{"uid":"cap__HX7ht6CMaeJw2GDwW2B6","slug":"agentdata-llm-chat-completion-x402-no-account-2b3adaca","name":"AgentData LLM Chat Completion (x402, No Account)","description":"LLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.","url":"https://agentdata-api.sander-van-aard.workers.dev/llm/chat","method":"POST","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method","bodyType","body"],"properties":{"body":{"type":"object"},"type":{"type":"string","const":"http"},"method":{"enum":["POST","PUT","PATCH"],"type":"string"},"headers":{"type":"object","additionalProperties":{"type":"string"}},"bodyType":{"enum":["json","form-data","text"],"type":"string"},"queryParams":{"type":"object","additionalProperties":{"type":"string"}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object"}}}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.002","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":"$0.002/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.002","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_BibRmQNL5W3NbB08JQLQ6","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.002","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs an OpenAI-style chat completion against one of three tiered models (DeepSeek Flash, GPT mini, DeepSeek Pro) billed per-call in USDC via x402 — no API key or account required.","exampleAgentPrompt":"Use the smart tier ($0.02) to answer this question with an OpenAI-style chat call — no API key needed, just pay per call in USDC: 'Summarize the key differences between transformer and mamba architectures in three bullet points.'","exampleUseCases":[{"title":"Cheap agent reasoning without API keys","prompt":"I need to run a quick AI answer for a user question — use the fast tier at $0.002 to complete this prompt: 'What are three ways to reduce churn in a SaaS product?' Pay per call, no account setup."},{"title":"Complex multi-step reasoning task","prompt":"Use the reasoning tier at $0.03 to think through this problem carefully: 'Given a sorted rotated array, explain and implement binary search in Python with edge cases.' I want the full thought-out response."},{"title":"Autonomous agent sub-task delegation","prompt":"My pipeline needs to classify whether this support ticket is billing, technical, or general — use the smart model at $0.02 per call and return the category and confidence in the reply: 'I was charged twice this month and I can't log into my dashboard.'"}],"resultDescription":"Returns the assistant's reply text along with finish_reason (e.g. 'stop') and token usage counts for the request. If the model or source is unavailable a 503 is returned and no charge is made; a 402 response quotes the exact tier price before the call is executed.","failureModes":["503 if the selected model or upstream source is unavailable — no charge incurred","402 with tier price quoted if payment has not yet been provided","Input exceeds per-tier character cap (16k chars for fast, 32k for higher tiers) — request rejected","Malformed messages array or missing required body fields returns a 4xx validation error","Network timeout on the Cloudflare Workers edge layer"],"whenToPreferThis":"Choose this endpoint when you need LLM chat completions without managing API keys, rate limits, or monthly billing — ideal for agents that need pay-per-use inference billed in USDC on Base via x402. Best when you want predictable flat per-call pricing across fast, smart, or reasoning tiers and can tolerate the model being sourced from either DeepSeek or OpenAI depending on tier.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T06:42:59.655Z","isFirstParty":false}