{"uid":"cap__777M8_vIPLpTCdJYUuwG","slug":"aayat-ai-llm-chat-gateway-11649a42","name":"Aayat AI LLM Chat Gateway","description":"Pay-per-call LLM chat (Llama 3.3 70B): Strongest model for harder reasoning, coding and careful writing; supports JSON output. No API key or account. POST JSON {\"prompt\": \"...\"} or OpenAI-style {\"messages\": [{\"role\": \"user\", \"content\": \"...\"}]}, optional \"system\", \"max_tokens\" (up to 1536), \"temperature\", \"json\": true. Up to about 36,000 characters of English in. Failed calls are not charged.","url":"https://aayatai.com/chat/premium?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"json":{"type":"boolean","default":false,"description":"Ask for JSON-only output."},"prompt":{"type":"string","maxLength":48000,"description":"A single user message (use this or messages)."},"system":{"type":"string","maxLength":8000,"description":"System instructions."},"messages":{"type":"array","items":{"type":"object","properties":{"role":{"enum":["system","user","assistant"],"type":"string"},"content":{"type":"string"}}},"maxItems":50,"description":"Conversation so far, OpenAI style: [{role, content}]."},"max_tokens":{"type":"integer","maximum":1536,"minimum":1,"description":"Most tokens to generate (default 512)."},"temperature":{"type":"number","default":0.3,"maximum":2,"minimum":0,"description":"Randomness, 0-2."}}},"responseSchema":{"type":"json","example":{"text":"x402 is an open protocol that lets clients pay for HTTP requests with stablecoins using the 402 status code.","model":"@cf/meta/llama-3.3-70b-instruct-fp8-fast","usage":{"promptTokens":24,"completionTokens":26}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.03","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":"$0.03/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.03","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_wBmZ6cCXyjKiqNJpxX1HF","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.03","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"A pay-per-call LLM chat endpoint that accepts a prompt or conversation and returns a generated text response from a hosted large language model, no API key or account required.","exampleAgentPrompt":"Ask the LLM: 'Explain how x402 micropayments work for AI agents' — keep the response under 200 tokens with a temperature of 0.3.","exampleUseCases":[{"title":"On-demand AI answers in an agent","prompt":"Send this question to the LLM and give me the answer: 'What are the main risks of a rug pull in a DeFi token launch?' — use a temperature of 0.2 and keep it under 300 tokens."},{"title":"Multi-turn support chat with context","prompt":"Continue this conversation with the AI: the user previously asked 'How do I stake ETH?' and the assistant explained liquid staking. Now the user is asking 'What are the risks?' — send all three messages and get the next response."},{"title":"Structured JSON output from a prompt","prompt":"Run this prompt through the LLM and return the result as JSON only: 'List the top 3 benefits of using stablecoins for API micropayments, each with a title and one-sentence description.' Use max 512 tokens."}],"resultDescription":"Returns a JSON object containing the generated text reply, the model identifier used (e.g. @cf/meta/llama-3.3-70b-instruct-fp8-fast), and token usage stats (promptTokens, completionTokens).","failureModes":["Prompt exceeds 48,000 character limit — request rejected","messages array exceeds 50 items — request rejected","max_tokens set above 1536 — request rejected","Payment not received or insufficient USDC — 402 response, no generation","Temperature outside 0–2 range — validation error","Both prompt and messages omitted — ambiguous or empty request","Model timeout on very long prompts — partial or no response"],"whenToPreferThis":"Choose this endpoint when you need a quick, keyless LLM call paid per-use with USDC on Base or Solana via x402, especially in agent pipelines where managing API keys is impractical. Prefer it over OpenAI or Anthropic direct APIs when you want crypto-native micropayment billing and no account setup. It is best for single-turn or short multi-turn completions up to 1,536 output tokens.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-02T18:37:10.904Z","isFirstParty":false,"canonicalSlug":"aayat-ai-llm-chat-gateway-a1182c80"}