{"uid":"cap_FGzRVLDe3-ob2oKYraXR3","slug":"agent-weather-ai-model-category-conditions-1d2f45df","name":"Agent Weather – AI Model Category Conditions","description":"Use when you need conditions across a model category (reasoning, coding, vision-input...) with per-model job cost. Conditions across one category of AI models listed on OpenRouter (GET /v1/models/category/{name}; name one of reasoning, coding, vision-input, image-output, audio, retiring-soon, price-moved, free-tier): counts, price changes in the last 24h, new and removed models, models with an expiration date, vendor disturbances from the vendors' own status pages, and every model in the category with its standard job cost (10,000 input + 1,000 output tokens) as a plain fact. Categories come only from declared metadata, and the rule is stated in the response. Default order is by id; ?sort=cost orders by cost and is labelled \"sorted by cost, not quality\". Unknown categories get 400 before any payment. JSON. Example (illustrative): GET /v1/models/category/coding?sort=cost → {counts, price_movers_24h, models:[{id, standard_job_cost_usd}]}. Price: 0.01 RLUSD on XRPL mainnet (xrpl:0; RLUSD issuer rMxCKbEDwqr76QuheSUMdEGf4B9xJ8m5De) or 0.01 USDC on Base.","url":"https://api.agentweather.io/v1/models/category/:name?utm_source=zero.xyz","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"],"type":"string"},"pathParams":{"type":"object","properties":{"name":{"enum":["reasoning","coding","vision-input","image-output","audio","retiring-soon","price-moved","free-tier"],"type":"string","description":"model category"}}},"queryParams":{"type":"object","properties":{"sort":{"enum":["cost"],"type":"string","description":"optional: order by standard job cost (sorted by cost, not quality)"}},"additionalProperties":false}},"additionalProperties":false},"output":{"type":"object","required":["type"],"properties":{"type":{"type":"string"},"example":{"type":"object","required":["example_data","schema_version","report_id","issued_at","category","rule","summary","counts","models","sources"],"properties":{"rule":{"type":"string"},"counts":{"type":"object"},"models":{"type":"array"},"sources":{"type":"array"},"summary":{"type":"string"},"category":{"type":"string"},"issued_at":{"type":"string"},"report_id":{"type":"string"},"example_data":{"const":false},"schema_version":{"type":"string"}},"additionalProperties":true}}}}},"responseSchema":null,"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_TmoA0Dx2bXGSwnUXU1RJZ","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":"Returns a live snapshot of conditions across a named AI model category (reasoning, coding, vision-input, etc.) including counts, price changes, new/removed models, vendor disturbances, and per-model standard job costs.","exampleAgentPrompt":"Pull up the current conditions for all coding models — I want to see which ones have moved in price in the last 24 hours and what each one costs for a standard job, sorted by cost.","exampleUseCases":[{"title":"Budget-aware coding model selection","prompt":"Show me all the coding models available right now sorted by cost — I want to find the cheapest option for a standard 10k input / 1k output token job and see if any prices changed recently."},{"title":"Monitoring reasoning model vendor outages","prompt":"Are there any vendor disturbances or incidents affecting reasoning models right now? I also want to know if any new models were added or removed in that category today."},{"title":"Auditing soon-to-expire vision models","prompt":"Give me a full snapshot of the vision-input model category — especially any models that have an expiration date or are flagged as retiring soon, along with their standard job costs."}],"resultDescription":"A JSON object containing: total model count for the category, price movers in the last 24 hours, newly added models, removed models, models with expiration dates, vendor disturbance notices from provider status pages, and a full list of every model in the category with its standard job cost in USD (computed for 10,000 input + 1,000 output tokens). If sort=cost is specified, the model list is ordered by cost and labelled accordingly. Unknown category names return a 400 error before any charge.","failureModes":["400 error for unrecognized category name (no charge incurred)","Payment failure on XRPL if RLUSD balance is insufficient","Stale vendor disturbance data if provider status pages are slow to update","Empty model list if a valid category currently has no models","Truncated response if upstream OpenRouter metadata is incomplete"],"whenToPreferThis":"Choose this endpoint when you need a broad, category-level survey of the AI model landscape rather than details on a single model. It is ideal for cost comparison shopping across a model class, detecting ecosystem-wide price movements or vendor incidents, auditing model lifecycle (new, retiring, expiring), or building dashboards that track OpenRouter model availability by category. Use the single-model sibling endpoint instead when you already know which model you want and need its live individual metrics.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-10-19T06:30:37.332Z","isFirstParty":false,"canonicalSlug":"agent-weather-ai-model-category-conditions-1d2f45df"}