Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between Novita AI and Verda. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
Average Price Difference: $0.10/hour between comparable GPUs
| GPU Model ↑ | Novita AI Price | Verda Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A100 PCIE 40GB VRAM • Verda | Not Available | — | ||
A100 PCIE 40GB VRAM • | ||||
A100 SXM 80GB VRAM • Verda | Not Available | — | ||
A100 SXM 80GB VRAM • | ||||
B200 180GB VRAM • Verda | Not Available | — | ||
B200 180GB VRAM • | ||||
GB300 576GB VRAM • Verda | Not Available | 2x GPU | — | |
GB300 576GB VRAM • | ||||
H100 SXM 80GB VRAM • Novita AIVerda | 8x GPU | ↑+$0.03(+1.6%) | ||
H100 SXM 80GB VRAM • $1.70/hour Updated: 9/20/2026 $1.67/hour 8x GPU configuration Updated: 9/20/2026 ★Best Price Price Difference:↑+$0.03(+1.6%) | ||||
H200 141GB VRAM • Verda | Not Available | — | ||
H200 141GB VRAM • | ||||
HGX B300 288GB VRAM • Verda | Not Available | 2x GPU | — | |
HGX B300 288GB VRAM • | ||||
L40S 48GB VRAM • Novita AIVerda | ↓$0.18(24.3%) | |||
L40S 48GB VRAM • $0.55/hour Updated: 9/20/2026 ★Best Price $0.73/hour Updated: 9/20/2026 Price Difference:↓$0.18(24.3%) | ||||
RTX 4090 24GB VRAM • Novita AI | Not Available | — | ||
RTX 4090 24GB VRAM • | ||||
RTX 5090 32GB VRAM • Novita AI | Not Available | — | ||
RTX 5090 32GB VRAM • | ||||
RTX 6000 Ada 48GB VRAM • Verda | Not Available | — | ||
RTX 6000 Ada 48GB VRAM • | ||||
RTX A6000 48GB VRAM • Verda | Not Available | — | ||
RTX A6000 48GB VRAM • | ||||
RTX PRO 6000 96GB VRAM • Verda | Not Available | 2x GPU | — | |
RTX PRO 6000 96GB VRAM • | ||||
Tesla V100 32GB VRAM • Verda | Not Available | — | ||
Tesla V100 32GB VRAM • | ||||
A100 PCIE 40GB VRAM • Verda | Not Available | — | ||
A100 PCIE 40GB VRAM • | ||||
A100 SXM 80GB VRAM • Verda | Not Available | — | ||
A100 SXM 80GB VRAM • | ||||
B200 180GB VRAM • Verda | Not Available | — | ||
B200 180GB VRAM • | ||||
GB300 576GB VRAM • Verda | Not Available | 2x GPU | — | |
GB300 576GB VRAM • | ||||
H100 SXM 80GB VRAM • Novita AIVerda | 8x GPU | ↑+$0.03(+1.6%) | ||
H100 SXM 80GB VRAM • $1.70/hour Updated: 9/20/2026 $1.67/hour 8x GPU configuration Updated: 9/20/2026 ★Best Price Price Difference:↑+$0.03(+1.6%) | ||||
H200 141GB VRAM • Verda | Not Available | — | ||
H200 141GB VRAM • | ||||
HGX B300 288GB VRAM • Verda | Not Available | 2x GPU | — | |
HGX B300 288GB VRAM • | ||||
L40S 48GB VRAM • Novita AIVerda | ↓$0.18(24.3%) | |||
L40S 48GB VRAM • $0.55/hour Updated: 9/20/2026 ★Best Price $0.73/hour Updated: 9/20/2026 Price Difference:↓$0.18(24.3%) | ||||
RTX 4090 24GB VRAM • Novita AI | Not Available | — | ||
RTX 4090 24GB VRAM • | ||||
RTX 5090 32GB VRAM • Novita AI | Not Available | — | ||
RTX 5090 32GB VRAM • | ||||
RTX 6000 Ada 48GB VRAM • Verda | Not Available | — | ||
RTX 6000 Ada 48GB VRAM • | ||||
RTX A6000 48GB VRAM • Verda | Not Available | — | ||
RTX A6000 48GB VRAM • | ||||
RTX PRO 6000 96GB VRAM • Verda | Not Available | 2x GPU | — | |
RTX PRO 6000 96GB VRAM • | ||||
Tesla V100 32GB VRAM • Verda | Not Available | — | ||
Tesla V100 32GB VRAM • | ||||
| Model ↑ | Novita AI | Verda | Input Diff ↕ |
|---|---|---|---|
DeepSeek | $0.700 in $2.50 out | Not available | — |
DeepSeek | $0.060 in $0.090 out | Not available | — |
DeepSeek | $0.800 in $0.800 out | Not available | — |
DeepSeek | $0.270 in $1.00 out | Not available | — |
DeepSeek | $0.270 in $1.00 out | Not available | — |
