{"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":"z-ai-glm-5-3-flashx-2ou1eb","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":"z-ai/glm-5.3-flashx","name":"Z.ai: GLM 5.3 FlashX","aliases":["Z.ai: GLM 5.3 FlashX"],"context":1048576,"medusaId":"z-ai/glm-5.3-flashx","released":"2026-09-18T15:07:00.000Z","developer":"z-ai","parameters":["include_reasoning","max_tokens","reasoning","reasoning_effort","response_format","temperature","tool_choice","tools","top_k","top_p"],"description":"GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and linear attention architecture...","benchmarkKey":"z-ai/glm-5.3-flashx-20260918","sourceIdentity":{"source":"openrouter","version":"sfaie.source-model-identity.v1","sourceId":"z-ai/glm-5.3-flashx","reference":"https://openrouter.ai/api/v1/models","observedAt":"2026-10-17T14:13:14.864Z","canonicalId":"z-ai/glm-5.3-flashx-20260918","expirationDate":null},"inputModalities":["text","image","video"],"outputModalities":["text"],"offers":[{"id":"openrouter:z-ai/glm-5.3-flashx:z-ai/fp8","tier":"standard","unit":"1M tokens","input":0.37,"output":1.25,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":1048576,"latency":2.6395,"modelId":"z-ai/glm-5.3-flashx","currency":"USD","provider":"Z.AI","cacheRead":0.09,"maxOutput":131072,"retention":null,"sourceUrl":"https://openrouter.ai/z-ai/glm-5.3-flashx","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T14:04:18.887Z","parameters":["reasoning","include_reasoning","max_tokens","temperature","top_p","tools","tool_choice","top_k","response_format","reasoning_effort"],"provenance":"aggregator","throughput":82,"pricingRules":null,"quantization":"fp8","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":2639.5}],"firstSeen":"2026-09-19T04:24:24.719Z","ticker":"GLM53F4A","headlineOfferId":"openrouter:z-ai/glm-5.3-flashx:z-ai/fp8","displayName":"GLM 5.3 FlashX","brandedName":"Z.ai GLM 5.3 FlashX"}}