Files

1 line
3.2 KiB
JSON

{"text":["Models","NVIDIA","switchyard","Switchyard","Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests.","Get API key","Try in Chat","Specifications","Context Window","1M","Modalities","text","Price","No published rate","Model ID","nvidia/switchyard","Quick start","Get an API key →","TypeScript","Python","cURL","Go","import","OpenAI","from","openai","const","client = new","({","apiKey","process.env.HANZO_API_KEY","baseURL","https://api.hanzo.ai/v1","})","response =","await","client.chat.completions.","create","model","messages","[{","role","user","content","Hello!","}]","console.","log","response.choices",".message.content","client = OpenAI","api_key=os","environ","HANZO_API_KEY","],","base_url=","response = client","chat","completions","model=","messages=","print","response","choices","].","message","curl","https://api.hanzo.ai/v1/chat/completions","-H","Content-Type: application/json","Authorization: Bearer","-d","\"model\": \"nvidia/switchyard\",","\"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]","package","main","context","fmt","os","github.com/sashabaranov/go-openai","func","()","cfg := openai","DefaultConfig","Getenv","))","cfg","BaseURL =","client := openai","NewClientWithConfig","resp","_ := client","CreateChatCompletion","Background","(),","ChatCompletionRequest","Model","Messages","[]","ChatCompletionMessage","Role","ChatMessageRoleUser","Content","},","Println","Choices","Message","More from NVIDIA","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...","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...","Nemotron 3 Super","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...","Nemotron 3 Ultra","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...","Nemotron 3 Ultra (free)","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...","View all NVIDIA models →","Use Switchyard via Hanzo AI","One API key. Every major model. OpenAI-compatible. Start free.","Get an API key","Browse All Models"],"links":["/models","/models/nvidia","https://platform.hanzo.ai/api-keys","/chat","/models/nvidia/nemotron-3-nano-30b-a3b","/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free","/models/nvidia/nemotron-3-super-120b-a12b","/models/nvidia/nemotron-3-ultra-550b-a55b","/models/nvidia/nemotron-3-ultra-550b-a55b:free","/models/nvidia/nemotron-3.5-content-safety"]}