{"uid":"cap_KIWOLGrwf7JR-M_eoxQI9","slug":"minichan-nvidia-nim-minimax-m3-chat-api-3517f140","name":"MiniChan — NVIDIA NIM MiniMax-M3 Chat API","description":"NVIDIA NIM MiniMax-M3 (428B MoE) powered API for AI agents. 15 multimodal endpoints — text, vision, code, reasoning, creative. Pay with USDC on Base via x402.","url":"https://minizzzan.vercel.app/api/chat","method":"POST","headers":{},"bodySchema":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string","description":"Your message or question"},"max_tokens":{"type":"number","description":"Max response tokens (default 1024)"},"temperature":{"type":"number","description":"Creativity 0-1 (default 0.7)"}}},"responseSchema":{"type":"object"},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.05","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":"$0.05/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.05","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_LKhrqN1G01Xz26G8SwMog","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.05","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Sends a text prompt to a MiniMax-M3 428B MoE model hosted via NVIDIA NIM and returns an AI-generated response, payable per-call in USDC on Base.","exampleAgentPrompt":"Ask the MiniMax-M3 428B model through MiniChan: 'Explain the key differences between mixture-of-experts and dense transformer architectures in 3 paragraphs' — use temperature 0.5 and allow up to 800 tokens.","exampleUseCases":null,"resultDescription":"A JSON object containing the AI-generated text response from the MiniMax-M3 428B MoE model based on the submitted prompt, with length and style influenced by the max_tokens and temperature parameters.","failureModes":["Missing required 'prompt' field returns a 400 error","Payment not completed in USDC on Base results in 402 Payment Required","Prompt too long or max_tokens exceeds model limit causes a 400 or 500 error","Temperature outside valid range may be ignored or cause a validation error","Model inference timeout causes a 503 or 504 response","Invalid JSON body returns a 400 parse error"],"whenToPreferThis":"Choose this endpoint when you need a high-capacity 428B MoE language model for complex reasoning, creative, or multimodal tasks and are willing to pay $0.05 USDC per call via x402 on Base — ideal for agents that need large-model quality without managing their own NVIDIA NIM infrastructure.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:44:31.467Z","isFirstParty":false}