Skip to main content

​
One Format, All Providers

The beauty of Bifrost lies in its unified interface: regardless of whether you’re using OpenAI, Anthropic, AWS Bedrock, Google Vertex, or any other supported provider, you always get the same response format. This means your application logic never needs to change when switching providers. Bifrost standardizes all provider responses to follow the OpenAI-compatible structure, so you can write your code once and use it with any provider.

​
How It Works

When you make a request to any provider through Bifrost, the response always follows the same structure - the familiar OpenAI format that most developers already know. Behind the scenes, Bifrost handles all the complexity of translating between different provider formats.
  • Gateway
  • Go SDK
# Same response format regardless of provider
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

# Returns OpenAI-compatible format:
{
  "id": "chatcmpl-123",
  "object": "chat.completion", 
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 9,
    "total_tokens": 19
  }
}

​
Provider Support Matrix

The following table summarizes which operations are supported by each provider via Bifrost’s unified interface.
ProviderModelsTextText (stream)ChatChat (stream)ResponsesResponses (stream)EmbeddingsTTSTTS (stream)STTSTT (stream)
Anthropic (anthropic/<model>)YesYesNoYesYesYesYesNoNoNoNoNo
Azure OpenAI (azure/<model>)YesYesYesYesYesYesYesYesNoNoNoNo
Bedrock (bedrock/<model>)YesYesNoYesYesYesYesYesNoNoNoNo
Cerebras (cerebras/<model>)YesYesYesYesYesYesYesNoNoNoNoNo
Cohere (cohere/<model>)YesNoNoYesYesYesYesYesNoNoNoNo
Gemini (gemini/<model>)YesNoNoYesYesYesYesYesYesYesYesYes
Groq (groq/<model>)YesNoNoYesYesYesYesNoNoNoNoNo
Mistral (mistral/<model>)YesNoNoYesYesYesYesYesNoNoNoNo
Ollama (ollama/<model>)YesYesYesYesYesYesYesYesNoNoNoNo
OpenAI (openai/<model>)YesYesYesYesYesYesYesYesYesYesYesYes
OpenRouter (openrouter/<model>)YesYesYesYesYesYesYesNoNoNoNoNo
Parasail (parasail/<model>)YesYesYesYesYesYesYesNoNoNoNoNo
SGL (sgl/<model>)YesYesYesYesYesYesYesYesNoNoNoNo
Vertex AI (vertex/<model>)YesNoNoYesYesYesYesYesNoNoNoNo
Notes:
  • “Models” refers to the list models operation (/v1/models).
  • “Text” refers to the classic text completion interface (/v1/completions).
  • “Responses” refers to the OpenAI-style Responses API (/v1/responses). Non-OpenAI providers map this to their native chat API under the hood.
  • TTS corresponds to /v1/audio/speech and STT to /v1/audio/transcriptions.

​
The Power of Consistency

This unified approach means you can:
  • Switch providers instantly without changing application logic
  • Mix and match providers using fallbacks and load balancing
  • Future-proof your code as new providers get added
  • Use familiar OpenAI patterns regardless of the underlying provider
Whether you’re calling OpenAI’s GPT-4, Anthropic’s Claude, or AWS Bedrock’s models, your application sees the exact same response structure. This consistency is what makes Bifrost’s advanced features like automatic fallbacks and multi-provider load balancing possible.

​
Provider Transparency

While the response format stays consistent, Bifrost doesn’t hide which provider actually handled your request. Provider information is always available in the extra_fields section, along with any provider-specific metadata you might need for debugging or analytics. This gives you the best of both worlds: consistent application logic with full transparency into the underlying provider behavior. Learn more about configuring provider transparency: