What is the difference between Lyceum and Novita AI?

Lyceum and Novita AI are both cloud GPU providers offering different pricing models, features, and GPU availability. Use our comparison tool to see real-time pricing and feature differences.

Which is cheaper: Lyceum or Novita AI?

Pricing varies by GPU model and usage requirements. Check our real-time comparison table to find the best deals for your specific needs.

Can I switch between Lyceum and Novita AI?

Yes, both providers offer flexible cloud GPU services. However, consider factors like data transfer costs, setup time, and specific features when switching between providers.

How many GPU models are available for comparison?

We track pricing for 8 different GPU models across both Lyceum and Novita AI, with 0 models available from both providers.

Lyceum vs Novita AI

Compare GPU and LLM inference API pricing between Lyceum and Novita AI. Find the best rates for AI training, inference, and ML workloads.

Lyceum

Provider 1

GPUs Available

Visit Website

Novita AI

Provider 2

GPUs Available

Visit Website

Comparison Overview

Total GPU Models

Lyceum GPUs

Novita AI GPUs

Direct Comparisons

Average Price Difference: $1.06/hour between comparable GPUs

GPU Pricing Comparison

Total GPUs: 8Both available: 2Lyceum: 6Novita AI: 4

Showing 8 of 8 GPUs

Last updated: 10/30/2026, 8:17:38 PM

GPU Model ↑	Lyceum Price	Novita AI Price	Price Diff ↕	Sources
A100 SXM 80GB VRAM • Lyceum	$1.19/hr★ Best	Not Available	—	Lyceum
A100 SXM 80GB VRAM • Lyceum $1.19/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
B200 180GB VRAM • Lyceum	$4.49/hr★ Best	Not Available	—	Lyceum
B200 180GB VRAM • Lyceum $4.49/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
H100 SXM 80GB VRAM • LyceumNovita AI	$2.39/hr	$1.70/hr★ Best	↑+$0.69(+40.6%)	Lyceum Novita Market API
H100 SXM 80GB VRAM • Lyceum $2.39/hour Updated: 10/26/2026 Novita AI $1.70/hour Updated: 10/30/2026 ★Best Price Price Difference:↑+$0.69(+40.6%) Lyceum Novita Market API
H200 141GB VRAM • Lyceum	$3.09/hr★ Best	Not Available	—	Lyceum
H200 141GB VRAM • Lyceum $3.09/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
HGX B300 288GB VRAM • Lyceum	$5.59/hr★ Best	Not Available	—	Lyceum
HGX B300 288GB VRAM • Lyceum $5.59/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
L40S 48GB VRAM • LyceumNovita AI	$1.99/hr	$0.55/hr★ Best	↑+$1.44(+261.8%)	Lyceum Novita Market API
L40S 48GB VRAM • Lyceum $1.99/hour Updated: 10/28/2026 Novita AI $0.55/hour Updated: 10/30/2026 ★Best Price Price Difference:↑+$1.44(+261.8%) Lyceum Novita Market API
RTX 4090 24GB VRAM • Novita AI	Not Available	$0.34/hr★ Best	—	Novita Market API
RTX 4090 24GB VRAM • Not Available Novita AI $0.34/hour Updated: 10/30/2026 ★Best Price Novita Market API
RTX 5090 32GB VRAM • Novita AI	Not Available	$0.36/hr★ Best	—	Novita Market API
RTX 5090 32GB VRAM • Not Available Novita AI $0.36/hour Updated: 10/30/2026 ★Best Price Novita Market API

A100 SXM 80GB VRAM • Lyceum	$1.19/hr★ Best	Not Available	—	Lyceum
A100 SXM 80GB VRAM • Lyceum $1.19/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
B200 180GB VRAM • Lyceum	$4.49/hr★ Best	Not Available	—	Lyceum
B200 180GB VRAM • Lyceum $4.49/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
H100 SXM 80GB VRAM • LyceumNovita AI	$2.39/hr	$1.70/hr★ Best	↑+$0.69(+40.6%)	Lyceum Novita Market API
H100 SXM 80GB VRAM • Lyceum $2.39/hour Updated: 10/26/2026 Novita AI $1.70/hour Updated: 10/30/2026 ★Best Price Price Difference:↑+$0.69(+40.6%) Lyceum Novita Market API
H200 141GB VRAM • Lyceum	$3.09/hr★ Best	Not Available	—	Lyceum
H200 141GB VRAM • Lyceum $3.09/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
HGX B300 288GB VRAM • Lyceum	$5.59/hr★ Best	Not Available	—	Lyceum
HGX B300 288GB VRAM • Lyceum $5.59/hour Updated: 10/26/2026 ★Best Price Not Available Lyceum
L40S 48GB VRAM • LyceumNovita AI	$1.99/hr	$0.55/hr★ Best	↑+$1.44(+261.8%)	Lyceum Novita Market API
L40S 48GB VRAM • Lyceum $1.99/hour Updated: 10/28/2026 Novita AI $0.55/hour Updated: 10/30/2026 ★Best Price Price Difference:↑+$1.44(+261.8%) Lyceum Novita Market API
RTX 4090 24GB VRAM • Novita AI	Not Available	$0.34/hr★ Best	—	Novita Market API
RTX 4090 24GB VRAM • Not Available Novita AI $0.34/hour Updated: 10/30/2026 ★Best Price Novita Market API
RTX 5090 32GB VRAM • Novita AI	Not Available	$0.36/hr★ Best	—	Novita Market API
RTX 5090 32GB VRAM • Not Available Novita AI $0.36/hour Updated: 10/30/2026 ★Best Price Novita Market API

