Model scorecard
Moonshot kimi-linear-48b
Composite 75.5/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
A75.5/100moonshot/kimi-linear-48btext · 1000k context
Capability
eval compositeQuality (blended eval)77
Category: long
Usable context50
1000k advertised window
Serving
gateway measuredThroughput69
240 output tokens/s median
Time to first token83
100ms p50
Economics
at provider costPrice efficiency84
$0.30 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:long.
→ Full workload matrix