llmcloud.ai
Model scorecard

OpenAI gpt-5-mini

Composite 74.7/100 across quality, throughput, latency, price efficiency and usable context — measured through the gateway, not vendor-reported.

A74.7/100openai/gpt-5-minitext · vision · 400k context

Capability

eval composite
Quality (blended eval)84

Category: cheap

Usable context20

400k advertised window

Serving

gateway measured
Throughput61

215 output tokens/s median

Time to first token79

125ms p50

Economics

at provider cost
Price efficiency83

$0.35 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