{"uid":"cap_bw3Ew5sEsTQkGiZ6I4Tkd","slug":"manylives-ai-chat-completion-9f19402a","name":"ManyLives AI Chat Completion","description":"Chat completion from an open AI model (Llama 3.3 70B by default; Llama 3.1 8B for speed), no account or API key: send messages (or a prompt), get the model's reply. Up to 24,000 characters in and 1,024 tokens out per call.","url":"https://manylives.me/paid/ai/chat?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"optional llama-3.3-70b (default) or llama-3.1-8b"},"prompt":{"type":"string","examples":["In one sentence, what is a hit rate?"],"description":"a single user prompt (alternative to messages)"},"messages":{"type":"string","description":"array of {role: system|user|assistant, content} (or use prompt)"},"max_tokens":{"type":"string","description":"optional, up to 1024 (default 512)"},"temperature":{"type":"string","description":"optional 0-1.5 (default 0.6)"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.005","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":"$0.005/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.005","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_ZddTVbgqaga2j5SdAdSCr","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.005","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Send a prompt or message thread to Llama 3.3 70B (or Llama 3.1 8B for speed) and get a text reply, no API key required — pay per call via x402.","exampleAgentPrompt":"Ask the Llama 3.3 70B model: 'Explain the difference between supervised and unsupervised learning in two paragraphs' — use a temperature of 0.7 and return up to 800 tokens.","exampleUseCases":[{"title":"Quick factual Q&A in agent pipeline","prompt":"I need you to ask Llama 70B: 'What are the three main causes of the 2008 financial crisis?' — keep the response concise, max 300 tokens."},{"title":"Creative writing snippet generation","prompt":"Use the Llama 3.3 70B model to write a short opening paragraph for a thriller novel set in 1920s Berlin — temperature 1.2 for some creativity, up to 512 tokens."},{"title":"Fast classification with lightweight model","prompt":"Use the faster Llama 3.1 8B model to classify this sentence as positive, negative, or neutral and explain why in one sentence: 'The product arrived late but the quality exceeded my expectations.'"}],"resultDescription":"The endpoint returns the language model's text reply to the provided prompt or message thread. The response contains the generated assistant message content, produced by Llama 3.3 70B (default) or Llama 3.1 8B (speed mode), up to the requested max_tokens (default 512, maximum 1024).","failureModes":["Input exceeds 24,000 character limit — request rejected","max_tokens set above 1024 — capped or rejected","Invalid model name provided — may fall back to default or return error","Malformed messages array (not valid array of role/content objects) — parse error","Payment not processed via x402 — 402 Payment Required response","Model temporarily unavailable — 5xx server error"],"whenToPreferThis":"Choose this endpoint when you need keyless, accountless access to open-weight Llama models (70B or 8B) via a simple pay-per-call micropayment model. It is ideal for agents that need occasional LLM inference without managing API credentials or subscriptions. Prefer the 8B option when latency matters and the 70B option for higher-quality reasoning. Not suitable for very long outputs (>1024 tokens), streaming responses, or fine-tuned model variants.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-10T12:39:38.909Z","isFirstParty":false,"canonicalSlug":"manylives-ai-chat-completion-9f19402a"}