mirror of
https://github.com/katanemo/plano.git
synced 2026-05-05 05:42:49 +02:00
deploy: e224cba3e3
This commit is contained in:
adilhafeez
parent
0898a9aa15
commit
c25ce33efc
68 changed files with 9799 additions and 4588 deletions
|
|
@ -7,19 +7,19 @@
|
|||
<meta content="white" media="(prefers-color-scheme: light)" name="theme-color"/>
|
||||
<meta content="black" media="(prefers-color-scheme: dark)" name="theme-color"/>
|
||||
<meta content="width=device-width, initial-scale=1" name="viewport"/>
|
||||
<title>Supported Providers & Configuration | Arch Docs v0.3.22</title>
|
||||
<meta content="Supported Providers & Configuration | Arch Docs v0.3.22" property="og:title"/>
|
||||
<meta content="Supported Providers & Configuration | Arch Docs v0.3.22" name="twitter:title"/>
|
||||
<title>Supported Providers & Configuration | Plano Docs v0.4</title>
|
||||
<meta content="Supported Providers & Configuration | Plano Docs v0.4" property="og:title"/>
|
||||
<meta content="Supported Providers & Configuration | Plano Docs v0.4" name="twitter:title"/>
|
||||
<link href="../../_static/pygments.css?v=466e7b45" rel="stylesheet" type="text/css"/>
|
||||
<link href="../../_static/theme.css?v=42baaae4" rel="stylesheet" type="text/css"/>
|
||||
<link href="../../_static/_static/custom.css" rel="stylesheet" type="text/css"/>
|
||||
<link href="../../_static/sphinx-design.min.css?v=95c83b7e" rel="stylesheet" type="text/css"/>
|
||||
<link href="../../_static/css/custom.css?v=2929376a" rel="stylesheet" type="text/css"/>
|
||||
<link href="../../_static/awesome-sphinx-design.css?v=15e0fffa" rel="stylesheet" type="text/css"/>
|
||||
<link href="./docs/concepts/llm_providers/supported_providers.html" rel="canonical"/>
|
||||
<link href="../../_static/favicon.ico" rel="icon"/>
|
||||
<link href="../../search.html" rel="search" title="Search"/>
|
||||
<link href="client_libraries.html" rel="next" title="Client Libraries"/>
|
||||
<link href="llm_providers.html" rel="prev" title="LLM Providers"/>
|
||||
<link href="llm_providers.html" rel="prev" title="Model (LLM) Providers"/>
|
||||
<script>
|
||||
<!-- Prevent Flash of wrong theme -->
|
||||
const userPreference = localStorage.getItem('darkMode');
|
||||
|
|
@ -39,7 +39,7 @@
|
|||
</a><header class="sticky top-0 z-40 w-full border-b shadow-sm border-border supports-backdrop-blur:bg-background/60 bg-background/95 backdrop-blur"><div class="container flex items-center h-14">
|
||||
<div class="hidden mr-4 md:flex">
|
||||
<a class="flex items-center mr-6" href="../../index.html">
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="24" src="../../_static/favicon.ico" width="24"/><span class="hidden font-bold sm:inline-block text-clip whitespace-nowrap">Arch Docs v0.3.22</span>
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="24" src="../../_static/favicon.ico" width="24"/><span class="hidden font-bold sm:inline-block text-clip whitespace-nowrap">Plano Docs v0.4</span>
|
||||
</a></div><button @click="showSidebar = true" class="inline-flex items-center justify-center h-10 px-0 py-2 mr-2 text-base font-medium transition-colors rounded-md hover:text-accent-foreground hover:bg-transparent md:hidden" type="button">
|
||||
<svg aria-hidden="true" fill="currentColor" height="24" viewbox="0 96 960 960" width="24" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M152.587 825.087q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440Zm0-203.587q-19.152 0-32.326-13.174T107.087 576q0-19.152 13.174-32.326t32.326-13.174h320q19.152 0 32.326 13.174T518.087 576q0 19.152-13.174 32.326T472.587 621.5h-320Zm0-203.587q-19.152 0-32.326-13.174t-13.174-32.326q0-19.152 13.174-32.326t32.326-13.174h440q19.152 0 32.326 13.174t13.174 32.326q0 19.152-13.174 32.326t-32.326 13.174h-440ZM708.913 576l112.174 112.174q12.674 12.674 12.674 31.826t-12.674 31.826Q808.413 764.5 789.261 764.5t-31.826-12.674l-144-144Q600 594.391 600 576t13.435-31.826l144-144q12.674-12.674 31.826-12.674t31.826 12.674q12.674 12.674 12.674 31.826t-12.674 31.826L708.913 576Z"></path>
|
||||
|
|
@ -56,7 +56,7 @@
|
|||
</form>
|
||||
</div>
|
||||
<nav class="flex items-center space-x-1">
|
||||
<a href="https://github.com/katanemo/arch" rel="noopener nofollow" title="Visit repository on GitHub">
|
||||
<a href="https://github.com/katanemo/plano" rel="noopener nofollow" title="Visit repository on GitHub">
|
||||
<div class="inline-flex items-center justify-center px-0 text-sm font-medium transition-colors rounded-md disabled:opacity-50 disabled:pointer-events-none hover:bg-accent hover:text-accent-foreground h-9 w-9">
|
||||
