Vast.ai vs RunPod
A comparison of Vast.ai and RunPod built from values read directly from each provider's own documentation, with the source recorded against every figure.
The short answer
- Pick Vast.ai if
- Price-sensitive training and batch inference that can tolerate a marketplace — the median H100 rate is well under half what the managed clouds charge, and interruptible capacity goes lower still.
- Pick RunPod if
- Short experiments and bursty inference — per-second billing and a $0.27 entry card mean an idle hour costs nothing and a small job is genuinely small.
3 sourced criteria separate them:
- H100 SXM, per GPU-hour
- Vast.ai: Median $2.16 per hour for H100 SXM 80GB, with a floor of $1.33 from the cheapest host. Vast is a marketplace — the floor is one host's offer at one moment and the median is what the market is actually charging, so both move without anyone announcing anything. This figure is a snapshot, not a rate card.
- RunPod: $3.49 per hour for H100 SXM 80GB, single card. The PCIe variant is $2.89 and H100 NVL is $3.19.
- Cheapest GPU, per hour
- Vast.ai: Floor and median vary by card and by the hour; H100 PCIe runs from $1.87 with a median of $2.67, and H200 from $1.97 with a median of $4.24. The H200 floor now sits below the H100 PCIe median, which is the kind of inversion a marketplace produces and a rate card cannot.
- RunPod: $0.27 per hour for an RTX A5000 with 24GB. RTX 3090 is $0.50, RTX 4090 $0.74, L40S $1.09.
- Largest GPU offered
- Vast.ai: 192GB per GPU on B200, from $4.38 an hour with a median of $7.50.
- RunPod: 288GB per GPU on B300; B200 at 180GB is $6.79 an hour and H200 at 141GB is $4.59.
Pick the criteria you care about. The chart counts how many of them lean toward each provider — the same read as scanning the bars below, just totalled for the ones you chose.
Vast.ai 0
RunPod 0
At a glance.
| Criterion | Vast.ai | RunPod |
|---|---|---|
| GPU | ||
| H100 SXM, per GPU-hour | Median $2.16 per hour for H100 SXM 80GB, with a floor of $1.33 from the cheapest host. Vast is a marketplace — the floor is one host's offer at one moment and the median is what the market is actually charging, so both move without anyone announcing anything. This figure is a snapshot, not a rate card. | $3.49 per hour for H100 SXM 80GB, single card. The PCIe variant is $2.89 and H100 NVL is $3.19. |
| Cheapest GPU, per hour | Floor and median vary by card and by the hour; H100 PCIe runs from $1.87 with a median of $2.67, and H200 from $1.97 with a median of $4.24. The H200 floor now sits below the H100 PCIe median, which is the kind of inversion a marketplace produces and a rate card cannot. | $0.27 per hour for an RTX A5000 with 24GB. RTX 3090 is $0.50, RTX 4090 $0.74, L40S $1.09. |
| Largest GPU offered | 192GB per GPU on B200, from $4.38 an hour with a median of $7.50. | 288GB per GPU on B300; B200 at 180GB is $6.79 an hour and H200 at 141GB is $4.59. |
Where they differ.
H100 SXM, per GPU-hour
- Vast.ai
- Median $2.16 per hour for H100 SXM 80GB, with a floor of $1.33 from the cheapest host. Vast is a marketplace — the floor is one host's offer at one moment and the median is what the market is actually charging, so both move without anyone announcing anything. This figure is a snapshot, not a rate card.
- RunPod
- $3.49 per hour for H100 SXM 80GB, single card. The PCIe variant is $2.89 and H100 NVL is $3.19.
Sources (2) →Sources ↓
- Pricing — Vast.ai ↗
“H100 SXM Hopper 80GB VRAM from $1.33 /hr median $2.16/hr”
Read 2026-09-08 · official pricing
- Pricing — RunPod ↗
“H100 SXM 80 GB VRAM 125 GB RAM 20 vCPUs $ 3.49 /hr [...] H100 PCIe 80 GB VRAM 188 GB RAM 16 vCPUs $ 2.89 /hr [...] H100 NVL 94 GB VRAM 94 GB RAM 16 vCPUs $ 3.19 /hr”
Read 2026-09-06 · official pricing
Cheapest GPU, per hour
- Vast.ai
- Floor and median vary by card and by the hour; H100 PCIe runs from $1.87 with a median of $2.67, and H200 from $1.97 with a median of $4.24. The H200 floor now sits below the H100 PCIe median, which is the kind of inversion a marketplace produces and a rate card cannot.
- RunPod
- $0.27 per hour for an RTX A5000 with 24GB. RTX 3090 is $0.50, RTX 4090 $0.74, L40S $1.09.
Sources (2) →Sources ↓
- Pricing — Vast.ai ↗
“H100 PCIE Hopper 80GB VRAM from $1.87 /hr median $2.67/hr [...] H200 Hopper 141GB VRAM from $1.97 /hr median $4.24/hr”
Read 2026-09-08 · official pricing
- Pricing — RunPod ↗
“RTX A5000 24 GB VRAM 25 GB RAM 9 vCPUs $ 0.27 /hr [...] RTX 3090 24 GB VRAM [...] $ 0.5 /hr [...] L40S 48 GB VRAM 94 GB RAM 16 vCPUs $ 1.09 /hr”
Read 2026-09-06 · official pricing
Largest GPU offered
192GB per GPU on B200, from $4.38 an hour with a median of $7.50.
288GB per GPU on B300; B200 at 180GB is $6.79 an hour and H200 at 141GB is $4.59.
Sources (2) →Sources ↓
- Pricing — Vast.ai ↗
“B200 Blackwell 192GB VRAM from $4.38 /hr median $7.50/hr”
Read 2026-09-08 · official pricing
- Pricing — RunPod ↗
“B300 288 GB HBM3e 251 GB RAM 32 vCPUs [...] B200 180 GB VRAM 283 GB RAM 28 vCPUs $ 6.79 /hr [...] H200 141 GB VRAM 276 GB RAM 24 vCPUs $ 4.59 /hr”
Read 2026-09-06 · official pricing
When these numbers change, hear about it. Sources are re-checked monthly; a repricing goes out as a short note.
Which should you choose?
Choose Vast.ai if…
Price-sensitive training and batch inference that can tolerate a marketplace — the median H100 rate is well under half what the managed clouds charge, and interruptible capacity goes lower still.
Editorial · Palash Bagchi · approved
Choose RunPod if…
Short experiments and bursty inference — per-second billing and a $0.27 entry card mean an idle hour costs nothing and a small job is genuinely small.
Editorial · Palash Bagchi · approved
Consider something else if…
- Vast.ai: There is no single price to plan against: rates move with supply, the host is not Vast itself, and an interruptible instance can be reclaimed mid-run.
- RunPod: The catalogue mixes community and secure capacity, so the cheapest quoted rate is not always the tier a production workload should sit on.
Documented by only one.
These criteria are published by one provider and not the other. An absence here means we have not found a source, not that the feature is missing.
Questions this comparison answers.
Should I choose Vast.ai or RunPod?
Pick Vast.ai if Price-sensitive training and batch inference that can tolerate a marketplace — the median H100 rate is well under half what the managed clouds charge, and interruptible capacity goes lower still.
Pick RunPod if Short experiments and bursty inference — per-second billing and a $0.27 entry card mean an idle hour costs nothing and a small job is genuinely small.