Model scorecard
Sakana sarashina2-vision-14b
Composite 66.7/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B+66.7/100sakana/sarashina2-vision-14btext · vision · 32k context
Capability
eval compositeQuality (blended eval)71
Category: vision
Usable context2
32k advertised window
Serving
gateway measuredThroughput63
220 output tokens/s median
Time to first token80
120ms 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:vision.
→ Full workload matrix