<svg fill="currentColor" height="26px" style="margin-top:-2px;display:inline" viewbox="0 0 45 44" xmlns="http://www.w3.org/2000/svg"><path clip-rule="evenodd" d="M22.477.927C10.485.927.76 10.65.76 22.647c0 9.596 6.223 17.736 14.853 20.608 1.087.2 1.483-.47 1.483-1.047 0-.516-.019-1.881-.03-3.693-6.04 1.312-7.315-2.912-7.315-2.912-.988-2.51-2.412-3.178-2.412-3.178-1.972-1.346.149-1.32.149-1.32 2.18.154 3.327 2.24 3.327 2.24 1.937 3.318 5.084 2.36 6.321 1.803.197-1.403.759-2.36 1.379-2.903-4.823-.548-9.894-2.412-9.894-10.734 0-2.37.847-4.31 2.236-5.828-.224-.55-.969-2.759.214-5.748 0 0 1.822-.584 5.972 2.226 1.732-.482 3.59-.722 5.437-.732 1.845.01 3.703.25 5.437.732 4.147-2.81 5.967-2.226 5.967-2.226 1.185 2.99.44 5.198.217 5.748 1.392 1.517 2.232 3.457 2.232 5.828 0 8.344-5.078 10.18-9.916 10.717.779.67 1.474 1.996 1.474 4.021 0 2.904-.027 5.247-.027 5.96 0 .58.392 1.256 1.493 1.044C37.981 40.375 44.2 32.24 44.2 22.647c0-11.996-9.726-21.72-21.722-21.72" fill="currentColor" fill-rule="evenodd"></path></svg>
|
||||
</div>
|
||||
|
|
@ -75,40 +75,33 @@
|
|||
</header>
|
||||
<div class="flex-1"><div class="container flex-1 items-start md:grid md:grid-cols-[220px_minmax(0,1fr)] md:gap-6 lg:grid-cols-[240px_minmax(0,1fr)] lg:gap-10"><aside :aria-hidden="!showSidebar" :class="{ 'translate-x-0': showSidebar }" class="fixed inset-y-0 left-0 md:top-14 z-50 md:z-30 bg-background md:bg-transparent transition-all duration-100 -translate-x-full md:translate-x-0 ml-0 p-6 md:p-0 md:-ml-2 md:h-[calc(100vh-3.5rem)] w-5/6 md:w-full shrink-0 overflow-y-auto border-r border-border md:sticky" id="left-sidebar">
|
||||
<a class="!justify-start text-sm md:!hidden bg-background" href="../../index.html">
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="16" src="../../_static/favicon.ico" width="16"/><span class="font-bold text-clip whitespace-nowrap">Arch Docs v0.3.22</span>
|
||||
<img alt="Logo" class="mr-2 dark:invert" height="16" src="../../_static/favicon.ico" width="16"/><span class="font-bold text-clip whitespace-nowrap">Plano Docs v0.4</span>
|
||||
</a>
|
||||
<div class="relative overflow-hidden md:overflow-auto my-4 md:my-0 h-[calc(100vh-8rem)] md:h-auto">
|
||||
<div class="overflow-y-auto h-full w-full relative pr-6">
|
||||
|
||||
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-K2LXXSX6HB"></script>
|
||||
<script async="" src="https://www.googletagmanager.com/gtag/js?id=G-EH2VW19FXE"></script>
|
||||
<script>
|
||||
window.dataLayer = window.dataLayer || [];
|
||||
function gtag(){dataLayer.push(arguments);}
|
||||
gtag('js', new Date());
|
||||
|
||||
gtag('config', 'G-K2LXXSX6HB');
|
||||
gtag('config', 'G-EH2VW19FXE');
|
||||
</script>
|
||||
<nav class="table w-full min-w-full my-6 lg:my-8">
|
||||
<p class="caption" role="heading"><span class="caption-text">Get Started</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../get_started/overview.html">Overview</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../get_started/intro_to_arch.html">Intro to Arch</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../get_started/intro_to_plano.html">Intro to Plano</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../get_started/quickstart.html">Quickstart</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../get_started/quickstart.html#next-steps">Next Steps</a></li>
|
||||
</ul>
|
||||
<p class="caption" role="heading"><span class="caption-text">Concepts</span></p>
|
||||
<ul class="current">
|
||||
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../tech_overview/tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-show="expanded">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/terminology.html">Terminology</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/threading_model.html">Threading Model</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/listener.html">Listener</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/prompt.html">Prompts</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/model_serving.html">Model Serving</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../tech_overview/error_target.html">Error Target</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="llm_providers.html">LLM Providers<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
|
||||
<li class="toctree-l1"><a class="reference internal" href="../listeners.html">Listeners</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../agents.html">Agents</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../filter_chain.html">Filter Chains</a></li>
|
||||
<li class="toctree-l1 current" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="llm_providers.html">Model (LLM) Providers<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul class="current" x-show="expanded">
|
||||
<li class="toctree-l2 current"><a class="current reference internal" href="#">Supported Providers & Configuration</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="client_libraries.html">Client Libraries</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="model_aliases.html">Model Aliases</a></li>
|
||||
|
|
@ -118,27 +111,29 @@
|
|||
</ul>
|
||||
