Live rates — RunPod Secure vs RunPod Community vs Vast.ai Verified
| GPU | VRAM (GB) | RunPod Secure ($/hr) | RunPod Community ($/hr) | Vast.ai Verified ($/hr) | Lowest ($/hr) | Vast live rigs | RunPod Secure 730h | Vast 730h | Deploy |
|---|---|---|---|---|---|---|---|---|---|
| H100 PCIe 80GB | 80 | $2.89 | $1.99 | $2.14 | $1.99 | 2 | $2109.70 | $1558.99 | RunPodVast.ai |
| H100 SXM 80GB | 80 | $4.39 | $2.69 | $2.27 | $2.27 | 1 | $3204.70 | $1656.30 | Vast.aiRunPod |
| H100 NVL 94GB | 94 | $3.19 | $2.59 | — | $2.59 | 0 | $2328.70 | — | RunPodVast.ai |
Dual/quad reference for H100 PCIe 80GB: RunPod 2x from $3.98/hr, Vast.ai 2x from $4.27/hr, lowest 2x floor $3.98/hr. 4x floors: RunPod $7.96, Vast.ai $8.54, lowest $7.96/hr.
Open-model compatibility — 1x vs 2x at 32K context
| Open model (32K ctx) | H100 PCIe 80GB 1x | H100 PCIe 80GB 2x | H100 SXM 80GB 1x | H100 SXM 80GB 2x | H100 NVL 94GB 1x | H100 NVL 94GB 2x |
|---|---|---|---|---|---|---|
| Qwen3.8-27B | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) |
| Qwen3.8-Flash-Next | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x Fits FP8 (32K) Fits INT4 (32K) |
| Arete-27B | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) |
| diffusiongemma-26B-A4B-it | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) | Fits FP16 (32K) Fits FP8 (32K) Fits INT4 (32K) |
| MiniMax-M3.1-Flash | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) |
| GLM-5.3-Flash | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) |
| GLM-5.3 | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| GLM-5.2 | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| DeepSeek-V4.1-Flash-1017 | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| DeepSeek-V4.1-Flash | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| DeepSeek-V4-Flash-0731 | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) |
| DeepSeek-V4-Pro-0813 | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| Kimi-K2.7-Code | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| Kimi-K3.1-Pro | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| Qwen3.8-2.4T-A95B | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x |
| DeepSeek-V4-Flash-DSpark | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x No fit at 2x | Requires 2x+ Requires 2x+ Requires 2x+ | No fit at 2x No fit at 2x Fits INT4 (32K) |
Verdicts hard-computed from each repo's safetensors and config: FP16 (16-bit), FP8 (8-bit) and INT4 (4.5-bit effective) weights + GQA KV cache at 32768 tokens + runtime overhead, concurrency 1.
What the monthly gap looks like
Rent a H100 PCIe 80GB around the clock (730 h/month): RunPod Secure bills $2109.70/mo, while the cheapest verified, rentable Vast.ai bundle bills $1558.99/mo — a real gap of $550.71 every month ($6608.54 per year) for the identical GPU class. Locking a yearly hyperscaler contract instead of checking this table is where the real money leaks.