{"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":"meta-llama-llama-3-1-8b-instruct-ee485h","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":"meta-llama/llama-3.1-8b-instruct","name":"Meta: Llama 3.1 8B Instruct","aliases":["Meta: Llama 3.1 8B Instruct"],"context":131072,"medusaId":"meta-llama/llama-3.1-8b-instruct","released":"2024-07-23T00:00:00.000Z","developer":"meta-llama","parameters":["frequency_penalty","logit_bias","logprobs","max_tokens","min_p","presence_penalty","repetition_penalty","response_format","seed","stop","structured_outputs","temperature","tool_choice","tools","top_k","top_logprobs","top_p"],"description":"Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...","benchmarkKey":"meta-llama/llama-3.1-8b-instruct","sourceIdentity":{"source":"openrouter","version":"sfaie.source-model-identity.v1","sourceId":"meta-llama/llama-3.1-8b-instruct","reference":"https://openrouter.ai/api/v1/models","observedAt":"2026-10-17T14:01:14.886Z","canonicalId":"meta-llama/llama-3.1-8b-instruct","expirationDate":null},"inputModalities":["text"],"outputModalities":["text"],"offers":[{"id":"openrouter:meta-llama/llama-3.1-8b-instruct:cloudflare/fp8","tier":"standard","unit":"1M tokens","input":0.152,"output":0.287,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":32000,"latency":0.43,"modelId":"meta-llama/llama-3.1-8b-instruct","currency":"USD","provider":"Cloudflare","cacheRead":null,"maxOutput":28800,"retention":null,"sourceUrl":"https://openrouter.ai/meta-llama/llama-3.1-8b-instruct","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:48:18.757Z","parameters":["max_tokens","temperature","top_p","top_k","seed","repetition_penalty","frequency_penalty","presence_penalty","min_p","stop","logit_bias","response_format","tools"],"provenance":"aggregator","throughput":17,"pricingRules":null,"quantization":"fp8","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":430},{"id":"openrouter:meta-llama/llama-3.1-8b-instruct:coreweave/bf16","tier":"standard","unit":"1M tokens","input":0.22,"output":0.22,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":131072,"latency":0.242,"modelId":"meta-llama/llama-3.1-8b-instruct","currency":"USD","provider":"CoreWeave","cacheRead":0.22,"maxOutput":117964,"retention":null,"sourceUrl":"https://openrouter.ai/meta-llama/llama-3.1-8b-instruct","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:48:18.757Z","parameters":["structured_outputs","response_format","max_tokens","temperature","top_p","top_k","repetition_penalty","frequency_penalty","presence_penalty","stop","seed","tools","tool_choice","logprobs","top_logprobs"],"provenance":"aggregator","throughput":139,"pricingRules":null,"quantization":"bf16","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":242},{"id":"openrouter:meta-llama/llama-3.1-8b-instruct:deepinfra/fp8","tier":"standard","unit":"1M tokens","input":0.02,"output":0.04,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":131072,"latency":0.577,"modelId":"meta-llama/llama-3.1-8b-instruct","currency":"USD","provider":"DeepInfra","cacheRead":null,"maxOutput":16384,"retention":null,"sourceUrl":"https://openrouter.ai/meta-llama/llama-3.1-8b-instruct","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:48:18.757Z","parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","repetition_penalty","top_k","seed","min_p","logit_bias","response_format","tools"],"provenance":"aggregator","throughput":28,"pricingRules":null,"quantization":"fp8","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":577},{"id":"openrouter:meta-llama/llama-3.1-8b-instruct:groq","tier":"standard","unit":"1M tokens","input":0.05,"output":0.08,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":131072,"latency":0.116,"modelId":"meta-llama/llama-3.1-8b-instruct","currency":"USD","provider":"Groq","cacheRead":0.025,"maxOutput":117964,"retention":null,"sourceUrl":"https://openrouter.ai/meta-llama/llama-3.1-8b-instruct","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:48:18.757Z","parameters":["max_tokens","temperature","top_p","stop","seed","response_format","tools","tool_choice"],"provenance":"aggregator","throughput":334,"pricingRules":null,"quantization":null,"performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":116},{"id":"openrouter:meta-llama/llama-3.1-8b-instruct:novita/fp8","tier":"standard","unit":"1M tokens","input":0.02,"output":0.05,"region":null,"source":"openrouter","status":"priced","uptime":100,"channel":"openrouter","context":16384,"latency":0.5,"modelId":"meta-llama/llama-3.1-8b-instruct","currency":"USD","provider":"Novita","cacheRead":null,"maxOutput":14745,"retention":null,"sourceUrl":"https://openrouter.ai/meta-llama/llama-3.1-8b-instruct","unitPrice":null,"cacheWrite":null,"observedAt":"2026-10-17T13:48:18.757Z","parameters":["max_tokens","temperature","top_p","stop","frequency_penalty","presence_penalty","seed","top_k","repetition_penalty","response_format","logprobs","top_logprobs","tools"],"provenance":"aggregator","throughput":114,"pricingRules":null,"quantization":"fp8","performanceWindow":"Previous 30 minutes; reported by OpenRouter","latencyMs":500}],"firstSeen":"2026-09-16T23:50:33.173Z","ticker":"LLAMA318BH","headlineOfferId":"openrouter:meta-llama/llama-3.1-8b-instruct:deepinfra/fp8","displayName":"Llama 3.1 8B Instruct","brandedName":"Meta Llama 3.1 8B Instruct"}}