<p class="caption" role="heading"><span class="caption-text">Guides</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/prompt_guard.html">Prompt Guard</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/agent_routing.html">Agent Routing and Hand Off</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/function_calling.html">Function Calling</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/orchestration.html">Orchestration</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/llm_router.html">LLM Routing</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/function_calling.html">Function Calling</a></li>
|
||||
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../../guides/observability/observability.html">Observability<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-show="expanded">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/tracing.html">Tracing</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/monitoring.html">Monitoring</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../guides/observability/access_logging.html">Access Logging</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
</ul>
|
||||
<p class="caption" role="heading"><span class="caption-text">Build with Arch</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../build_with_arch/agent.html">Agentic Apps</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../build_with_arch/rag.html">RAG Apps</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../build_with_arch/multi_turn.html">Multi-Turn</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/prompt_guard.html">Guardrails</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../guides/state.html">Conversational State</a></li>
|
||||
</ul>
|
||||
<p class="caption" role="heading"><span class="caption-text">Resources</span></p>
|
||||
<ul>
|
||||
<li class="toctree-l1" x-data="{ expanded: $el.classList.contains('current') ? true : false }"><a :class="{ 'expanded' : expanded }" @click="expanded = !expanded" class="reference internal expandable" href="../../resources/tech_overview/tech_overview.html">Tech Overview<button @click.prevent.stop="expanded = !expanded" type="button"><span class="sr-only"></span><svg fill="currentColor" height="18px" stroke="none" viewbox="0 0 24 24" width="18px" xmlns="http://www.w3.org/2000/svg"><path d="M10 6L8.59 7.41 13.17 12l-4.58 4.59L10 18l6-6z"></path></svg></button></a><ul x-show="expanded">
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../resources/tech_overview/request_lifecycle.html">Request Lifecycle</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../resources/tech_overview/model_serving.html">Bright Staff</a></li>
|
||||
<li class="toctree-l2"><a class="reference internal" href="../../resources/tech_overview/threading_model.html">Threading Model</a></li>
|
||||
</ul>
|
||||
</li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../resources/deployment.html">Deployment</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../resources/configuration_reference.html">Configuration Reference</a></li>
|
||||
<li class="toctree-l1"><a class="reference internal" href="../../resources/llms_txt.html">llms.txt</a></li>
|
||||
</ul>
|
||||
</nav>
|
||||
</div>
|
||||
|
|
@ -153,39 +148,31 @@
|
|||
<div class="w-full min-w-0 mx-auto">
|
||||
<nav aria-label="breadcrumbs" class="flex items-center mb-4 space-x-1 text-sm text-muted-foreground">
|
||||
<a class="overflow-hidden text-ellipsis whitespace-nowrap hover:text-foreground" href="../../index.html">
|
||||
<span class="hidden md:inline">Arch Docs v0.3.22</span>
|
||||
<span class="hidden md:inline">Plano Docs v0.4</span>
|
||||
<svg aria-label="Home" class="md:hidden" fill="currentColor" height="18" stroke="none" viewbox="0 96 960 960" width="18" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M240 856h120V616h240v240h120V496L480 316 240 496v360Zm-80 80V456l320-240 320 240v480H520V696h-80v240H160Zm320-350Z"></path>
|
||||
</svg>
|
||||
</a>
|
||||
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="llm_providers.html">LLM Providers</a>
|
||||
<div class="mr-1">/</div><a class="hover:text-foreground overflow-hidden text-ellipsis whitespace-nowrap" href="llm_providers.html">Model (LLM) Providers</a>
|
||||
<div class="mr-1">/</div><span aria-current="page" class="font-medium text-foreground overflow-hidden text-ellipsis whitespace-nowrap">Supported Providers & Configuration</span>
|
||||
</nav>
|
||||
<div id="content" role="main">
|
||||
<section id="supported-providers-configuration">
|
||||
<span id="supported-providers"></span><h1>Supported Providers & Configuration<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#supported-providers-configuration"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h1>
|
||||
<p>Arch provides first-class support for multiple LLM providers through native integrations and OpenAI-compatible interfaces. This comprehensive guide covers all supported providers, their available chat models, and detailed configuration instructions.</p>
|
||||
<p>Plano provides first-class support for multiple LLM providers through native integrations and OpenAI-compatible interfaces. This comprehensive guide covers all supported providers, their available chat models, and detailed configuration instructions.</p>
