DeepSeek V3 vs DeepSeek V4 Pro 0813

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.

CompareDeepSeek V3DeepSeek V4 Pro 0813


DeepSeek V3	1/3	99.42% StreamLake	98.86% StreamLake	98.22% StreamLake	684ms DeepInfra	6.66s StreamLake	41 tps StreamLake	164K	$0.257 / $1.03 StreamLake
DeepSeek V4 Pro 0813	17/28	100% Baidu	99.96% DeepSeek	99.97% DeepSeek	561ms CoreWeave	2.63s DigitalOcean	125 tps CoreWeave	1.0M	$0.220 / $4.20 Wafer

Measured 2m 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.