{"uid":"cap_yDELZTKtNP3g9R_0amnCq","slug":"webbersites-llm-inference-claude-haiku-dd7dd52d","name":"webbersites LLM Inference (Claude Haiku)","description":"LLM INFERENCE for keyless agents — POST {prompt, system?} and get Claude Haiku's answer: summarize, classify, extract, rewrite, translate, draft. No API key, no account, no subscription — the x402 payment IS the auth. One flat price per call. Caps: 8,000-char prompt, 2,000-char system, ~1,000-token response (stop_reason tells you if you hit it). Powered by Claude Haiku 4.5.","url":"https://api.webbersites.com/api/llm","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"required":["prompt"],"properties":{"prompt":{"type":"string","description":"The task/question, up to 8,000 chars"},"system":{"type":"string","description":"Optional system prompt (persona, format rules), up to 2,000 chars"}}},"type":{"type":"string","const":"http"},"method":{"enum":["POST"],"type":"string"},"bodyType":{"enum":["json","form-data","text"],"type":"string"}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","properties":{"model":{"type":"string"},"usage":{"type":"object"},"response":{"type":"string","description":"the model's answer"},"stop_reason":{"type":"string","description":"end_turn, or max_tokens if the 1,000-token cap was hit"}}}}}}},"responseSchema":{"type":"json","example":{"model":"claude-haiku-4-5","usage":{"input_tokens":41,"output_tokens":4},"response":"billing","stop_reason":"end_turn"}},"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_CdTmKYs0HVITUFH7WM3ex","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 single LLM inference call using Claude Haiku 3.5, accepting a prompt and optional system message and returning a generated text response — no API key required, paid per-call via x402.","exampleAgentPrompt":"Summarize the following support ticket in two sentences and classify its urgency as low, medium, or high: 'Our entire checkout flow is broken since the last deploy — no customers can complete purchases and we're losing revenue fast. Please fix ASAP.'","exampleUseCases":null,"resultDescription":"A JSON response containing the LLM-generated text completion from Claude Haiku, along with a stop_reason field indicating whether the response ended naturally or was truncated at the ~1,000-token limit.","failureModes":["Prompt exceeds 8,000 characters — request rejected with validation error","System prompt exceeds 2,000 characters — request rejected","Response truncated at ~1,000 tokens — stop_reason indicates max_tokens hit","Payment not processed via x402 — 402 Payment Required returned","Model unavailable or upstream Anthropic error — 5xx response"],"whenToPreferThis":"Choose this endpoint when you need a quick, keyless LLM inference call — especially for summarization, classification, extraction, or rewriting tasks — and don't want to manage API keys or subscriptions. Ideal for agents that need on-demand AI text generation at a flat $0.01/call price. Not suited for very long outputs (capped at ~1,000 tokens) or multi-turn conversations.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T00:43:39.393Z","isFirstParty":false}