|
||||
<div class="admonition note">
|
||||
<p class="admonition-title">Note</p>
|
||||
<p><strong>Model Support:</strong> Arch supports all chat models from each provider, not just the examples shown in this guide. The configurations below demonstrate common models for reference, but you can use any chat model available from your chosen provider.</p>
|
||||
<p><strong>Model Support:</strong> Plano supports all chat models from each provider, not just the examples shown in this guide. The configurations below demonstrate common models for reference, but you can use any chat model available from your chosen provider.</p>
|
||||
<p>Please refer to the quuickstart guide <a class="reference internal" href="../../get_started/quickstart.html#llm-routing-quickstart"><span class="std std-ref">here</span></a> to configure and use LLM providers via common client libraries like OpenAI and Anthropic Python SDKs, or via direct HTTP/cURL requests.</p>
|
||||
</div>
|
||||
<section id="configuration-structure">
|
||||
<h2>Configuration Structure<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#configuration-structure" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#configuration-structure'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>All providers are configured in the <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> section of your <code class="docutils literal notranslate"><span class="pre">arch_config.yaml</span></code> file:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">version</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">v0.1</span>
|
||||
</span><span id="line-2">
|
||||
</span><span id="line-3"><span class="nt">listeners</span><span class="p">:</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">egress_traffic</span><span class="p">:</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">address</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">0.0.0.0</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">port</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">12000</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="nt">message_format</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai</span>
|
||||
</span><span id="line-8"><span class="w"> </span><span class="nt">timeout</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">30s</span>
|
||||
</span><span id="line-9">
|
||||
</span><span id="line-10"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="c1"># Provider configurations go here</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">provider/model-name</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$API_KEY</span>
|
||||
</span><span id="line-14"><span class="w"> </span><span class="c1"># Additional provider-specific options</span>
|
||||
<p>All providers are configured in the <code class="docutils literal notranslate"><span class="pre">llm_providers</span></code> section of your <code class="docutils literal notranslate"><span class="pre">plano_config.yaml</span></code> file:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="c1"># Provider configurations go here</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">provider/model-name</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$API_KEY</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="c1"># Additional provider-specific options</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
<p><strong>Common Configuration Fields:</strong></p>
|
||||
|
|
@ -206,7 +193,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</section>
|
||||
<section id="supported-api-endpoints">
|
||||
<h2>Supported API Endpoints<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#supported-api-endpoints" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#supported-api-endpoints'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p>Arch supports the following standardized endpoints across providers:</p>
|
||||
<p>Plano supports the following standardized endpoints across providers:</p>
|
||||
<table class="docutils align-default">
|
||||
<colgroup>
|
||||
<col style="width: 30.0%"/>
|
||||
|
|
@ -228,6 +215,10 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<td><p>Anthropic-style messages</p></td>
|
||||
<td><p>Anthropic SDK, cURL, custom clients</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p><code class="docutils literal notranslate"><span class="pre">/v1/responses</span></code></p></td>
|
||||
<td><p>Unified response endpoint for agentic apps</p></td>
|
||||
<td><p>All SDKs, cURL, custom clients</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
</section>
|
||||
|
|
@ -238,7 +229,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<p><strong>Provider Prefix:</strong> <code class="docutils literal notranslate"><span class="pre">openai/</span></code></p>
|
||||
<p><strong>API Endpoint:</strong> <code class="docutils literal notranslate"><span class="pre">/v1/chat/completions</span></code></p>
