8 GPUs in common. Modal is cheaper on 3, Vast.ai on 5; on average Vast.ai is 22% below Modal.
Prices collected 2026-09-18
| GPU | Modal | Vast.ai | Difference | Market |
|---|---|---|---|---|
| $7.10 | $9.38 | Modal −24% | $7.85 | |
| $6.25 | $8.75 | Modal −29% | $6.59 | |
| $4.54 | $4.67 | Modal −3% | $4.45 | |
| $3.95 | $3.45 | Vast.ai −13% | $3.50 | |
| $3.03 | $1.47 | Vast.ai −51% | $2.05 | |
| $2.50 | $0.80 | Vast.ai −68% | $1.79 | |
| $1.95 | $0.80 | Vast.ai −59% | $1.47 | |
| $0.80 | $0.33 | Vast.ai −59% | $0.80 |
On the 8 GPUs both price on 2026-09-18, Modal is cheaper on 3 and Vast.ai on 5. On average Vast.ai is 22% cheaper than Modal across those GPUs. The table shows each one; the gap is rarely uniform.
Modal alone prices A100 40GB, A10, T4; Vast.ai alone prices H200 NVL, H100 NVL, H100 PCIe, L40, A40, RTX 4090, RTX 6000 Ada, RTX 5090, RTX A6000, RTX 5080, RTX 4080, RTX 3090, RTX A5000, V100 16GB, RTX A4000. They are different kinds of provider — Modal is a neocloud, Vast.ai a marketplace — which is most of why the prices differ.
Modal: Public pricing page, parsed. Per-GPU price is the listed per-GPU rate, or the node price divided by GPU count. Prices near reserved, committed or contract terms are discarded; anything outside a plausible range for the GPU is discarded. Vast.ai: Public offer search, verified and rentable hosts only. Each offer is one observation; on-demand rate, not interruptible bids. Both are read every six hours; nothing is estimated.