{"uid":"cap_ExJkIn29OpGHdCEYQnR_H","slug":"yiduochan-minimax-inference-fa83d6f7","name":"YiduoChan MiniMax Inference","description":"OpenAI-compatible LLM inference, paid per call. POST a standard chat completion body with an x402 payment and the response is the completion itself; the API key and remaining balance come back in headers, so the next call can skip payment. Serves MiniMax language models: MiniMax-M3 for long-context reasoning with a 1,048,576-token window, and MiniMax-M2.7 for general chat, agent loops and coding. Text to speech and video generation run on the same balance. Whatever a call does not spend stays on the paying wallet. No account, email or signup.","url":"https://yiduochan.com/api/x402/chat/completions","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"A model id from /v1/models, for example MiniMax-M2.7 or MiniMax-M3"},"messages":{"type":"array","items":{"type":"object","required":["role","content"],"properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"description":"OpenAI chat messages"},"max_tokens":{"type":"integer"},"temperature":{"type":"number"}}},"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_vhI-tjF5m2z3H8B0-KwIN","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":"OpenAI-compatible chat completions using MiniMax language models (MiniMax-M3 and MiniMax-M2.7), paid per call via x402 micro-payment with no account required.","exampleAgentPrompt":"Ask MiniMax-M3 to summarize this 500-page legal document I just uploaded — use up to 4000 output tokens and keep the temperature at 0.2 for a factual, low-creativity response.","exampleUseCases":[{"title":"Long-context document reasoning","prompt":"I have a 200,000-token research paper I need analyzed. Use MiniMax-M3 to extract the key findings and methodology — set max_tokens to 2000 and temperature to 0.1 so the answer is precise."},{"title":"Agent loop coding assistant","prompt":"Run a MiniMax-M2.7 completion for my coding agent: the system prompt is 'You are a senior Python engineer', the user message is 'Refactor this function to use async/await', and give me up to 1500 tokens back."},{"title":"Accountless one-off chat query","prompt":"I don't want to sign up anywhere — just send a single chat message to MiniMax-M2.7 asking 'What are the top 3 differences between REST and GraphQL?' and pay per call. Keep temperature at 0.7 and max_tokens at 500."}],"resultDescription":"Returns the full OpenAI-compatible chat completion response body containing the generated text. Response headers include a freshly issued API key and the remaining balance, allowing the caller to skip the x402 payment on subsequent requests until the balance is depleted.","failureModes":["Payment not included or malformed x402 header — returns 402 Payment Required","Insufficient payment amount — transaction rejected","Invalid or unsupported model ID — returns 400 Bad Request","Messages array missing required role or content fields — returns 400","Context length exceeds model window — returns 400 or truncation error","Network timeout for very long completions with large max_tokens","Balance exhausted mid-session — subsequent calls require new payment"],"whenToPreferThis":"Choose this endpoint when you need OpenAI-compatible LLM inference without account creation or API key management, especially for one-off or infrequent calls paid with USDC micropayments. It is ideal for agents that need MiniMax-M3's massive 1,048,576-token context window for long-document tasks, or MiniMax-M2.7 for general chat and coding loops. Prefer it over standard API providers when you want pay-per-call economics with no subscription, or when integrating crypto-native payment flows via x402.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T12:34:19.705Z","isFirstParty":false}