{"uid":"cap_eODf-_ZO6NWQd03O6C-uF","slug":"x402-nvidia-nim-ai-models-api-streaming-chat-completions-e3ab9d1d","name":"X402-NVIDIA NIM AI Models API – Streaming Chat Completions","description":"Access 48+ NVIDIA NIM AI models via x402 micropayments. Chat completions, vision, safety, translation, and more.","url":"https://x402-nvidia.vercel.app/api/streampetr","method":"POST","headers":{},"bodySchema":null,"responseSchema":{"type":"object","example":{"choices":[{"message":{"role":"assistant","content":"Hello!"}}]},"properties":{"choices":{"type":"array","description":"Model responses"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.082553","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":"$0.082553/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.082553","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.082553","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_6VtyKag166GypalvBsZ7c","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.082553","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Streams AI chat completion responses from NVIDIA NIM models via x402 micropayment-gated API endpoint","exampleAgentPrompt":"Send a chat message to an NVIDIA NIM AI model asking 'What are the key differences between transformer and diffusion models?' and stream back the response — pay per call using x402.","exampleUseCases":[{"title":"Real-time customer support chatbot","prompt":"I need you to handle a customer question about our product warranty. Call an NVIDIA NIM model to draft a helpful response, stream it back to me, and charge only for what we use via x402 micropayments."},{"title":"Content moderation for user uploads","prompt":"Check if this user-submitted comment is safe and appropriate. Use an NVIDIA safety model through x402 to analyze it, stream back the safety assessment, and we'll pay only per check."},{"title":"Multi-language customer feedback analysis","prompt":"We got feedback in three different languages. Run each through an NVIDIA NIM translation model via x402 to convert them to English, stream the results back, and bill us per translation only."}],"resultDescription":"A streaming JSON response containing an array of choices, each with an assistant message including role and content fields — the generated AI model reply to the submitted prompt.","failureModes":["Payment not included or insufficient USDC causes 402 Payment Required response","Invalid or malformed choices array in request body causes 400 Bad Request","Requested NVIDIA NIM model unavailable or quota exceeded causes 503 or 429 error","Network timeout if streaming response takes too long","Missing required message fields causes parsing error"],"whenToPreferThis":"Choose this endpoint when you need on-demand, pay-per-call access to NVIDIA NIM AI models (including vision, safety, and translation models) without managing subscriptions or API keys — ideal for agents that need cost-controlled, per-inference billing via x402 USDC micropayments and require streaming completions from NVIDIA-hosted models.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:45:49.736Z","isFirstParty":false}