 13:43:27 UTC">October 26, 2025</span>
</span>
</aside>
</article>
</div>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
<div class="md-social">
<a href="https://github.com/lordmathis/llamactl" target="_blank" rel="noopener" title="github.com" class="md-social__link">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><!--! Font Awesome Free 7.1.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2025 Fonticons, Inc.--><path d="M173.9 397.4c0 2-2.3 3.6-5.2 3.6-3.3.3-5.6-1.3-5.6-3.6 0-2 2.3-3.6 5.2-3.6 3-.3 5.6 1.3 5.6 3.6m-31.1-4.5c-.7 2 1.3 4.3 4.3 4.9 2.6 1 5.6 0 6.2-2s-1.3-4.3-4.3-5.2c-2.6-.7-5.5.3-6.2 2.3m44.2-1.7c-2.9.7-4.9 2.6-4.6 4.9.3 2 2.9 3.3 5.9 2.6 2.9-.7 4.9-2.6 4.6-4.6-.3-1.9-3-3.2-5.9-2.9M252.8 8C114.1 8 8 113.3 8 252c0 110.9 69.8 205.8 169.5 239.2 12.8 2.3 17.3-5.6 17.3-12.1 0-6.2-.3-40.4-.3-61.4 0 0-70 15-84.7-29.8 0 0-11.4-29.1-27.8-36.6 0 0-22.9-15.7 1.6-15.4 0 0 24.9 2 38.6 25.8 21.9 38.6 58.6 27.5 72.9 20.9 2.3-16 8.8-27.1 16-33.7-55.9-6.2-112.3-14.3-112.3-110.5 0-27.5 7.6-41.3 23.6-58.9-2.6-6.5-11.1-33.3 2.6-67.9 20.9-6.5 69 27 69 27 20-5.6 41.5-8.5 62.8-8.5s42.8 2.9 62.8 8.5c0 0 48.1-33.6 69-27 13.7 34.7 5.2 61.4 2.6 67.9 16 17.7 25.8 31.5 25.8 58.9 0 96.5-58.9 104.2-114.8 110.5 9.2 7.9 17 22.9 17 46.4 0 33.7-.3 75.4-.3 83.6 0 6.5 4.6 14.4 17.3 12.1C436.2 457.8 504 362.9 504 252 504 113.3 391.5 8 252.8 8M105.2 352.9c-1.3 1-1 3.3.7 5.2 1.6 1.6 3.9 2.3 5.2 1 1.3-1 1-3.3-.7-5.2-1.6-1.6-3.9-2.3-5.2-1m-10.8-8.1c-.7 1.3.3 2.9 2.3 3.9 1.6 1 3.6.7 4.3-.7.7-1.3-.3-2.9-2.3-3.9-2-.6-3.6-.3-4.3.7m32.4 35.6c-1.6 1.3-1 4.3 1.3 6.2 2.3 2.3 5.2 2.6 6.5 1 1.3-1.3.7-4.3-1.3-6.2-2.2-2.3-5.2-2.6-6.5-1m-11.4-14.7c-1.6 1-1.6 3.6 0 5.9s4.3 3.3 5.6 2.3c1.6-1.3 1.6-3.9 0-6.2-1.4-2.3-4-3.3-5.6-2"/></svg>
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.tabs", "navigation.tabs.sticky", "toc.integrate", "navigation.top", "search.highlight", "search.share", "content.code.copy"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": {"default": "stable", "provider": "mike"}}</script>
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>
Reference in New Issue View Git Blame Copy Permalink