|
||||
<p><strong>Authentication:</strong> API Key - Get your OpenAI API key from <a class="reference external" href="https://platform.openai.com/api-keys" rel="nofollow noopener">OpenAI Platform<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All OpenAI chat models including GPT-5, GPT-4o, GPT-4, GPT-3.5-turbo, and all future releases.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All OpenAI chat models including GPT-5.2, GPT-5, GPT-4o, and all future releases.</p>
|
||||
<table class="docutils align-default">
|
||||
<colgroup>
|
||||
<col style="width: 30.0%"/>
|
||||
|
|
@ -252,31 +243,27 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>GPT-5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-5</span></code></p></td>
|
||||
<tr class="row-even"><td><p>GPT-5.2</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-5.2</span></code></p></td>
|
||||
<td><p>Next-generation model (use any model name from OpenAI’s API)</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>GPT-4o</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-4o</span></code></p></td>
|
||||
<tr class="row-odd"><td><p>GPT-5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-5</span></code></p></td>
|
||||
<td><p>Latest multimodal model</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>GPT-4o mini</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-4o-mini</span></code></p></td>
|
||||
<td><p>Fast, cost-effective model</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>GPT-4</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-4</span></code></p></td>
|
||||
<tr class="row-odd"><td><p>GPT-4o</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-4o</span></code></p></td>
|
||||
<td><p>High-capability reasoning model</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>GPT-3.5 Turbo</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/gpt-3.5-turbo</span></code></p></td>
|
||||
<td><p>Balanced performance and cost</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>o3-mini</p></td>
|
||||
<tr class="row-even"><td><p>o3-mini</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/o3-mini</span></code></p></td>
|
||||
<td><p>Reasoning-focused model (preview)</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>o3</p></td>
|
||||
<tr class="row-odd"><td><p>o3</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">openai/o3</span></code></p></td>
|
||||
<td><p>Advanced reasoning model (preview)</p></td>
|
||||
</tr>
|
||||
|
|
@ -285,15 +272,15 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<p><strong>Configuration Examples:</strong></p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="c1"># Latest models (examples - use any OpenAI chat model)</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o-mini</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-5.2</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="nt">default</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">true</span>
|
||||
</span><span id="line-6">
|
||||
</span><span id="line-7"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-5</span>
|
||||
</span><span id="line-8"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-9">
|
||||
</span><span id="line-10"><span class="w"> </span><span class="c1"># Use any model name from OpenAI's API</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-5</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
|
|
@ -303,7 +290,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<p><strong>Provider Prefix:</strong> <code class="docutils literal notranslate"><span class="pre">anthropic/</span></code></p>
|
||||
<p><strong>API Endpoint:</strong> <code class="docutils literal notranslate"><span class="pre">/v1/messages</span></code></p>
|
||||
<p><strong>Authentication:</strong> API Key - Get your Anthropic API key from <a class="reference external" href="https://console.anthropic.com/settings/keys" rel="nofollow noopener">Anthropic Console<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Anthropic Claude models including Claude Sonnet 4, Claude 3.5 Sonnet, Claude 3.5 Haiku, Claude 3 Opus, and all future releases.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Anthropic Claude models including Claude Sonnet 4.5, Claude Opus 4.5, Claude Haiku 4.5, and all future releases.</p>
|
||||
<table class="docutils align-default">
|
||||
<colgroup>
|
||||
<col style="width: 30.0%"/>
|
||||
|
|
@ -317,43 +304,35 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>Claude Sonnet 4</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-sonnet-4</span></code></p></td>
|
||||
<td><p>Next-generation model (use any model name from Anthropic’s API)</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Claude 3.5 Sonnet</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-3-5-sonnet-20241022</span></code></p></td>
|
||||
<td><p>Latest high-performance model</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>Claude 3.5 Haiku</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-3-5-haiku-20241022</span></code></p></td>
