Files

113 lines
4.2 KiB
JSON

[
[
{
"a": "Models",
"href": "/models"
},
{
"a": "NVIDIA",
"href": "/models/nvidia"
},
{
"h1": "Switchyard"
},
{
"p": "Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests."
},
{
"a": "Get API key",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"a": "Try in Chat",
"href": "/chat"
}
],
[
{
"h2": "Specifications"
}
],
[
{
"h2": "Quick start"
},
{
"a": "Get an API key →",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"button": "TypeScript"
},
{
"button": "Python"
},
{
"button": "cURL"
},
{
"button": "Go"
},
{
"code": "import OpenAI from ' openai ' const client = new OpenAI ({ apiKey : process.env.HANZO_API_KEY , baseURL : ' https://api.hanzo.ai/v1 ' }) const response = await client.chat.completions. create ({ model : ' nvidia/switchyard ' , messages : [{ role : ' user ' , content : ' Hello! ' }] }) console. log ( response.choices [ 0 ] .message.content )"
},
{
"code": "from openai import OpenAI client = OpenAI ( api_key=os . environ [ \" HANZO_API_KEY \" ], base_url= \" https://api.hanzo.ai/v1 \" ) response = client . chat . completions . create ( model= \" nvidia/switchyard \" , messages= [{ \" role \" : \" user \" , \" content \" : \" Hello! \" }] ) print ( response . choices [ 0 ]. message . content )"
},
{
"code": "curl https://api.hanzo.ai/v1/chat/completions \\ -H \" Content-Type: application/json \" \\ -H \" Authorization: Bearer $ HANZO_API_KEY \" \\ -d ' { \"model\": \"nvidia/switchyard\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}] } '"
},
{
"code": "package main import ( \" context \" \" fmt \" \" os \" \" github.com/sashabaranov/go-openai \" ) func main () { cfg := openai . DefaultConfig ( os . Getenv ( \" HANZO_API_KEY \" )) cfg . BaseURL = \" https://api.hanzo.ai/v1 \" client := openai . NewClientWithConfig ( cfg ) resp , _ := client . CreateChatCompletion ( context . Background (), openai . ChatCompletionRequest { Model : \" nvidia/switchyard \" , Messages : [] openai . ChatCompletionMessage { { Role : openai . ChatMessageRoleUser , Content : \" Hello! \" }, }, }, ) fmt . Println ( resp . Choices [ 0 ]. Message . Content ) }"
}
],
[
{
"h2": "More from NVIDIA"
},
{
"a": "Nemotron 3 Nano 30B A3B 262K NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...",
"href": "/models/nvidia/nemotron-3-nano-30b-a3b"
},
{
"a": "Nemotron 3 Nano Omni (free) 256K NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, video, and...",
"href": "/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free"
},
{
"a": "Nemotron 3 Super 1M NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...",
"href": "/models/nvidia/nemotron-3-super-120b-a12b"
},
{
"a": "Nemotron 3 Ultra 262K NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"href": "/models/nvidia/nemotron-3-ultra-550b-a55b"
},
{
"a": "Nemotron 3 Ultra (free) 1M NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...",
"href": "/models/nvidia/nemotron-3-ultra-550b-a55b:free"
},
{
"a": "Nemotron 3.5 Content Safety 131K NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses from LLMs and VLMs, accepting...",
"href": "/models/nvidia/nemotron-3.5-content-safety"
},
{
"a": "View all NVIDIA models →",
"href": "/models/nvidia"
}
],
[
{
"h2": "Use Switchyard via Hanzo AI"
},
{
"p": "One API key. Every major model. OpenAI-compatible. Start free."
},
{
"a": "Get an API key",
"href": "https://platform.hanzo.ai/api-keys"
},
{
"a": "Browse All Models",
"href": "/models"
}
]
]