Model scorecard
Alibaba qwen3-8b
Composite 72.3/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
A72.3/100alibaba/qwen3-8btext · 128k context
Capability
eval compositeQuality (blended eval)70
Category: cheap
Usable context6
128k advertised window
Serving
gateway measuredThroughput91
320 output tokens/s median
Time to first token87
80ms p50
Economics
at provider costPrice efficiency94
$0.10 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