AMD · CDNA 4 · 288 GB HBM3e · OAM · 2025
1 providers · 4 configurations · prices as of Sep 27, 2026, 01:12 UTC
Daily Instinct MI350X prices per GPU-hour. The shaded period is reconstructed from the version history of SkyPilot's public price catalogs (fewer providers than live data); after that, PetaPrice's own tracking.
Cheapest On-demand Instinct MI350X offer at each provider, per GPU-hour. Shorter and greener is cheaper.
Thin vertical line = median across providers ($6.16).
1 providers · 4 configurations
GPUs with similar compute and memory, and their lowest on-demand price right now.
On-demand Instinct MI350X prices start at $6.16 per GPU-hour (DigitalOcean). The median across 1 providers is $6.16, and the most expensive is $6.16. Running one GPU around the clock costs about $4,497 per month at the lowest price.
Yes. Spot (interruptible) Instinct MI350X capacity starts at $2.46 per GPU-hour, 60% below the cheapest on-demand price. Spot instances can be preempted at any time, so use them for checkpointed training or batch jobs.
At $6.16 per hour and 2.31 PF of dense FP16/BF16, the Instinct MI350X costs $2.67 per PFLOP-hour. That ranks 44 of 70 GPUs with on-demand prices on PetaPrice. Figures are datasheet peaks; real utilization is typically 30–60%.
288 GB HBM3e with 8,000 GB/s of memory bandwidth, CDNA 4 architecture (2025), OAM form factor, 1000 W. Dense peak: 2.31 PF FP16 / BF16, 4.61 PF FP8, 9.23 PF FP4, 4.61 PF INT8, 0.144 PF FP32, 0.0721 PF FP64.
Prices were collected on Sep 27, 2026, 01:12 UTC from provider APIs and public catalogs and refresh about every 2 hours. They are indicative list prices; always confirm on the provider's website before booking.