
6 offers at on-demand rates across 6 providers that publish this card — cheapest first, in USD (non-USD marked “≈”). Rates are per GPU-hour; the total is what the whole configuration costs.
Standalone A10 — distinct chip from AWS's A10G, kept as a separate model.
OVHcloudfrom ≈$1.03/GPU/hr
Cerebriumfrom $1.10/GPU/hr
Modalfrom $1.10/GPU/hr
Lambdafrom $1.29/GPU/hr
Runcratefrom $1.42/GPU/hr