{"uid":"cap_5oxP14NNoSK76n0zzNx0O","slug":"uxus-finance-llm-completion-api-817c629d","name":"uxus.finance LLM Completion API","description":"LLM chat completions for AI agents — no API key, no account, no signup; pay per call in USDC on Base. POST JSON { prompt } or { messages: [{ role, content }] }; optional model (OpenRouter slug), max_tokens (default 800, max 2000). Routes across a 5-model fallback chain so one unavailable model doesn't fail the call. Returns { model, content, usage, latency_ms }. For agents that need inference without holding an OpenAI or Anthropic key.","url":"https://uxus.finance/api/llm","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","description":"Optional model slug; still falls back through the chain."},"prompt":{"type":"string","description":"User prompt. Provide this or messages[]."},"messages":{"type":"array","description":"Chat messages [{ role, content }]. Alternative to prompt."},"max_tokens":{"type":"number","description":"Max completion tokens. Default 800, max 2000."}}},"responseSchema":{"type":"json","example":{"model":"deepseek/deepseek-chat","usage":{"total_tokens":104,"prompt_tokens":24,"completion_tokens":80},"content":"The answer is ...","latency_ms":1200}},"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_8M23Z7v4HXmYFDy5hsA_O","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":"Generates text completions using a 5-model fallback chain, returning the completion text, model used, token usage, and latency in milliseconds.","exampleAgentPrompt":"Complete this prompt using your best available model and tell me which model answered and how many tokens it used: 'Summarize the key benefits of renewable energy in 3 bullet points.'","exampleUseCases":[{"title":"Resilient LLM for agentic pipelines","prompt":"I need you to generate a structured summary of this legal document using a reliable LLM — if one model is down, automatically fall back to the next available one and tell me which model actually responded and how many tokens it consumed."},{"title":"Cost-tracked copywriting generation","prompt":"Write me a punchy 3-sentence product description for a wireless noise-cancelling headphone, and tell me the token usage and latency so I can track my content generation costs."},{"title":"Chatbot response with model transparency","prompt":"Answer this customer support question as helpfully as possible: 'How do I reset my password?' — and let me know which underlying model produced the answer and how long it took."}],"resultDescription":"A JSON object containing: the generated completion text, the name of the model that produced it (selected from a 5-model fallback chain), token usage statistics (prompt tokens, completion tokens, total), and latency_ms indicating how long the inference took in milliseconds.","failureModes":["All 5 models in the fallback chain are unavailable — returns an error after exhausting fallbacks","Prompt exceeds maximum token limit for all available models","Invalid or malformed request body — returns 400 bad request","Payment not received or insufficient USDC — returns 402 Payment Required","Rate limiting or quota exceeded on underlying model providers"],"whenToPreferThis":"Choose this endpoint when you need reliable LLM text generation with automatic failover across multiple models, and when you want transparency about which model responded along with token usage and latency metrics. Ideal for agentic workflows that require high availability without managing individual model API keys, and for pay-per-call cost tracking at $0.01 USDC per request.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-15T18:37:14.524Z","isFirstParty":false}