{"uid":"cap_nvj8xy2h2vlVK-v5oNdtq","slug":"agent-hub-nvidia-nemotron-3-120b-chat-completions-fbeccc5d","name":"Agent Hub – NVIDIA Nemotron 3 120B Chat Completions","description":"OpenAI-compatible chat completions on NVIDIA Nemotron 3 120B, agentic reasoning with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/nemotron and pay $0.01 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Also callable as GET with the same fields as query parameters.","url":"https://agents.torbrooknews.com/v1/nemotron/chat/completions?utm_source=zero.xyz","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET"],"type":"string"},"queryParams":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string","description":"User message"},"system":{"type":"string","description":"Optional system message"},"max_tokens":{"type":"integer"},"temperature":{"type":"number"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_Fn6q94iI-dok7qU3YOHNJ","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Provides OpenAI-compatible chat completions with agentic reasoning and tool calling powered by NVIDIA Nemotron 3 120B, payable at $0.01 per request via x402.","exampleAgentPrompt":"Ask Nemotron 3 120B to reason through this multi-step problem: given the following list of tasks and deadlines, create a prioritized plan with justifications for each decision, using a system prompt that emphasizes concise, structured output.","exampleUseCases":[{"title":"Agentic task planning with tool calls","prompt":"I need you to use the Nemotron 120B model to break down this project into subtasks, call the calendar tool to schedule each one, and return a structured plan — system prompt should say 'you are a precise project manager'."},{"title":"Pay-per-call LLM for a one-off analysis","prompt":"Without setting up an API key subscription, use Nemotron 3 120B to analyze this business proposal and tell me the top three risks — just charge $0.01 for the call."},{"title":"Automated agent reasoning loop","prompt":"Run a reasoning chain on Nemotron 120B: given this customer support transcript, identify the root cause, suggest a resolution, and format the output as JSON — set max output to 2048 tokens and temperature to 0.2."}],"resultDescription":"Returns an OpenAI-compatible chat completion object containing the assistant's message, optional tool call payloads, and usage metadata. Streaming is supported. Maximum 4096 output tokens per response.","failureModes":["Payment not received or x402 authentication fails — request rejected with 402 status","Prompt exceeds model context window — returns a context length error","Invalid JSON in query parameters when using GET method — 400 bad request","Tool schema malformed — model returns error or ignores tool calls","Rate limiting or upstream NVIDIA inference timeout — 5xx response"],"whenToPreferThis":"Choose this endpoint when you need a very large (120B parameter) model with strong agentic reasoning and tool calling, want OpenAI SDK drop-in compatibility, prefer micropayment-per-call billing over API key subscriptions, and do not want to manage credentials. Prefer over smaller sibling models (Llama 70B, GLM 4.7 Flash) when task complexity demands stronger reasoning.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:45:47.887Z","isFirstParty":false,"canonicalSlug":"agent-hub-nvidia-nemotron-3-120b-chat-completions-fbeccc5d"}