Phi 4 vs DeepSeek V4 Flash 0731

One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.

ComparePhi 4DeepSeek V4 Flash 0731


Phi 4	1/1	100% DeepInfra	378ms DeepInfra	4.46s DeepInfra	67 tps DeepInfra	16K	$0.070 / $0.140 DeepInfra
DeepSeek V4 Flash 0731	27/30	100% BaseTen	550ms DigitalOcean	2.94s DeepSeek	117 tps Baidu	1.3M	$0.065 / $0.140 OpenInference

Measured 1m ago. Each figure is the best available across that model's providers.

History

Availability

Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.

Time to first token

Fastest P50 available from any provider. Logarithmic axis.

Throughput

Best median tokens per second available.