{"uid":"cap_ctyThGvKOFm_yIY6aDUhW","slug":"agishub-general-purpose-llm-chat-c696869e","name":"AGISHub General-Purpose LLM Chat","description":"Ask a general-purpose LLM a question or give it an instruction, with an optional system prompt. No external API key required.","url":"https://api.agishub.com/paid/chat","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input","output"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object","required":["prompt"],"properties":{"prompt":{"type":"string","minLength":1,"description":"The user's message or question for the assistant."},"system":{"type":"string","description":"Optional system instruction to steer the assistant's behaviour/persona."},"max_tokens":{"type":"integer","maximum":2048,"minimum":0,"description":"Maximum tokens to generate (default 512).","exclusiveMinimum":true}},"additionalProperties":false},"type":{"enum":["http"],"type":"string"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type","example"],"properties":{"type":{"enum":["json"],"type":"string"},"example":{"type":"object"}},"additionalProperties":false}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.02","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":"$0.02/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.02","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_gXbbSb_N6EQeCVIbDNrqe","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.02","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Send a prompt (and optional system instruction) to a general-purpose LLM and receive a text response, no external API key required.","exampleAgentPrompt":"Ask the AI: 'What are three creative names for a boutique coffee shop that specializes in single-origin beans?' — use a system prompt that says 'You are a branding expert who gives concise, punchy suggestions' and cap the response at 200 tokens.","exampleUseCases":[{"title":"AI-powered customer support reply","prompt":"I need you to draft a polite reply to this customer complaint: 'My order arrived damaged and I want a refund.' Use the persona 'You are a helpful customer service agent for an e-commerce store' and keep the response under 150 words."},{"title":"On-the-fly content brainstorming","prompt":"Ask the LLM to brainstorm 5 blog post titles about sustainable home gardening — use the system prompt 'You are a creative content strategist' and limit the output to 300 tokens."},{"title":"Inline question answering for an agent pipeline","prompt":"I need a quick answer: what is the difference between TCP and UDP? Keep it under 100 tokens and explain it like I'm a non-technical product manager."}],"resultDescription":"A JSON object containing the LLM-generated text response to the provided prompt, shaped by the optional system instruction and bounded by the max_tokens parameter (default 512, up to 2048).","failureModes":["Missing required 'prompt' parameter returns a 400 validation error","max_tokens set to 0 or exceeding 2048 causes a validation error","Payment not included or insufficient USDC triggers a 402 Payment Required response","Very long prompts may be truncated or rejected if they exceed model context limits","Network timeouts if the LLM backend is slow to respond under high load"],"whenToPreferThis":"Choose this endpoint when you need LLM text generation without managing your own OpenAI, Anthropic, or other API keys — especially in agentic pipelines where per-call micropayments (x402/USDC) are preferred over subscription billing. It supports custom system prompts, making it suitable for persona-driven or task-specific completions. Prefer alternatives if you need streaming responses, function calling, structured JSON output guarantees, or specific model selection.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:45:24.207Z","isFirstParty":false}