Bifrost

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

docker run -p 8080:8080 -v $(pwd)/data:/app/data maximhq/bifrost

npx -y @maximhq/bifrost

Quick Start

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

{
  "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
        }
      }
    }
  }
}

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?"}]
  }'

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:

EDEN_AI_API_KEY=your_api_key_here

Next Steps

Chat Completions - Core LLM endpoint
List LLM Models - Browse available providers and models
OpenAI SDK (Python) - Direct SDK usage

V3 Documentation

Quick Start

Overview

LLMs

Expert Models

General

Organization

Data Governance

Integrations

Overview

Installation

Quick Start

Available Models

Routing & Fallbacks

Environment Variables

Next Steps

​Overview

​Installation

​Quick Start

​Available Models

​Routing & Fallbacks

​Environment Variables

​Next Steps

Overview

Installation

Quick Start

Available Models

Routing & Fallbacks

Environment Variables

Next Steps