Available Models

Access all major LLM providers through a single API Use any model from Anthropic, OpenAI, DeepSeek, Google, and more.

Model Format

Models are specified in the format: provider/model-name

{
  "model": "anthropic/claude-sonnet-4-5-20250929"
}

Anthropic Models

Model	Context	Input Cost	Output Cost	Best For
claude-opus-4-20250514	200k	$15.00/1M	$75.00/1M	Complex reasoning
claude-sonnet-4-5-20250929	200k	$3.00/1M	$15.00/1M	Balance of quality/speed
claude-haiku-4-5-20251001	200k	$0.25/1M	$1.25/1M	Fast, cost-effective

response = client.chat.completions.create(
    model="anthropic/claude-sonnet-4-5-20250929",
    messages=[...]
)

OpenAI Models

Model	Context	Input Cost	Output Cost	Best For
gpt-4o	128k	$2.50/1M	$10.00/1M	Multimodal, general purpose
gpt-4o-mini	128k	$0.15/1M	$0.60/1M	Fast, cost-effective
gpt-4-turbo	128k	$10.00/1M	$30.00/1M	Complex tasks

response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[...]
)

DeepSeek Models

Model	Context	Input Cost	Output Cost	Best For
deepseek-chat	128k	$0.14/1M	$0.28/1M	General chat
deepseek-reasoner	64k	$0.55/1M	$2.19/1M	Complex reasoning

response = client.chat.completions.create(
    model="deepseek-chat/deepseek-chat",
    messages=[...]
)

Google Gemini Models

Model	Context	Input Cost	Output Cost	Best For
gemini-2.5-pro	1M	$1.25/1M	$10.00/1M	Complex tasks
gemini-2.5-flash	1M	$0.075/1M	$0.30/1M	Fast, general purpose
gemini-2.0-flash	1M	$0.075/1M	$0.30/1M	Fast, cost-effective

response = client.chat.completions.create(
    model="google-gemini/gemini-2.5-flash",
    messages=[...]
)

Choosing the Right Model

For Quality

• claude-opus-4-20250514 - Best for complex reasoning
• gpt-4o - Best for multimodal tasks
• gemini-2.5-pro - Best for very large contexts

For Value

• claude-haiku-4-5-20251001 - Fast and cheap
• gpt-4o-mini - Good balance
• deepseek-chat - Lowest cost

For Speed

• claude-haiku-4-5-20251001 - Fastest Anthropic model
• gemini-2.0-flash - Fastest overall
• deepseek-chat - Quick responses

Model Availability

Models are subject to:

• Provider uptime
• Your Virtual Key configuration
• Regional availability

List Models Endpoint

Get the list of available models:

curl http://localhost:8084/v1/models \
  -H "x-bf-vk: sk-bf-YOUR_VIRTUAL_KEY"

Response:

{
  "object": "list",
  "data": [
    {
      "id": "anthropic/claude-opus-4-20250514",
      "object": "model",
      "owned_by": "anthropic"
    },
    {
      "id": "anthropic/claude-sonnet-4-5-20250929",
      "object": "model",
      "owned_by": "anthropic"
    }
  ]
}

---

Use any model from any provider through a single API.