Loading Comparison
Fetching pricing data and provider information...
Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between Modal and Sesterce. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
Average Price Difference: $1.83/hour between comparable GPUs
| GPU Model ↑ | Modal Price | Sesterce Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A10 24GB VRAM • ModalSesterce | ↓$1.41(99.2%) | |||
A10 24GB VRAM • $0.01/hour Updated: 6/22/2026 ★Best Price $1.42/hour Updated: 6/26/2026 Price Difference:↓$1.41(99.2%) | ||||
A100 SXM 80GB VRAM • ModalSesterce | ↓$1.48(98.6%) | |||
A100 SXM 80GB VRAM • $0.02/hour Updated: 6/22/2026 ★Best Price $1.50/hour Updated: 6/26/2026 Price Difference:↓$1.48(98.6%) | ||||
A16 64GB VRAM • Sesterce | Not Available | — | ||
A16 64GB VRAM • | ||||
A30 24GB VRAM • Sesterce | Not Available | — | ||
A30 24GB VRAM • | ||||
A40 48GB VRAM • Sesterce | Not Available | — | ||
A40 48GB VRAM • | ||||
B200 192GB VRAM • ModalSesterce | 8x GPU | ↓$4.01(97.5%) | ||
B200 192GB VRAM • $0.10/hour Updated: 6/22/2026 ★Best Price $4.11/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$4.01(97.5%) | ||||
Gaudi 2 96GB VRAM • Sesterce | Not Available | 8x GPU | — | |
Gaudi 2 96GB VRAM • | ||||
GH200 96GB VRAM • Sesterce | Not Available | — | ||
GH200 96GB VRAM • | ||||
H100 NVL 94GB VRAM • Sesterce | Not Available | 2x GPU | — | |
H100 NVL 94GB VRAM • | ||||
H100 SXM 80GB VRAM • ModalSesterce | ↓$1.76(96.4%) | |||
H100 SXM 80GB VRAM • $0.07/hour Updated: 6/22/2026 ★Best Price $1.83/hour Updated: 6/26/2026 Price Difference:↓$1.76(96.4%) | ||||
H200 141GB VRAM • ModalSesterce | 8x GPU | ↓$2.40(96.9%) | ||
H200 141GB VRAM • $0.08/hour Updated: 6/22/2026 ★Best Price $2.48/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$2.40(96.9%) | ||||
HGX B300 288GB VRAM • Sesterce | Not Available | 8x GPU | — | |
HGX B300 288GB VRAM • | ||||
L4 24GB VRAM • Sesterce | Not Available | — | ||
L4 24GB VRAM • | ||||
L40 40GB VRAM • Sesterce | Not Available | — | ||
L40 40GB VRAM • | ||||
L40S 48GB VRAM • ModalSesterce | 8x GPU | ↓$0.74(97.6%) | ||
L40S 48GB VRAM • $0.02/hour Updated: 6/22/2026 ★Best Price $0.76/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$0.74(97.6%) | ||||
A10 24GB VRAM • ModalSesterce | ↓$1.41(99.2%) | |||
A10 24GB VRAM • $0.01/hour Updated: 6/22/2026 ★Best Price $1.42/hour Updated: 6/26/2026 Price Difference:↓$1.41(99.2%) | ||||
A100 SXM 80GB VRAM • ModalSesterce | ↓$1.48(98.6%) | |||
A100 SXM 80GB VRAM • $0.02/hour Updated: 6/22/2026 ★Best Price $1.50/hour Updated: 6/26/2026 Price Difference:↓$1.48(98.6%) | ||||
A16 64GB VRAM • Sesterce | Not Available | — | ||
A16 64GB VRAM • | ||||
A30 24GB VRAM • Sesterce | Not Available | — | ||
A30 24GB VRAM • | ||||
A40 48GB VRAM • Sesterce | Not Available | — | ||
A40 48GB VRAM • | ||||
B200 192GB VRAM • ModalSesterce | 8x GPU | ↓$4.01(97.5%) | ||
B200 192GB VRAM • $0.10/hour Updated: 6/22/2026 ★Best Price $4.11/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$4.01(97.5%) | ||||
Gaudi 2 96GB VRAM • Sesterce | Not Available | 8x GPU | — | |
Gaudi 2 96GB VRAM • | ||||
GH200 96GB VRAM • Sesterce | Not Available | — | ||
GH200 96GB VRAM • | ||||
H100 NVL 94GB VRAM • Sesterce | Not Available | 2x GPU | — | |
H100 NVL 94GB VRAM • | ||||
H100 SXM 80GB VRAM • ModalSesterce | ↓$1.76(96.4%) | |||
H100 SXM 80GB VRAM • $0.07/hour Updated: 6/22/2026 ★Best Price $1.83/hour Updated: 6/26/2026 Price Difference:↓$1.76(96.4%) | ||||
H200 141GB VRAM • ModalSesterce | 8x GPU | ↓$2.40(96.9%) | ||
H200 141GB VRAM • $0.08/hour Updated: 6/22/2026 ★Best Price $2.48/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$2.40(96.9%) | ||||
HGX B300 288GB VRAM • Sesterce | Not Available | 8x GPU | — | |
HGX B300 288GB VRAM • | ||||
L4 24GB VRAM • Sesterce | Not Available | — | ||
L4 24GB VRAM • | ||||
L40 40GB VRAM • Sesterce | Not Available | — | ||
L40 40GB VRAM • | ||||
L40S 48GB VRAM • ModalSesterce | 8x GPU | ↓$0.74(97.6%) | ||
L40S 48GB VRAM • $0.02/hour Updated: 6/22/2026 ★Best Price $0.76/hour 8x GPU configuration Updated: 6/26/2026 Price Difference:↓$0.74(97.6%) | ||||
Explore how these providers compare to other popular GPU cloud services
Compare Modal with another leading provider
Compare Modal with another leading provider
Compare Modal with another leading provider
Compare Modal with another leading provider
Compare Modal with another leading provider
Compare Modal with another leading provider
Run Python functions on NVIDIA GPUs without provisioning instances; cold starts in seconds
Pay for actual GPU runtime at sub-minute granularity, with scale-to-zero by default
Define environments in code, with automatic image building and caching
From T4 and L4 through A100, L40S, H100, H200 and B200
Datacenters powered by renewable energy across Europe, reducing environmental impact of AI systems
Choose from VM, container, or bare-metal deployment options based on your workload requirements
Bare metal dedicated cluster solutions available within 2 hours with HPC job management
Full-stack AI platform covering training, inference, and data preparation workflows
Virtualized GPU instances with flexible configurations and secure SSH access
Dedicated GPU clusters for maximum performance and control
Charged per second of GPU runtime, with scale-to-zero when idle
Monthly free credits for experimentation and personal projects
Volume commitments and enterprise support for production deployments
Flexible pricing starting at $0.30 per hour with payment based solely on usage
Pre-funded account balance system for streamlined resource management
Run `pip install modal` and authenticate via the CLI
Decorate a Python function with the desired GPU and image specification
Invoke locally or deploy as a long-lived endpoint or scheduled job
Sign up for Sesterce Cloud platform access
Fund your account with credits for pay-as-you-go billing
Choose your GPU type and configuration, launch in just a few clicks
Multi-region availability across North America and Europe
Documentation, community forum, and enterprise support for paid plans
Multiple regions across Europe with focus on renewable energy datacenters
Documentation available, self-service console, REST API