|
||||
<td><p>Fast and efficient model</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Claude 3 Opus</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-3-opus-20240229</span></code></p></td>
|
||||
<tr class="row-even"><td><p>Claude Opus 4.5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-opus-4-5</span></code></p></td>
|
||||
<td><p>Most capable model for complex tasks</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>Claude 3 Sonnet</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-3-sonnet-20240229</span></code></p></td>
|
||||
<tr class="row-odd"><td><p>Claude Sonnet 4.5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-sonnet-4-5</span></code></p></td>
|
||||
<td><p>Balanced performance model</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Claude 3 Haiku</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-3-haiku-20240307</span></code></p></td>
|
||||
<td><p>Fastest model</p></td>
|
||||
<tr class="row-even"><td><p>Claude Haiku 4.5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-haiku-4-5</span></code></p></td>
|
||||
<td><p>Fast and efficient model</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Claude Sonnet 3.5</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">anthropic/claude-sonnet-3-5</span></code></p></td>
|
||||
<td><p>Complex agents and coding</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p><strong>Configuration Examples:</strong></p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="c1"># Latest models (examples - use any Anthropic chat model)</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-3-5-sonnet-20241022</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-opus-4-5</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-5">
|
||||
</span><span id="line-6"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-3-5-haiku-20241022</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-5</span>
|
||||
</span><span id="line-7"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-8">
|
||||
</span><span id="line-9"><span class="w"> </span><span class="c1"># Use any model name from Anthropic's API</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-haiku-4-5</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
|
|
@ -450,7 +429,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<p><strong>Provider Prefix:</strong> <code class="docutils literal notranslate"><span class="pre">groq/</span></code></p>
|
||||
<p><strong>API Endpoint:</strong> <code class="docutils literal notranslate"><span class="pre">/openai/v1/chat/completions</span></code> (transformed internally)</p>
|
||||
<p><strong>Authentication:</strong> API Key - Get your Groq API key from <a class="reference external" href="https://console.groq.com/keys" rel="nofollow noopener">Groq Console<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Groq chat models including Llama 3, Mixtral, Gemma, and all future releases.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Groq chat models including Llama 4, GPT OSS, Mixtral, Gemma, and all future releases.</p>
|
||||
<table class="docutils align-default">
|
||||
<colgroup>
|
||||
<col style="width: 30.0%"/>
|
||||
|
|
@ -464,27 +443,30 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>Llama 3.1 8B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/llama3-8b-8192</span></code></p></td>
|
||||
<tr class="row-even"><td><p>Llama 4 Maverick 17B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/llama-4-maverick-17b-128e-instruct</span></code></p></td>
|
||||
<td><p>Fast inference Llama model</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Llama 3.1 70B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/llama3-70b-8192</span></code></p></td>
|
||||
<td><p>Larger Llama model</p></td>
|
||||
<tr class="row-odd"><td><p>Llama 4 Scout 8B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/llama-4-scout-8b-128e-instruct</span></code></p></td>
|
||||
<td><p>Smaller Llama model</p></td>
|
||||
</tr>
|
||||
<tr class="row-even"><td><p>Mixtral 8x7B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/mixtral-8x7b-32768</span></code></p></td>
|
||||
<td><p>Mixture of experts model</p></td>
|
||||
<tr class="row-even"><td><p>GPT OSS 20B</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">groq/gpt-oss-20b</span></code></p></td>
|
||||
<td><p>Open source GPT model</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p><strong>Configuration Examples:</strong></p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama3-8b-8192</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama-4-maverick-17b-128e-instruct</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
|
||||
</span><span id="line-4">
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/mixtral-8x7b-32768</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/llama-4-scout-8b-128e-instruct</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
