{"format":"sfai.catalog-model.v1","dataQuality":{"version":"sfaie.catalog-quality.v1","status":"ok","quarantinedOffers":0,"quarantinedPerformanceOffers":0,"duplicateObservations":0,"issueCount":0,"issues":[],"issuesTruncated":false},"coverage":{"models":15225,"offers":16986,"providers":296,"priced":11103,"endpointModels":381,"independentlyBenchmarked":0},"units":{"version":"sfaie.catalog-units.v1","currency":"Offer.currency (ISO 4217)","tokenPrices":"currency per 1,000,000 tokens (input, output, cacheRead, cacheWrite when unit is \"1M tokens\")","unitPrice":"currency per Offer.unit","latency":"s (legacy field for older clients; prefer latencyMs)","latencyMs":"ms","latencyMetric":"p50 time to first token over Offer.performanceWindow","throughput":"tokens/s","throughputMetric":"p50 output tokens per second over Offer.performanceWindow","uptime":"percent","context":"tokens"},"policy":{"paidInference":false,"paidFeeds":false,"refreshMinutes":5,"historyDays":30,"benchmarkStatus":"Paid measurements are disabled. Published benchmarks and performance retain source attribution."},"canonical":true,"slug":"thinkingmachines-inkling-small-4mmbse","sources":[{"id":"openrouter","count":470,"label":"OpenRouter","status":"ok","message":null,"observedAt":"2026-10-17T14:01:14.886Z","attemptedAt":"2026-10-17T14:01:14.359Z","quarantinedOffers":0}],"model":{"id":"thinkingmachines/inkling-small","name":"Thinking Machines: Inkling Small","aliases":["Thinking Machines: Inkling Small"],"context":524288,"medusaId":"thinkingmachines/inkling-small","released":"2026-07-30T20:25:17.000Z","developer":"thinkingmachines","parameters":["frequency_penalty","include_reasoning","logit_bias","max_tokens","min_p","presence_penalty","reasoning","reasoning_effort","repetition_penalty","seed","stop","temperature","tool_choice","tools","top_k","top_p"],"description":"Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more efficient member of...","benchmarkKey":"thinkingmachines/inkling-small-20260730","sourceIdentity":{"source":"openrouter","version":"sfaie.source-model-identity.v1","sourceId":"thinkingmachines/inkling-small","reference":"https://openrouter.ai/api/v1/models","observedAt":"2026-10-17T14:01:14.886Z","canonicalId":"thinkingmachines/inkling-small-20260730","expirationDate":null},"inputModalities":["text","image","audio"],"outputModalities":["text"],"offers":[{"id":"openrouter:thinkingmachines/inkling-small:deepinfra/fp8","tier":"standard","unit":"1M tokens","input":0.45,"output":1.2,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":524288,"latency":0.694,"modelId":"thinkingmachines/inkling-small","currency":"USD","provider":"DeepInfra","cacheRead":0.1,"maxOutput":262144,"retention":null,"sourceUrl":"https://openrouter.ai/thinkingmachines/inkling-small","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:32:20.490Z","parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","tools","tool_choice","logit_bias","reasoning_effort"],"provenance":"aggregator","throughput":166.5,"pricingRules":null,"quantization":"fp8","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":694}],"firstSeen":"2026-09-16T23:50:33.173Z","ticker":"INKLINSF","headlineOfferId":"openrouter:thinkingmachines/inkling-small:deepinfra/fp8","displayName":"Inkling Small","brandedName":"Thinking Machines Inkling Small"}}