← GPU cloud (on-demand)
Crusoe Cloud
Crusoe AMD MI300X
192GB AMD Instinct MI300X, good for large-model inference.
USD per GPU-hour
$3.45
Verified Oct 6, 2026
#9 cheapest of 20 in GPU cloud (on-demand)
Official pricing ↗Capabilities, explained
What this API can do, and what each capability means for your project.
GPU
MI300X
The GPU model. Newer generations are faster per dollar for large models.
VRAM
192 GB
Memory per GPU. A 70B-parameter model needs ~140 GB in 16-bit, or ~40 GB quantised.
Interconnect
—
How fast GPUs talk to each other; matters for multi-GPU training.
Regions
—
Where the hardware is located (latency, data residency).
Per-second billing
—
You pay only for the seconds used rather than full hours.
Price history
Only one price recorded so far. The chart appears once the price changes.