Model scorecard
Meta llama-3.1-405b-instruct
Composite 66.7/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+66.7/100meta/llama-3.1-405b-instructtext · 128k context
Capability
eval compositeQuality (blended eval)85
Category: reasoning
Usable context6
128k advertised window
Serving
gateway measuredThroughput37
130 output tokens/s median
Time to first token67
200ms p50
Economics
at provider costPrice efficiency65
$2.70 per 1M output tokens
Quality per dollar95
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:reasoning.
→ Full workload matrix