|
||||
</span><span id="line-7">
|
||||
</span><span id="line-8"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">groq/gpt-oss-20b</span>
|
||||
</span><span id="line-9"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GROQ_API_KEY</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
</section>
|
||||
|
|
@ -493,7 +475,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<p><strong>Provider Prefix:</strong> <code class="docutils literal notranslate"><span class="pre">gemini/</span></code></p>
|
||||
<p><strong>API Endpoint:</strong> <code class="docutils literal notranslate"><span class="pre">/v1beta/openai/chat/completions</span></code> (transformed internally)</p>
|
||||
<p><strong>Authentication:</strong> API Key - Get your Google AI API key from <a class="reference external" href="https://aistudio.google.com/app/apikey" rel="nofollow noopener">Google AI Studio<svg fill="currentColor" height="1em" stroke="none" viewbox="0 96 960 960" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M188 868q-11-11-11-28t11-28l436-436H400q-17 0-28.5-11.5T360 336q0-17 11.5-28.5T400 296h320q17 0 28.5 11.5T760 336v320q0 17-11.5 28.5T720 696q-17 0-28.5-11.5T680 656V432L244 868q-11 11-28 11t-28-11Z"></path></svg></a>.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Google Gemini chat models including Gemini 1.5 Pro, Gemini 1.5 Flash, and all future releases.</p>
|
||||
<p><strong>Supported Chat Models:</strong> All Google Gemini chat models including Gemini 3 Pro, Gemini 3 Flash, and all future releases.</p>
|
||||
<table class="docutils align-default">
|
||||
<colgroup>
|
||||
<col style="width: 30.0%"/>
|
||||
|
|
@ -507,22 +489,22 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr class="row-even"><td><p>Gemini 1.5 Pro</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">gemini/gemini-1.5-pro</span></code></p></td>
|
||||
<tr class="row-even"><td><p>Gemini 3 Pro</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">gemini/gemini-3-pro</span></code></p></td>
|
||||
<td><p>Advanced reasoning and creativity</p></td>
|
||||
</tr>
|
||||
<tr class="row-odd"><td><p>Gemini 1.5 Flash</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">gemini/gemini-1.5-flash</span></code></p></td>
|
||||
<tr class="row-odd"><td><p>Gemini 3 Flash</p></td>
|
||||
<td><p><code class="docutils literal notranslate"><span class="pre">gemini/gemini-3-flash</span></code></p></td>
|
||||
<td><p>Fast and efficient model</p></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
<p><strong>Configuration Examples:</strong></p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gemini/gemini-1.5-pro</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gemini/gemini-3-pro</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GOOGLE_API_KEY</span>
|
||||
</span><span id="line-4">
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gemini/gemini-1.5-flash</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">gemini/gemini-3-flash</span>
|
||||
</span><span id="line-6"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$GOOGLE_API_KEY</span>
|
||||
</span></code></pre></div>
|
||||
</div>
|
||||
|
|
@ -724,7 +706,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<h3>Amazon Bedrock<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#amazon-bedrock" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#amazon-bedrock'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||||
<p><strong>Provider Prefix:</strong> <code class="docutils literal notranslate"><span class="pre">amazon_bedrock/</span></code></p>
|
||||
<dl class="simple">
|
||||
<dt><strong>API Endpoint:</strong> Arch automatically constructs the endpoint as:</dt><dd><ul class="simple">
|
||||
<dt><strong>API Endpoint:</strong> Plano automatically constructs the endpoint as:</dt><dd><ul class="simple">
|
||||
<li><p>Non-streaming: <code class="docutils literal notranslate"><span class="pre">/model/{model-id}/converse</span></code></p></li>
|
||||
<li><p>Streaming: <code class="docutils literal notranslate"><span class="pre">/model/{model-id}/converse-stream</span></code></p></li>
|
||||
</ul>
|
||||
|
|
@ -894,7 +876,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<h3>Routing Preferences<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#routing-preferences" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#routing-preferences'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h3>
|
||||
<p>Configure routing preferences for dynamic model selection:</p>
|
||||
<div class="highlight-yaml notranslate"><div class="highlight"><pre><span></span><code><span id="line-1"><span class="nt">llm_providers</span><span class="p">:</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-4o</span>
|
||||
</span><span id="line-2"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">openai/gpt-5.2</span>
|
||||
</span><span id="line-3"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$OPENAI_API_KEY</span>
|
||||
