Model scorecard
LMMs-Lab llava-onevision-72b
Composite 60.3/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B60.3/100lmms-lab/llava-onevision-72btext · vision · 32k context
Capability
eval compositeQuality (blended eval)74
Category: vision
Usable context2
32k advertised window
Serving
gateway measuredThroughput29
100 output tokens/s median
Time to first token50
300ms p50
Economics
at provider costPrice efficiency76
$0.80 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:vision.
→ Full workload matrix