Model scorecard
Inflection inflection-3-productivity
Composite 63.0/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.
B63.0/100inflection/inflection-3-productivitytext · 8k context
Capability
eval compositeQuality (blended eval)75
Category: cheap
Usable context0
8k advertised window
Serving
gateway measuredThroughput51
180 output tokens/s median
Time to first token73
160ms p50
Economics
at provider costPrice efficiency66
$2.50 per 1M output tokens
Quality per dollar90
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