Providers - Maxim Docs

Supported Providers

Provider	Models	Features	Enterprise
OpenAI	GPT-4o, GPT-4 Turbo, GPT-4, GPT-3.5	Function calling, streaming, vision	✅
Anthropic	Claude 3.5 Sonnet, Claude 3 Opus/Haiku	Tool use, vision, 200K context	✅
Azure OpenAI	Enterprise GPT deployment	Private networks, compliance	✅
Amazon Bedrock	Claude, Titan, Cohere, Meta	Multi-model platform, VPC	✅
Google Vertex	Gemini Pro, PaLM, Codey	Enterprise AI platform	✅
Cohere	Command, Embed, Rerank	Enterprise NLP, multilingual	✅
Mistral	Mistral Large, Medium, Small	European AI, cost-effective	✅
Ollama	Llama, Mistral, CodeLlama	Local deployment, privacy	✅
Groq	Mixtral, Llama, Gemma	Enterprise AI platform	✅
SGLang	Qwen	Enterprise AI platform	✅

Provider Features Matrix

Feature	OpenAI	Anthropic	Azure	Bedrock	Vertex	Cohere	Mistral	Ollama	Groq	SGLang
Chat Completion	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
Function Calling	✅	✅	✅	✅	✅	❌	✅	✅	✅	✅
Streaming	✅	✅	✅	✅	✅	✅	✅	✅	✅	✅
Vision	✅	✅	✅	✅	✅	❌	✅	✅	❌	✅
JSON Mode	✅	✅	✅	✅	✅	❌	✅	✅	✅	✅
Custom Base URL	✅	✅	✅	❌	❌	✅	✅	✅	✅	✅
Proxy Support	✅	✅	✅	❌	❌	✅	✅	✅	✅	✅

Next Steps

Task	Documentation
Configure multiple API keys	Key Management
Set up networking & proxies	Networking
Optimize performance	Memory Management
Handle errors gracefully	Error Handling
Go Package deep dive	Go Package Usage
HTTP Transport setup	HTTP Transport Usage

Tip: All responses from Bifrost follow OpenAI’s format regardless of the underlying provider, ensuring consistent integration across your application.

⌘I