GPU comparison · live prices
A100 vs 5090: price per hour and cost per token
Last generation, often the cheapest datacenter GPU per hour for models that fit. Consumer card, cheap per hour; great for small models, slow when split across many.
Prices observed 12m ago · refreshed every 15 minutes
| NVIDIA A100 80GB | NVIDIA RTX 5090 | |
|---|---|---|
| Memory | 80 GB HBM2e | 32 GB GDDR7 |
| Memory bandwidth | 2.0 TB/s | 1.8 TB/s |
| Cheapest on-demandper GPU-hour | $0.34Vast.ai | $0.46Vast.ai |
| Cheapest spotper GPU-hour | —None in stock | —None in stock |
| Providers in stock | 3 | 3 |
Per GPU-hour on demand, the 5090 costs 1.37× the A100. Per token, that depends on the model:
Cost per 1M output tokens
Cheapest on-demand offer, GPUs per replica to fit the model, 60% average utilization.
A100 is cheaper per token for every model below that runs on both at today’s prices.
| Model | A100 | 5090 |
|---|---|---|
| Llama 3.1 8BBF16 | $0.05 1× GPUs · ~3,059 tok/s | $0.08 1× GPUs · ~2,688 tok/s |
| Qwen 2.5 32BFP8 | $0.10 1× GPUs · ~1,506 tok/s | $0.27 2× GPUs · ~1,588 tok/s |
| Llama 3.3 70BFP8 | $0.22 2× GPUs · ~1,386 tok/s | $0.58 4× GPUs · ~1,462 tok/s |
| Mixtral 8x22BFP8 | $0.12 4× GPUs · ~5,019 tok/s | $0.32 8× GPUs · ~5,293 tok/s |
| Llama 3.1 405BFP8 | $1.29 8× GPUs · ~967 tok/s | — Doesn’t fit on 8 |
| DeepSeek V3 (671B MoE)FP8 | — Doesn’t fit on 8 | — Doesn’t fit on 8 |
Estimates: tokens/s from memory bandwidth with batched serving, not a benchmark. Check each provider before you buy.