providers
offerings
2
GPU SKUs
3
regions
us · eu
tags
inference · low-latency
:: GPU compute SKUs
GPUVRAMregion$/hr$/gpu·secnotesverified
- A100-40GB[cheapest]40 GB美洲$1.10——2d ago
- A100-80GB80 GB美洲$1.50——2d ago
- H10080 GB美洲$2.40——2d ago
:: offerings · pricing · limits
filter:2 / 2
modelctxstatuspricing · $/Mrate limitsverified
- 128Kactive[标准] in $0.700/M out $0.700/M—2d ago
Llama 3.3 70B
文本Function CallingJSON Mode流式
- 128Kactive[标准] in $0.200/M out $0.600/M—2d ago
Mistral Small
文本Function CallingJSON Mode流式