H100 SXM vs RTX PRO 6000 Blackwell
The RTX PRO 6000 Blackwell rents for 41% less per hour today — $2.05 against $3.50 — with 96 GB against 80 GB of memory.
Prices collected 2026-09-18 · 23 providers price both
Index median per GPU-hour, on-demand, per snapshot.
Side by side
| H100 SXM | RTX PRO 6000 Blackwell | |
|---|---|---|
| Median rental, per GPU-hour | $3.50 | $2.05 |
| Cheapest listing | $1.68 | $0.80 |
| Per month at 720 h | $2,516 | $1,472 |
| Providers pricing it | 46 | 24 |
| Memory | 80 GB HBM3 | 96 GB GDDR7 |
| Memory bandwidth | 3,350 GB/s | 1,792 GB/s |
| GB of memory per $/hr | 22.9 | 46.9 |
| Architecture | Hopper | Blackwell |
| Class | Datacenter | Workstation |
| Released | 2022-09 | 2025-04 |
Same provider, both GPUs
The cleanest comparison: 23 providers price both cards, so the difference is the GPU and nothing else. The H100 SXM is cheaper at 2 of them.
| Provider | H100 SXM | RTX PRO 6000 Blackwell | RTX PRO 6000 Blackwell premium |
|---|---|---|---|
 Latitude.sh | $1.68 | $3.00 | +79% |
 HyperAI | $1.80 | $0.80 | -56% |
 Seeweb | $2.17 | $1.44 | -34% |
 Hyperstack | $2.60 | $1.85 | -29% |
| $2.64 | $2.27 | -14% | |
 RunPod Community Cloud | $2.69 | $1.69 | -37% |
 Jarvislabs | $2.69 | $1.89 | -30% |
| $2.69 | $1.90 | -29% | |
 Northflank | $2.74 | $3.00 | +9% |
 Runcrate | $2.75 | $2.41 | -12% |
| $2.81 | $2.19 | -22% | |
 Cerebrium | $3.40 | $2.50 | -26% |
 Vast.ai | $3.45 | $1.47 | -57% |
 RunPod Secure Cloud | $3.49 | $2.14 | -39% |
 Beam | $3.50 | $1.09 | -69% |
 DataCrunch (Verda) | $3.52 | $1.90 | -46% |
 GPU.ai | $3.69 | $1.84 | -50% |
 io.net | $3.76 | $2.24 | -40% |
 Nebius | $3.85 | $1.80 | -53% |
 Modal | $3.95 | $3.03 | -23% |
 fal.ai | $4.50 | $2.99 | -34% |
 CoreWeave | $6.16 | $2.50 | -59% |
 Oracle Cloud | $10.00 | $4.50 | -55% |
What each one runs, and what a million tokens costs
Weights + KV cache at 8K context + overhead against 90% of each card's memory. Where a model needs more than one card the cell says how many and prices the set at today's median. $/M tokens is the hourly median divided by estimated single-stream output, from memory bandwidth — an estimate for ranking, not a benchmark.
| Model | Bits | H100 SXM | RTX PRO 6000 Blackwell |
|---|---|---|---|
| Kimi K3 | 4-bit | 22× GPU$76.89/hr | 19× GPU$38.85/hr |
| Kimi K3 | 16-bit | 78× GPU$272.61/hr | 65× GPU$132.92/hr |
| DeepSeek V4.1-Flash | 4-bit | 5× GPU$17.48/hr | 4× GPU$8.18/hr |
| DeepSeek V4.1-Flash | 16-bit | 16× GPU$55.92/hr | 13× GPU$26.59/hr |
| Llama 4 Maverick | 4-bit | 4× GPU$13.98/hr | 3× GPU$6.14/hr |
| Llama 4 Maverick | 16-bit | 12× GPU$41.94/hr | 10× GPU$20.45/hr |
| gpt-oss-120b | 4-bit | ✓ 67.9 GB~934 tok/s · $1.04/M | ✓ 67.9 GB~500 tok/s · $1.14/M |
| gpt-oss-120b | 16-bit | 4× GPU$13.98/hr | 3× GPU$6.14/hr |
| Llama 3.1 70B | 4-bit | ✓ 44.5 GB~68 tok/s · $14.28/M | ✓ 44.5 GB~36 tok/s · $15.78/M |
| Llama 3.1 70B | 16-bit | 3× GPU$10.49/hr | 2× GPU$4.09/hr |
| Gemma 4 31B | 4-bit | ✓ 21.2 GB~154 tok/s · $6.3/M | ✓ 21.2 GB~82 tok/s · $6.93/M |
| Gemma 4 31B | 16-bit | ✓ 65.7 GB~43 tok/s · $22.58/M | ✓ 65.7 GB~23 tok/s · $24.7/M |
| Qwen3 Coder 30B-A3B | 4-bit | ✓ 19 GB~1444 tok/s · $0.67/M | ✓ 19 GB~772 tok/s · $0.74/M |
| Qwen3 Coder 30B-A3B | 16-bit | ✓ 62.9 GB~406 tok/s · $2.39/M | ✓ 62.9 GB~217 tok/s · $2.62/M |
| Qwen3.8 27B | 4-bit | ✓ 18.7 GB~176 tok/s · $5.52/M | ✓ 18.7 GB~94 tok/s · $6.04/M |
| Qwen3.8 27B | 16-bit | ✓ 57.6 GB~50 tok/s · $19.42/M | ✓ 57.6 GB~27 tok/s · $21.04/M |
| gpt-oss-20b | 4-bit | ✓ 13.7 GB~1323 tok/s · $0.73/M | ✓ 13.7 GB~708 tok/s · $0.8/M |
| gpt-oss-20b | 16-bit | ✓ 43.9 GB~372 tok/s · $2.61/M | ✓ 43.9 GB~199 tok/s · $2.85/M |
| Llama 3.1 8B | 4-bit | ✓ 6.9 GB~596 tok/s · $1.63/M | ✓ 6.9 GB~319 tok/s · $1.78/M |
| Llama 3.1 8B | 16-bit | ✓ 18.4 GB~168 tok/s · $5.78/M | ✓ 18.4 GB~90 tok/s · $6.31/M |
Buy or rent?
Hours of renting at today's median that add up to the card's approximate list price. List prices are typical quoted figures, not tracked, and do not include the server, power or the person to run it — so the break-even is a floor, not a verdict.
Questions
Is the H100 SXM or the RTX PRO 6000 Blackwell cheaper to rent?
On 2026-09-18 the H100 SXM has a market median of $3.50 per GPU-hour across 46 providers and the RTX PRO 6000 Blackwell $2.04 across 24, so the RTX PRO 6000 Blackwell is 41% cheaper per hour. Among the 23 providers that price both, the H100 SXM is cheaper at 2 and the RTX PRO 6000 Blackwell at 21. Per hour is only half the answer — the table below prices a whole model on each.
Which should I rent for a 70B model?
At 4-bit, Llama 3.1 70B needs about 44.5 GB. On the H100 SXM that is one card at $3.50/hr; on the RTX PRO 6000 Blackwell one card at $2.05/hr. Estimated single-stream decode is ~68 vs ~36 tokens per second, from memory bandwidth.
What is the real difference between them?
80 GB HBM3 at 3,350 GB/s (Hopper) against 96 GB GDDR7 at 1,792 GB/s (Blackwell). Memory decides what fits; bandwidth decides how fast it generates, because each token streams the active weights once. Compute matters for prompt processing and training, not for how fast text appears.