{"uid":"cap_lIYow8b5PMvuuP578kJh1","slug":"combify-compute-chat-fb2607db","name":"Combify Compute Chat","description":"Short prompt in, text out (Llama 3.1 8B instruct), fixed price $0.01 USDC. POST JSON body {prompt (required, max 2000 chars), max_tokens (optional 1-512, default 256)}. Unpaid calls get 402; paid calls settle only on success.","url":"https://combify-compute-production.up.railway.app/chat?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"prompt":{"type":"string","description":"User prompt, max 2000 chars"},"max_tokens":{"type":"integer","description":"Max output tokens, 1 to 512"}}},"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_qYHBgEuMwS8i1LMAbFkKM","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":"Runs a user prompt through Llama 3.1 8B Instruct and returns generated text for a fixed $0.01 USDC payment per call","exampleAgentPrompt":"Ask the Llama 3.1 8B model to explain the difference between supervised and unsupervised learning in plain English, keeping the answer under 200 tokens.","exampleUseCases":[{"title":"Quick factual question answering","prompt":"Use the Combify Compute LLM to answer this question in under 150 tokens: what are the main causes of the French Revolution?"},{"title":"Short creative writing snippet","prompt":"Generate a two-sentence product tagline for a sustainable coffee brand using the Llama 3.1 model — keep it under 80 tokens."},{"title":"Code explanation on a budget","prompt":"Send this Python snippet to the Llama 3.1 inference endpoint and ask it to explain what it does in plain English, up to 300 tokens: `def fib(n): return n if n <= 1 else fib(n-1) + fib(n-2)`"}],"resultDescription":"A plain text string containing the model's generated response, limited to the number of tokens specified (default 256, max 512). The response is only returned and payment settled if the call succeeds; unpaid requests receive a 402 error.","failureModes":["402 Payment Required — request was made without a valid USDC payment header or insufficient funds","prompt exceeds 2000 character limit — request rejected with validation error","max_tokens out of range (less than 1 or greater than 512) — validation error","model inference timeout or Railway infrastructure error — 5xx response","network connectivity issues to railway.app deployment"],"whenToPreferThis":"Choose this endpoint when you need low-cost, on-demand text generation from a capable small LLM (Llama 3.1 8B) and want predictable per-call pricing in USDC via the x402 payment protocol. It is well-suited for agents that need to run many short inference calls economically without a subscription, or for workflows that require pay-as-you-go LLM access settled on-chain. Prefer larger hosted LLMs (e.g. GPT-4, Claude) for complex reasoning tasks requiring larger context or superior accuracy.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-29T06:33:09.338Z","isFirstParty":false,"canonicalSlug":"combify-compute-chat-fb2607db"}