{"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":15226,"offers":16988,"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":"nvidia-nemotron-3-5-lightning-ms1qh3","sources":[{"id":"openrouter","count":470,"label":"OpenRouter","status":"ok","message":null,"observedAt":"2026-10-17T14:13:14.864Z","attemptedAt":"2026-10-17T14:13:14.356Z","quarantinedOffers":0}],"model":{"id":"nvidia/nemotron-3.5-lightning","name":"NVIDIA: Nemotron 3.5 Lightning","aliases":["NVIDIA: Nemotron 3.5 Lightning"],"context":262144,"medusaId":"nvidia/nemotron-3.5-lightning","released":"2026-08-11T12:52:31.000Z","developer":"nvidia","parameters":["frequency_penalty","include_reasoning","logit_bias","logprobs","max_tokens","min_p","presence_penalty","reasoning","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"description":"NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...","benchmarkKey":"nvidia/nemotron-3.5-lightning-20260807","sourceIdentity":{"source":"openrouter","version":"sfaie.source-model-identity.v1","sourceId":"nvidia/nemotron-3.5-lightning","reference":"https://openrouter.ai/api/v1/models","observedAt":"2026-10-17T14:13:14.864Z","canonicalId":"nvidia/nemotron-3.5-lightning-20260807","expirationDate":null},"inputModalities":["text"],"outputModalities":["text"],"offers":[{"id":"openrouter:nvidia/nemotron-3.5-lightning:coreweave/bf16","tier":"standard","unit":"1M tokens","input":0.07,"output":0.2,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":262144,"latency":0.228,"modelId":"nvidia/nemotron-3.5-lightning","currency":"USD","provider":"CoreWeave","cacheRead":0.04,"maxOutput":235929,"retention":null,"sourceUrl":"https://openrouter.ai/nvidia/nemotron-3.5-lightning","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:32:19.773Z","parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"provenance":"aggregator","throughput":253,"pricingRules":null,"quantization":"bf16","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":228},{"id":"openrouter:nvidia/nemotron-3.5-lightning:darkbloom/int4","tier":"standard","unit":"1M tokens","input":0.025,"output":0.12,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":262144,"latency":2.6555,"modelId":"nvidia/nemotron-3.5-lightning","currency":"USD","provider":"Darkbloom","cacheRead":0.0125,"maxOutput":32768,"retention":null,"sourceUrl":"https://openrouter.ai/nvidia/nemotron-3.5-lightning","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:32:19.773Z","parameters":["reasoning","include_reasoning","temperature","top_p","top_k","frequency_penalty","presence_penalty","repetition_penalty","stop","seed","max_tokens","response_format","structured_outputs","logprobs","top_logprobs","tools","tool_choice"],"provenance":"aggregator","throughput":40,"pricingRules":null,"quantization":"int4","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":2655.5},{"id":"openrouter:nvidia/nemotron-3.5-lightning:deepinfra/bf16","tier":"standard","unit":"1M tokens","input":0.06,"output":0.16,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":262144,"latency":0.294,"modelId":"nvidia/nemotron-3.5-lightning","currency":"USD","provider":"DeepInfra","cacheRead":0.03,"maxOutput":32768,"retention":null,"sourceUrl":"https://openrouter.ai/nvidia/nemotron-3.5-lightning","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:32:19.773Z","parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","structured_outputs","response_format","tools","tool_choice","logit_bias"],"provenance":"aggregator","throughput":160,"pricingRules":null,"quantization":"bf16","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":294},{"id":"openrouter:nvidia/nemotron-3.5-lightning:io-net","tier":"standard","unit":"1M tokens","input":0.0469,"output":0.134,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":262144,"latency":2.178,"modelId":"nvidia/nemotron-3.5-lightning","currency":"USD","provider":"Io Net","cacheRead":0.02345,"maxOutput":131072,"retention":null,"sourceUrl":"https://openrouter.ai/nvidia/nemotron-3.5-lightning","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:32:19.773Z","parameters":["reasoning","include_reasoning","max_tokens","temperature","logprobs","top_logprobs","tools","response_format","tool_choice","structured_outputs"],"provenance":"aggregator","throughput":37,"pricingRules":{"discount":0.33},"quantization":null,"performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":2178}],"firstSeen":"2026-09-16T23:50:33.173Z","ticker":"NEMOTR35LF","headlineOfferId":"openrouter:nvidia/nemotron-3.5-lightning:darkbloom/int4","displayName":"Nemotron 3.5 Lightning","brandedName":"NVIDIA Nemotron 3.5 Lightning"}}