Accessible GPUs for training and inference
Last reviewed Aug 11, 2026
Lyceum offers serverless inference, dedicated endpoints, GPU VMs, and large-scale clusters for AI workloads. The platform is designed to facilitate the deployment and management of AI solutions without the complexity of traditional infrastructure.
Hourly on-demand pricing. Click column headers to sort.
Prices last updated: September 14, 2026
Configurations, price rank, and alternatives for one GPU at a time.
Pay-per-token pricing. Prices shown per 1M tokens.
Prices last updated: September 15, 2026
| Model | Input/1M | Output/1M | |||
|---|---|---|---|---|---|
| $0.150 | $0.200 | ||||
| $0.200 | $0.600 | ||||
| $0.200 | $0.500 | ||||
| $0.200 | $0.500 | ||||
| $0.250 | $0.300 | ||||
| $0.300 | $0.450 | ||||
| $0.400 | $2.00 | ||||
| $0.400 | $2.40 | ||||
| $0.500 | $2.50 | ||||
| $0.500 | $1.50 | ||||
Input, output, and batch rates, plus alternatives, for one model at a time.
API access to open-source models with pay-per-token pricing.
Reserved GPU capacity for production models ensuring low latency and high availability.
Run training jobs on GPUs without the need for infrastructure management.
Full root access to customizable GPU instances ready in seconds.
Support for configurations from 8 to 8,000 GPUs with InfiniBand connectivity.
GPUs hosted in European data centres
Contact support via sales inquiry or demo booking.
Create an account on the Lyceum platform.
Select between inference, training, or virtual machine options.
Use provided API or CLI instructions to submit your workload.
Utilize dashboard features to track resource usage and performance.
Contact the sales or support team for assistance.
Lyceum offers various GPU types including A100 SXM, H100 SXM, H200, HGX B300, L40S, B200. Check the pricing table above for current availability and pricing.
Sign Up, Choose a Service, Deploy a Model or Job, Monitor Usage, Seek Support if Needed
Lyceum's main advantages include: Instant availability of GPUs with minimal provisioning time., No capacity planning or vendor lock-in required., Complies with EU data residency requirements..
Lyceum's main limitations include: Limited pricing information available publicly., Documentation and support resources not explicitly listed..
Find the best prices for the same GPUs and models from other providers