Granite 4.2 8B 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.

CompareGranite 4.2 8BGLM 5.3


Granite 4.2 8B	1/2	100% CoreWeave	99.98% CoreWeave	96.77% CoreWeave	312ms CoreWeave	972ms CoreWeave	58 tps CoreWeave	131K	$0.060 / $0.250 DeepInfra
GLM 5.3	25/40	100% AkashML	99.98% Friendli	99.94% Sail Research	362ms Together	2.10s AkashML	122 tps Together	1.3M	$0.700 / $2.20 StreamLake

Measured 3m 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.