{"uid":"cap_p8WS7UVRVMt5J0N2kJzsS","slug":"live-model-inference-cost-index-6fe0826c","name":"Live Model Inference Cost Index","description":"Live merchant inference-cost index from OpenRouter's public model catalog: per-model USD-per-token prompt and completion pricing, context window, reasoning requirements, and cache-read pricing where offered. Use to price an x402 inference service, select the cheapest model for a workload, or sanity-check a vendor quote against current market rates. Returns the full live model list with pricing in raw USD per token (multiply by 1e6 for per-million-token cost).","url":"https://k2so.wrong.systems/api/services/live-model-inference-cost-index","method":"GET","headers":{},"bodySchema":{"type":"object","$schema":"https://json-schema.org/draft/2020-12/schema","required":["input"],"properties":{"input":{"type":"object","required":["type","method"],"properties":{"type":{"type":"string","const":"http"},"method":{"enum":["GET","HEAD","DELETE"],"type":"string"},"queryParams":{"type":"object","properties":{"meta":{"enum":["0","1"],"type":"string","description":"Set to 1 for free metadata JSON (no payment required)"}}}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","title":"Live model inference cost index paid response","$schema":"https://json-schema.org/draft/2020-12/schema","required":["ok","paid","service","provider","result"],"properties":{"ok":{"type":"boolean"},"paid":{"type":"boolean"},"result":{"type":"object","required":["ok","service"],"properties":{"ok":{"type":"boolean","description":"Handler success"},"body":{},"service":{"type":"string","description":"Service slug"},"generatedAt":{"type":"string","description":"ISO-8601 timestamp"},"upstreamStatus":{"type":"number"}}},"payment":{"type":"object","properties":{"code":{"type":"string"},"payer":{"type":"string"},"detail":{"type":"string"},"selfPay":{"type":"boolean"},"transaction":{"type":"string"}}},"service":{"type":"string"},"provider":{"type":"string","const":"K-2SO"}}}}}}},"responseSchema":{"type":"json","example":{"ok":true,"paid":true,"result":{"ok":true,"body":{},"service":"live-model-inference-cost-index","generatedAt":"2026-01-01T00:00:00.000Z","upstreamStatus":200},"service":"live-model-inference-cost-index","provider":"K-2SO"}},"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_-Orj3lhjiTXh1DKkAz5My","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":"Returns live per-model USD-per-token prompt and completion pricing, context window size, and cache-read pricing from OpenRouter's public model catalog.","exampleAgentPrompt":"Pull the current live inference pricing index so I can see prompt and completion costs per token for all available models and figure out which one is cheapest for a long-context summarization workload.","exampleUseCases":[{"title":"Cheapest model selection for workload","prompt":"I need to pick the most cost-effective LLM for processing a million customer support tickets — can you pull the live inference pricing index and tell me which model has the lowest completion token cost while offering at least 32k context?"},{"title":"Sanity-check a vendor inference quote","prompt":"A vendor just quoted me $2.50 per million output tokens for Claude 3.5 Sonnet — can you check the current live market rates and tell me whether that's fair or if I'm being overcharged?"},{"title":"Price an x402 inference service","prompt":"I'm about to list my inference service on x402 and I want to set competitive prices — can you fetch the live model cost index so I can see what OpenRouter is currently charging per token for the models I'm wrapping?"}],"resultDescription":"A full list of AI models with their live USD-per-token pricing for prompt tokens, completion tokens, and cache-read tokens where available, plus context window sizes and reasoning requirements. Multiply any price by 1,000,000 to get cost per million tokens.","failureModes":["OpenRouter upstream unavailable — upstreamStatus non-200 returned with ok:false","Payment not received — 402 response requiring x402 payment before data is returned","Invalid query parameter value for meta field — schema validation error","Network timeout reaching k2so.wrong.systems — no response"],"whenToPreferThis":"Choose this endpoint when you need live, up-to-date inference pricing across the full OpenRouter model catalog in a single call — particularly useful for x402 inference service pricing, cost-optimized model selection, or validating vendor quotes against current market rates. Prefer this over scraping OpenRouter directly when you need a paid, metered, agent-friendly JSON response with structured schema.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-14T00:50:28.675Z","isFirstParty":false}