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

# Plano

> Route Plano, the AI-native proxy for agentic apps, through Eden AI and reach 500+ models behind one key.

export const TechArticleSchema = ({title, description, path, articleSection, about, proficiencyLevel = "Beginner", dependencies, keywords = [], datePublished, dateModified, image, inLanguage = "en"}) => {
  const baseUrl = "https://www.edenai.co/docs";
  const canonicalUrl = `${baseUrl}/${path}`.replace(/\/+$/, "");
  const ogParams = new URLSearchParams({
    division: articleSection || "",
    title: title || "",
    description: description || ""
  });
  const resolvedImage = image || `https://edenai.mintlify.app/_mintlify/api/og?${ogParams.toString()}`;
  const data = {
    "@context": "https://schema.org",
    "@type": "TechArticle",
    "@id": `${canonicalUrl}#techarticle`,
    mainEntityOfPage: {
      "@type": "WebPage",
      "@id": canonicalUrl
    },
    headline: title,
    name: title,
    description: description,
    url: canonicalUrl,
    inLanguage: inLanguage,
    isPartOf: {
      "@type": "WebSite",
      name: "Eden AI Documentation",
      url: baseUrl
    },
    author: [{
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/"
    }],
    publisher: {
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/",
      logo: {
        "@type": "ImageObject",
        url: "https://www.edenai.co/assets/logo.png"
      }
    }
  };
  if (articleSection) data.articleSection = articleSection;
  if (about) data.about = {
    "@type": "Thing",
    name: about
  };
  if (proficiencyLevel) data.proficiencyLevel = proficiencyLevel;
  if (dependencies) data.dependencies = dependencies;
  if (keywords && keywords.length) data.keywords = keywords;
  if (datePublished) data.datePublished = datePublished;
  if (dateModified) data.dateModified = dateModified;
  data.image = Array.isArray(resolvedImage) ? resolvedImage : [resolvedImage];
  const json = JSON.stringify(data);
  const schemaId = `techarticle-${canonicalUrl}`;
  React.useEffect(() => {
    if (typeof document === "undefined") return;
    document.querySelectorAll(`script[data-schema-id="${schemaId}"]`).forEach(n => n.remove());
    const script = document.createElement("script");
    script.type = "application/ld+json";
    script.dataset.schemaId = schemaId;
    script.textContent = json;
    document.head.appendChild(script);
    return () => script.remove();
  }, [json, schemaId]);
  return null;
};

<TechArticleSchema title={"Plano"} description={"Route Plano, the AI-native proxy for agentic apps, through Eden AI and reach 500+ models behind one key."} path="v3/integrations/plano" articleSection="AI Gateway" about={"LLM Gateway Integration"} proficiencyLevel="Intermediate" keywords={["Eden AI", "AI API", "Plano", "LLM Gateway", "Katanemo"]} datePublished="2026-08-31T00:00:00Z" dateModified="2026-08-31T00:00:00Z" />

Route [Plano](https://github.com/katanemo/plano), the AI-native proxy and data plane for agentic apps, through Eden AI and reach 500+ models behind one key.

## Overview

Plano is a Rust proxy that sits in front of your models and handles routing, observability and guardrails. Eden AI is a **built-in provider**, so there is no plugin to write:

* **500+ models**: reach OpenAI, Anthropic, Google, Mistral and more through one key
* **Wildcard routing**: one entry covers the whole Eden AI catalogue, with no per-model declaration
* **Client shape translation**: Plano accepts requests in either the OpenAI or the Anthropic shape and translates both to Eden AI's OpenAI-compatible endpoint
* **EU endpoint**: point the provider at `api.eu.edenai.run` when you have data-residency requirements

Plano treats Eden AI the way it treats OpenRouter and Vercel, as a broad multi-vendor gateway. It therefore ships **no hardcoded model list** for it and reads the catalogue from Eden AI instead.

## Prerequisites

* Plano installed. See the [Plano repository](https://github.com/katanemo/plano)
* An Eden AI API key from [app.edenai.run](https://app.edenai.run) → **API Keys**

## Setup

### 1. Declare Eden AI in your Plano config

The wildcard form covers the whole catalogue in a single entry:

<CodeGroup>
  ```yaml config.yaml theme={null}
  version: v0.4.0

  listeners:
    - name: llm
      type: model
      port: 12000

  model_providers:
    - model: edenai/*
      base_url: https://api.edenai.run/v3
      passthrough_auth: true
  ```
</CodeGroup>

To pin specific models instead, name them and supply the key from the environment:

<CodeGroup>
  ```yaml config.yaml theme={null}
  model_providers:
    - model: edenai/anthropic/claude-sonnet-latest
      access_key: $EDENAI_API_KEY
      base_url: https://api.edenai.run/v3
      default: true

    - model: edenai/openai/gpt-5-mini
      access_key: $EDENAI_API_KEY
      base_url: https://api.edenai.run/v3
  ```
</CodeGroup>

### 2. Export your key

<CodeGroup>
  ```bash Terminal theme={null}
  export EDENAI_API_KEY="your_api_key_here"
  ```
</CodeGroup>

### 3. Start Plano

<CodeGroup>
  ```bash Terminal theme={null}
  planoai up
  ```
</CodeGroup>

## Model naming

Eden AI model IDs are already `vendor/model`, so a full reference in Plano has **three** segments, `edenai/<vendor>/<model>`. The provider key is spelled exactly `edenai`; Plano rejects `eden_ai`.

The live catalogue is public and needs no key, so you can browse it before choosing:

<CodeGroup>
  ```bash cURL theme={null}
  curl https://api.edenai.run/v3/models
  ```
</CodeGroup>

Read the catalogue rather than copying a list from a guide, since IDs are retired over time. `anthropic/claude-sonnet-latest` is an alias that always resolves to the current Sonnet, which makes it a safe default.

## Routing preferences

Plano can pick between models per request. Eden AI models work in `routing_preferences` like any other:

<CodeGroup>
  ```yaml config.yaml theme={null}
  routing_preferences:
    - name: complex_reasoning
      description: multi-step analysis or detailed explanations
      models:
        - edenai/anthropic/claude-sonnet-latest
        - edenai/openai/gpt-5-mini

    - name: cheap_and_fast
      description: short answers, classification, extraction
      models:
        - edenai/mistral/mistral-small-latest
  ```
</CodeGroup>

## EU data residency

Point the provider at the EU gateway:

<CodeGroup>
  ```yaml config.yaml theme={null}
  model_providers:
    - model: edenai/*
      base_url: https://api.eu.edenai.run/v3
      passthrough_auth: true
  ```
</CodeGroup>

The EU endpoint serves the subset of the catalogue available in the EU, so a model that works on the global endpoint is not guaranteed to be reachable through it.

## Troubleshooting

### `401 Unauthorized`

Check that `EDENAI_API_KEY` is exported in the environment Plano runs from, and that the value is an Eden AI key rather than a vendor key. With `passthrough_auth: true` the key travels from the client instead, so verify what your client sends.

### Provider not recognised

The provider key is `edenai`, not `eden_ai` and not `eden-ai`. Plano validates it strictly.

### `model not found`

Copy the identifier exactly as `GET /v3/models` returns it, and keep all three segments, `edenai/<vendor>/<model>`.

## Next Steps

* [Chat Completions](/docs/v3/llms/chat-completions) - Core LLM endpoint
* [List LLM Models](/docs/v3/llms/listing-models) - Browse available providers and models
* [Bifrost](/docs/v3/integrations/bifrost) - Another gateway in front of Eden AI
* [open-connector](/docs/v3/integrations/open-connector) - Self-hosted gateway on Eden AI