{"uid":"cap_xp6u53CnUpy98MzGalE_J","slug":"stack-facts-llm-model-price-estimator-d7da812c","name":"Stack Facts LLM Model Price Estimator","description":"Check a package before install: malware, known vulnerabilities (OSV), exploited CVEs (CISA KEV) and end-of-life, plus LLM prices; signed answers, pay per call in USDC, no account or API key.","url":"https://g5joilnmeep4ntz3nwezxt5dmu.srv.us/v1/models/estimate?utm_source=zero.xyz","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"model":{"type":"string","maxLength":200,"minLength":1},"input_tokens":{"type":"integer","maximum":10000000000,"minimum":0},"cached_tokens":{"type":"integer","maximum":10000000000,"minimum":0},"output_tokens":{"type":"integer","maximum":10000000000,"minimum":0}}},"responseSchema":{"type":"json","example":{"data":{"name":"GPT-4o","lines":[{"kind":"input","tokens":1000,"cost_usd":"0.002","price_field":"input_usd_per_mtok","usd_per_mtok":2}],"model":"openai/gpt-4o","notes":[],"formula":"cost_usd = (input_tokens × inpu…","cost_usd":"0.004","deprecated":false,"cost_micro_usd":4000,"deprecation_date":null,"sources_disagree":["input_usd_per_mtok"],"days_until_deprecation":null},"meta":{"as_of":"2026-10-09T06:00:00Z","stale":false,"key_id":"sf-test-1","notice":"Normalised (modified) from the …","sha256":"f99d55c9aa420561de698d63d70d916…","source":"https://raw.githubusercontent.c…","dataset":"models","licence":"MIT","signature":"AvlI5FXM8fD9oncZAr9velQseOBO9X7…","attribution":"Pricing data derived from LiteL…","snapshot_id":"models-20261009T060000Z-f99d55c9","manifest_url":"/v1/models/manifest","retrieved_at":"2026-10-09T06:00:00.000Z"}}},"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.003","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":"$0.003/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_LYdN7cCDn_UDrBQEgeZ6U","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.003","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Estimates the cost of an LLM API call given a model name and token counts, returning a signed, pay-per-call breakdown in USD","exampleAgentPrompt":"How much will it cost to call GPT-4o with 1,000 input tokens, 200 cached tokens, and 500 output tokens? Use Stack Facts to get a signed price estimate.","exampleUseCases":[{"title":"Pre-call cost gate for AI workflow","prompt":"Before sending this request to GPT-4o, estimate what it will cost me — I'm planning 2,000 input tokens and 800 output tokens — so I can decide if it's worth it."},{"title":"Budget check for high-volume inference","prompt":"I'm about to run a batch job using Claude 3.5 Sonnet with roughly 500 input tokens and 1,500 output tokens per call. What's the estimated USD cost per call so I can figure out what 10,000 calls will cost me?"},{"title":"Comparing cached vs uncached token pricing","prompt":"Get me the cost breakdown for calling openai/gpt-4o with 1,000 input tokens where 400 of them are cached and 600 are new, plus 300 output tokens — I want to see how much the caching saves me."}],"resultDescription":"Returns a signed JSON payload with the model's canonical name, a line-by-line cost breakdown (input, cached, output tokens), total cost in USD and micro-USD, the pricing formula used, deprecation status and date, a SHA-256 hash and cryptographic signature for tamper verification, the data source URL, dataset snapshot ID, licence, and a staleness flag — all reflecting the latest pricing snapshot.","failureModes":["Unknown or misspelled model name returns no matching data or an error","Token count values exceeding the maximum (10B) are rejected","Payment in USDC not submitted or insufficient causes HTTP 402 before any data is returned","Stale pricing snapshot may cause meta.stale=true flag if data hasn't been refreshed","Sources disagreeing on a price field triggers a sources_disagree array warning rather than a hard error"],"whenToPreferThis":"Choose this endpoint when you need a cryptographically signed, verifiable LLM cost estimate on a per-call basis with no API key or account setup — especially suitable for agents that need to gate or log LLM spending, compare model costs programmatically, or audit pricing with a tamper-evident signature. Prefer it over scraping provider pricing pages or using unofficial community spreadsheets when auditability and freshness guarantees matter.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-13T12:44:15.156Z","isFirstParty":false,"canonicalSlug":"stack-facts-llm-model-price-estimator-d7da812c"}