{"uid":"cap_Jx9NxO_QxJIVKdy-mZ5U9","slug":"x402-gateway-production-up-railway-app-8dc8cc1e","name":"Llama 4 Maverick LLM API (x402 Gateway)","description":"Meta's latest open model — 1M context, strong multilingual and reasoning at very low cost","url":"https://x402-gateway-production.up.railway.app/api/llm/llama-4-maverick","method":"POST","headers":{},"bodySchema":null,"responseSchema":null,"example":{"request":{"messages":[{"role":"user","content":"Explain the difference between supervised and unsupervised learning in one paragraph."}],"max_tokens":200,"temperature":0.7},"response":{"model":"meta-llama/llama-4-maverick-17b-128e-instruct","usage":{"cost":0.0000825,"is_byok":false,"cost_details":{"upstream_inference_cost":0.0000825,"upstream_inference_prompt_cost":0.0000033,"upstream_inference_completions_cost":0.0000792},"total_tokens":154,"prompt_tokens":22,"completion_tokens":132,"prompt_tokens_details":{"audio_tokens":0,"video_tokens":0,"cached_tokens":0,"cache_write_tokens":0},"completion_tokens_details":{"audio_tokens":0,"image_tokens":0,"reasoning_tokens":0}},"content":"Supervised and unsupervised learning are two distinct approaches to machine learning. Supervised learning involves training a model on labeled data, where the correct output or response is already known, allowing the model to learn from the examples and make predictions on new, unseen data. In contrast, unsupervised learning involves training a model on unlabeled data, where the model is tasked with discovering patterns, relationships, or groupings within the data on its own, without any prior knowledge of the correct output. This fundamental difference in approach enables supervised learning to be used for tasks like classification and regression, while unsupervised learning is often used for tasks like clustering, dimensionality reduction, and anomaly detection."}},"exampleRequest":{"messages":[{"role":"user","content":"Explain the difference between supervised and unsupervised learning in one paragraph."}],"max_tokens":200,"temperature":0.7},"tags":["x402"],"displayCostAmount":"0.003000","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"settled","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":"$0.003000/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.003","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_JiTY0guDbgE3l5Ouq9bKs","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":null,"unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Runs inference on Meta's Llama 4 Maverick model — a 1M-context, multilingual, reasoning-capable open model — via a pay-per-call x402 gateway.","exampleAgentPrompt":"Use Llama 4 Maverick to summarize this 500-page legal document and highlight all clauses related to liability — it's in French and I need the output in English.","exampleUseCases":null,"resultDescription":"A generated text completion from Meta's Llama 4 Maverick model, capable of handling up to 1 million tokens of context, with strong multilingual and reasoning performance. The response is a natural language output matching the prompt's intent, delivered at very low cost ($0.003 USDC per call) via x402 micropayment.","failureModes":["Payment not included or invalid x402 payment header — 402 Payment Required","Prompt exceeds model limits despite large context window — 400 Bad Request","Model overloaded or gateway unavailable — 503 Service Unavailable","Malformed request body — 400 Bad Request","Unsupported language or encoding issues in multilingual input — unexpected output quality"],"whenToPreferThis":"Choose this endpoint when you need a high-context (1M token), multilingual, open-weight model at very low per-call cost, especially when processing long documents, cross-lingual tasks, or complex reasoning without committing to a subscription. Prefer over GPT or Claude endpoints when cost sensitivity is high and Meta's open-model quality is sufficient.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-13T18:49:34.655Z","isFirstParty":false}