Pareto vs GLM 5.3

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.

CompareParetoGLM 5.3


Pareto	1/1	100% Unbiased	100% Unbiased	100% Unbiased	4.64s Unbiased	155s Unbiased	38 tps Unbiased	262K	$2.50 / $7.50 Unbiased
GLM 5.3	23/40	100% Alibaba	99.98% Friendli	99.94% Sail Research	520ms Wafer	6.42s Alibaba	140 tps Wafer	1.3M	$0.700 / $2.20 StreamLake

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.