Models · Mistral · live prices
Mistral 7B: GPUs needed and cost to self-host
7.2B parameters. In BF16 that is about 17 GB with room for the KV cache.
Memory, BF16
17 GB
weights + ~20%
Cheapest per 1M output tokens
$0.05
1× A100 · on-demand · 60% utilization
Hosted API, sample list price
$0.20
per 1M output tokens
Cost per 1M output tokens, BF16
Prices observed 11m ago. Cheapest on-demand offer per GPU, whole instances, 60% average utilization.
- A10080 GB 1× on Vast.ai · on-demand · $0.34/hr · ~3,398 tok/s $0.05per 1M out
- 509032 GB 1× on Vast.ai · on-demand · $0.46/hr · ~2,987 tok/s $0.07per 1M out
- H200141 GB 1× on Vast.ai · on-demand · $1.32/hr · ~8,000 tok/s $0.08per 1M out
- 409024 GB 1× on Vast.ai · on-demand · $0.31/hr · ~1,680 tok/s $0.09per 1M out
- RTX PRO 600096 GB 1× on Vast.ai · on-demand · $1.00/hr · ~2,987 tok/s $0.16per 1M out
- H10080 GB 1× on RunPod · community · $1.99/hr · ~5,583 tok/s $0.17per 1M out
- B300288 GB 1× on RunPod · community · $6.94/hr · ~13,333 tok/s $0.24per 1M out
The tick marks the sample hosted-API price. Estimates: tokens/s from memory bandwidth with batched serving, not a benchmark. Idle hours still bill, so lower utilization means pricier tokens.
GPUs per replica by precision
One node, split 1, 2, 4 or 8 ways; 90% of VRAM usable.
| GPU | BF1617 GB | FP89 GB | INT44 GB |
|---|---|---|---|
| H10080 GB | 1× | 1× | 1× |
| H200141 GB | 1× | 1× | 1× |
| B300288 GB | 1× | 1× | 1× |
| A10080 GB | 1× | 1× | 1× |
| RTX PRO 600096 GB | 1× | 1× | 1× |
| 509032 GB | 1× | 1× | 1× |
| 409024 GB | 1× | 1× | 1× |