Model scorecard
Meta llama-guard-3-8b
Composite 71.3/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+71.3/100meta/llama-guard-3-8btext · 8k context
Capability
eval compositeQuality (blended eval)65
Category: cheap
Usable context0
8k advertised window
Serving
gateway measuredThroughput97
340 output tokens/s median
Time to first token90
60ms p50
Economics
at provider costPrice efficiency100
$0.05 per 1M output tokens
Quality per dollar100
llmcloud adds $0 to these token prices.
Suggested usage
Not a default pick today. It is a reasonable explicit choice when you need this vendor specifically, or as a failover target inside auto:cheap.
→ Full workload matrix