LLM API Pricing Comparison

Total models: 60Both available: 10Lyceum: 12Novita AI: 58

Showing 15 of 60 models

Prices per 1M tokens · Last updated: 10/30/2026, 8:17:38 PM

Model ↑	Lyceum	Novita AI	Input Diff ↕
DeepSeek R1 DeepSeek	Not available	$0.700 in $2.50 out	—
DeepSeek R1 0528 Qwen3 8B DeepSeek	Not available	$0.060 in $0.090 out	—
DeepSeek V4 Flash DeepSeek	$0.250 in $0.300 out	Not available	—
DeepSeek V4 Pro DeepSeek	$2.00 in $4.00 out	$1.32 in $3.96 out	$0.680
DeepSeek V4.1 Flash DeepSeek	$0.500 in $1.50 out	$0.300 in $1.20 out	$0.200
ERNIE 4.5 21B Baidu	Not available	$0.070 in $0.280 out	—
Gemma 3 12B Google	Not available	$0.050 in $0.100 out	—
Gemma 3 27B Google	Not available	$0.119 in $0.200 out	—
Gemma 4 26B Google	Not available	$0.130 in $0.400 out	—
Gemma 4 31B Google	Not available	$0.140 in $0.400 out	—
GLM 4.7 Flash Z.ai	Not available	$0.070 in $0.400 out	—
GLM-4.5 Air Z.ai	Not available	$0.130 in $0.850 out	—
GLM-4.5V Z.ai	Not available	$0.600 in $1.80 out	—
GLM-4.6 Z.ai	Not available	$0.550 in $2.20 out	—
GLM-4.6V Z.ai	Not available	$0.300 in $0.900 out	—

Features Comparison

Lyceum

Serverless Inference
API access to open-source models with pay-per-token pricing.
Dedicated Endpoints
Reserved GPU capacity for production models ensuring low latency and high availability.
Serverless Training
Run training jobs on GPUs without the need for infrastructure management.
GPU Virtual Machines
Full root access to customizable GPU instances ready in seconds.
Large-Scale Clusters
Support for configurations from 8 to 8,000 GPUs with InfiniBand connectivity.
OpenAI-Compatible API
Serverless models are served through an OpenAI-compatible endpoint, so existing OpenAI SDK code works by changing the base URL and API key.

Novita AI

OpenAI-Compatible Model API
One endpoint for 200+ text, image, audio and video models, callable with existing OpenAI client libraries
Open-Weight Catalogue
Qwen, DeepSeek, GLM, Kimi, MiniMax, Llama, Gemma and Nemotron families served serverlessly with per-token billing
Prompt Caching
Cache-read pricing published separately from standard input pricing on most chat models
Serverless and Dedicated GPUs
Per-second serverless GPU jobs, on-demand instances, and bare-metal clusters with H100 and H200 hardware
Private Endpoints
Dedicated deployments for workloads that need reserved capacity rather than shared serverless throughput
Agent Sandbox
Isolated runtimes for agent workloads that call models and execute tools, billed per second

Pros & Cons

Lyceum

Advantages

Instant availability of GPUs with minimal provisioning time.
No capacity planning or vendor lock-in required.
Complies with EU data residency requirements.

Considerations

Dedicated endpoint and reserved capacity pricing is agreed per contract rather than published.
Spot GPUs can be reclaimed, and not every GPU type is offered as spot.
Data centres are in Europe only.

Novita AI

Advantages

Broad open-weight model coverage under one API, so several model families can be compared without changing providers
Catalogue endpoint publishes per-model pricing openly, with no account required
Prompt caching rates published alongside standard input rates
Both token-billed inference and GPU rental available from one account

Considerations

Model catalogue turns over quickly, and retired models stay listed with a status flag rather than being removed
A few models use tiered billing where the rate depends on prompt length
Headquarters and data-centre regions are not published on the marketing site

Compute Services

Lyceum

Novita AI

Model APIs

Serverless per-token inference across text, image, audio and video models through an OpenAI-compatible API

GPU Instances

On-demand and serverless GPU compute, plus bare-metal clusters for larger deployments

Pricing Options

Lyceum

Serverless inference

Billed per token for input, cached input and output, with no base fee

Prompt caching

Repeated prompt prefixes still in GPU memory are billed at the cached input rate where listed

On-demand GPUs

Billed per second with no subscription

Spot GPUs

About 45% less than on-demand; capacity can be reclaimed

Reserved GPUs, clusters and dedicated endpoints

Commitment pricing agreed per contract, including multi-year reserved blocks

Novita AI

Getting Started

Lyceum

Get Started

1
Sign Up
Create an account on the Lyceum platform.
2
Choose a Service
Select between inference, training, or virtual machine options.
3
Deploy a Model or Job
Use provided API or CLI instructions to submit your workload.
4
Monitor Usage
Utilize dashboard features to track resource usage and performance.
5
Seek Support if Needed
Contact the sales or support team for assistance.

Novita AI

Get Started

1
Sign up at novita.ai and generate an API key from the dashboard
2
Set the base URL to Novita's OpenAI-compatible endpoint and pass the API key as the bearer token
3
Browse the model library for the model id, then pass it as the model parameter
4
Move to a private endpoint or dedicated GPU instance when shared serverless throughput is not enough

Support & Global Availability

Lyceum

Global Regions

European data centres; serverless models run in Paris and Finland, while dedicated and VM locations are agreed per contract

Support

Email support for all customers; business customers also get a shared Slack channel and agreed response times.

Novita AI

Global Regions

Regional availability is not published on the marketing site.

Support

Documentation site, dashboard guidance, a Discord community, and email support at support@novita.ai.