DeepSeek | $0.270 in $0.410 out | Not available | — |
DeepSeek | $0.140 in $0.280 out | Not available | — |
DeepSeek | $0.440 in $1.32 out | Not available | — |
DeepSeek | $1.60 in $3.20 out | Not available | — |
DeepSeek | $0.300 in $1.20 out | Not available | — |
Baidu | $0.070 in $0.280 out | Not available | — |
Baidu | $0.420 in $1.25 out | Not available | — |
Google | $0.050 in $0.100 out | Not available | — |
Google | $0.119 in $0.200 out | Not available | — |
Google | $0.130 in $0.400 out | Not available | — |
Explore how these providers compare to other popular GPU cloud services
Compare Novita AI with another leading provider
Compare Novita AI with another leading provider
Compare Novita AI with another leading provider
Compare Novita AI with another leading provider
Compare Novita AI with another leading provider
Compare Novita AI with another leading provider
One endpoint for 200+ text, image, audio and video models, callable with existing OpenAI client libraries
Qwen, DeepSeek, GLM, Kimi, MiniMax, Llama, Gemma and Nemotron families served serverlessly with per-token billing
Cache-read pricing published separately from standard input pricing on most chat models
Per-second serverless GPU jobs, on-demand instances, and bare-metal clusters with H100 and H200 hardware
Dedicated deployments for workloads that need reserved capacity rather than shared serverless throughput
Isolated runtimes for agent workloads that call models and execute tools, billed per second
Complete platform for AI development from experimentation to production deployment
InfiniBand and NVLink for efficient multi-GPU communication and clustering
ISO 27001/27017/27018/27701 certified with GDPR compliance and EU sovereignty
100% renewable energy-powered Nordic data centers
Web console, API, SDK, Verda CLI, Terraform and OpenTofu providers, and comprehensive documentation
Internal research team contributing to open inference projects such as SGLang and vLLM and co-researching with customers
Serverless per-token inference across text, image, audio and video models through an OpenAI-compatible API
On-demand and serverless GPU compute, plus bare-metal clusters for larger deployments
On-demand virtual machines with 1x-8x NVIDIA GPUs and NVLink interconnects
Self-service access to 16x-128x GPU clusters with InfiniBand
Custom-built GPU clusters tailored to specifications
Transparent hourly pricing with no upfront commitments
Access spare capacity at significant discounts for flexible workloads
Volume discounts up to 25% with 1-2 year commitments
Sign up at novita.ai and generate an API key from the dashboard
Set the base URL to Novita's OpenAI-compatible endpoint and pass the API key as the bearer token
Browse the model library for the model id, then pass it as the model parameter
Move to a private endpoint or dedicated GPU instance when shared serverless throughput is not enough
Create account at console.verda.com with email or GitHub
Add credit card for pay-as-you-go billing
Select GPU model and configuration, deploy in minutes
SSH access, JupyterLab, or API integration for your ML workloads
Regional availability is not published on the marketing site.
Documentation site, dashboard guidance, and email support at support@novita.ai.
European data centers with focus on Nordic locations for optimal sustainability
Expert AI/ML infrastructure support team, comprehensive documentation, 99.9%+ uptime SLA