</span><span id="line-4"><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
|
||||
</span><span id="line-5"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">complex_reasoning</span>
|
||||
|
|
@ -902,7 +884,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</span><span id="line-7"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">code_review</span>
|
||||
</span><span id="line-8"><span class="w"> </span><span class="nt">description</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">reviewing and analyzing existing code for bugs and improvements</span>
|
||||
</span><span id="line-9">
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-3-5-sonnet-20241022</span>
|
||||
</span><span id="line-10"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">model</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">anthropic/claude-sonnet-4-5</span>
|
||||
</span><span id="line-11"><span class="w"> </span><span class="nt">access_key</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">$ANTHROPIC_API_KEY</span>
|
||||
</span><span id="line-12"><span class="w"> </span><span class="nt">routing_preferences</span><span class="p">:</span>
|
||||
</span><span id="line-13"><span class="w"> </span><span class="p p-Indicator">-</span><span class="w"> </span><span class="nt">name</span><span class="p">:</span><span class="w"> </span><span class="l l-Scalar l-Scalar-Plain">creative_writing</span>
|
||||
|
|
@ -914,14 +896,14 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<section id="model-selection-guidelines">
|
||||
<h2>Model Selection Guidelines<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#model-selection-guidelines" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#model-selection-guidelines'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
<p><strong>For Production Applications:</strong>
|
||||
- <strong>High Performance</strong>: OpenAI GPT-4o, Anthropic Claude 3.5 Sonnet
|
||||
- <strong>Cost-Effective</strong>: OpenAI GPT-4o mini, Anthropic Claude 3.5 Haiku
|
||||
- <strong>High Performance</strong>: OpenAI GPT-5.2, Anthropic Claude Sonnet 4.5
|
||||
- <strong>Cost-Effective</strong>: OpenAI GPT-5, Anthropic Claude Haiku 4.5
|
||||
- <strong>Code Tasks</strong>: DeepSeek Coder, Together AI Code Llama
|
||||
- <strong>Local Deployment</strong>: Ollama with Llama 3.1 or Code Llama</p>
|
||||
<p><strong>For Development/Testing:</strong>
|
||||
- <strong>Fast Iteration</strong>: Groq models (optimized inference)
|
||||
- <strong>Local Testing</strong>: Ollama models
|
||||
- <strong>Cost Control</strong>: Smaller models like GPT-4o mini or Mistral Small</p>
|
||||
- <strong>Cost Control</strong>: Smaller models like GPT-4o or Mistral Small</p>
|
||||
</section>
|
||||
<section id="see-also">
|
||||
<h2>See Also<a @click.prevent="window.navigator.clipboard.writeText($el.href); $el.setAttribute('data-tooltip', 'Copied!'); setTimeout(() => $el.setAttribute('data-tooltip', 'Copy link to this element'), 2000)" aria-label="Copy link to this element" class="headerlink" data-tooltip="Copy link to this element" href="#see-also" x-intersect.margin.0%.0%.-70%.0%="activeSection = '#see-also'"><svg height="1em" viewbox="0 0 24 24" width="1em" xmlns="http://www.w3.org/2000/svg"><path d="M3.9 12c0-1.71 1.39-3.1 3.1-3.1h4V7H7c-2.76 0-5 2.24-5 5s2.24 5 5 5h4v-1.9H7c-1.71 0-3.1-1.39-3.1-3.1zM8 13h8v-2H8v2zm9-6h-4v1.9h4c1.71 0 3.1 1.39 3.1 3.1s-1.39 3.1-3.1 3.1h-4V17h4c2.76 0 5-2.24 5-5s-2.24-5-5-5z"></path></svg></a></h2>
|
||||
|
|
@ -940,7 +922,7 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
<svg class="mr-2 h-4 w-4" fill="none" height="24" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" viewbox="0 0 24 24" width="24" xmlns="http://www.w3.org/2000/svg">
|
||||
<polyline points="15 18 9 12 15 6"></polyline>
|
||||
</svg>
|
||||
LLM Providers
|
||||
Model (LLM) Providers
|
||||
</a>
|
||||
</div>
|
||||
<div class="ml-auto">
|
||||
|
|
@ -995,12 +977,12 @@ Any provider that implements the OpenAI API interface can be configured using cu
|
|||
</div><footer class="py-6 border-t border-border md:py-0">
|
||||
<div class="container flex flex-col items-center justify-between gap-4 md:h-24 md:flex-row">
|
||||
<div class="flex flex-col items-center gap-4 px-8 md:flex-row md:gap-2 md:px-0">
|
||||
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Dec 23, 2025. </p>
|
||||
<p class="text-sm leading-loose text-center text-muted-foreground md:text-left">© 2025, Katanemo Labs, Inc Last updated: Dec 24, 2025. </p>
|
||||
</div>
|
||||
</div>
|
||||
</footer>
|
||||
</div>
|
||||
<script src="../../_static/documentation_options.js?v=3bad885e"></script>
|
||||
<script src="../../_static/documentation_options.js?v=8cf1ab6b"></script>
|
||||
<script src="../../_static/doctools.js?v=9bcbadda"></script>
|
||||
<script src="../../_static/sphinx_highlight.js?v=dc90522c"></script>
|
||||
<script defer="defer" src="../../_static/theme.js?v=073f68d9"></script>
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue