> ## 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.

# Bifrost

> Use Bifrost with Eden AI to route to 500+ AI models through one OpenAI-compatible gateway.

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={"Bifrost"} description={"Use Bifrost with Eden AI to route to 500+ AI models through one OpenAI-compatible gateway."} path="v3/integrations/bifrost" articleSection="AI Gateway" about={"LLM Gateway Integration"} proficiencyLevel="Intermediate" keywords={["Eden AI", "AI API", "Bifrost", "LLM Gateway", "Go"]} datePublished="2026-07-16T00:00:00Z" dateModified="2026-07-16T00:00:00Z" />

Use Bifrost with Eden AI to route to 500+ AI models through one OpenAI-compatible gateway.

## Overview

Bifrost is a high-performance open-source LLM gateway (Go) that adds routing, fallbacks, load-balancing and governance across providers. Because Eden AI is fully OpenAI-compatible, you add it through Bifrost's **Custom Provider** configuration — no build and no fork — and route to models from OpenAI, Anthropic, Google, Cohere, Meta and more behind one key, with EU-based, GDPR-aligned inference.

## Installation

<CodeGroup>
  ```bash Docker theme={null}
  docker run -p 8080:8080 -v $(pwd)/data:/app/data maximhq/bifrost
  ```

  ```bash npx theme={null}
  npx -y @maximhq/bifrost
  ```
</CodeGroup>

## Quick Start

Add Eden AI as a Custom Provider in your `config.json`, then point any request at it:

<CodeGroup>
  ```json config.json theme={null}
  {
    "providers": {
      "edenai": {
        "keys": [
          { "name": "edenai-key", "value": "env.EDEN_AI_API_KEY", "models": ["*"], "weight": 1.0 }
        ],
        "network_config": { "base_url": "https://api.edenai.run/v3" },
        "custom_provider_config": {
          "base_provider_type": "openai",
          "allowed_requests": {
            "chat_completion": true,
            "chat_completion_stream": true,
            "embedding": true
          }
        }
      }
    }
  }
  ```

  ```bash curl theme={null}
  curl -X POST http://localhost:8080/v1/chat/completions \
    -H "Content-Type: application/json" \
    -d '{
      "model": "edenai/openai/gpt-5.5",
      "messages": [{"role": "user", "content": "Hello! How are you?"}]
    }'
  ```
</CodeGroup>

You can also add the provider at runtime via `POST /api/providers` or from the Bifrost web UI under **Model Providers** — no restart needed.

## Available Models

Call any Eden AI model through Bifrost as `edenai/<provider>/<model>`:

**OpenAI**

* `edenai/openai/gpt-5.5`
* `edenai/openai/gpt-5-mini`

**Anthropic**

* `edenai/anthropic/claude-sonnet-5`
* `edenai/anthropic/claude-haiku-4-5`

**Google**

* `edenai/google/gemini-2.5-pro`
* `edenai/google/gemini-3.5-flash`

**Mistral**

* `edenai/mistral/mistral-large-2512`
* `edenai/mistral/mistral-small-2603`

## Routing & Fallbacks

Because Eden AI is a standard Bifrost provider, it participates in Bifrost's reliability features — weighted keys, load-balancing and provider fallbacks. Add Eden AI alongside other providers and let Bifrost route or fall back to it as needed, all through the same OpenAI-compatible endpoint.

## Environment Variables

Bifrost reads the key referenced as `env.EDEN_AI_API_KEY` in `config.json` from the environment:

<CodeGroup>
  ```bash .env theme={null}
  EDEN_AI_API_KEY=your_api_key_here
  ```
</CodeGroup>

## 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
* [OpenAI SDK (Python)](/docs/v3/integrations/openai-sdk-python) - Direct SDK usage