Loading Comparison
Fetching pricing data and provider information...
Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between Amazon AWS and Vast.ai. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
| GPU Model ↑ | Amazon AWS Price | Vast.ai Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A10 24GB VRAM • Amazon AWS | Not Available | — | ||
A10 24GB VRAM • | ||||
A100 SXM 80GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
A100 SXM 80GB VRAM • $2.74/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
H100 SXM 80GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
H100 SXM 80GB VRAM • $6.88/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
H200 141GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
H200 141GB VRAM • $7.91/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
L4 24GB VRAM • Amazon AWS | Not Available | — | ||
L4 24GB VRAM • | ||||
L40S 48GB VRAM • Amazon AWS | Not Available | — | ||
L40S 48GB VRAM • | ||||
Quadro P4000 8GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
Quadro P4000 8GB VRAM • | ||||
Quadro RTX 6000 24GB VRAM • Vast.ai | Not Available | — | ||
Quadro RTX 6000 24GB VRAM • | ||||
RTX 3070 8GB VRAM • Vast.ai | Not Available | — | ||
RTX 3070 8GB VRAM • | ||||
RTX 3070 Ti 8GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
RTX 3070 Ti 8GB VRAM • | ||||
RTX 3080 10GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
RTX 3080 10GB VRAM • | ||||
RTX 3080 Ti 12GB VRAM • Vast.ai | Not Available | — | ||
RTX 3080 Ti 12GB VRAM • | ||||
RTX 3090 24GB VRAM • Vast.ai | Not Available | — | ||
RTX 3090 24GB VRAM • | ||||
RTX 3090 Ti 24GB VRAM • Vast.ai | Not Available | — | ||
RTX 3090 Ti 24GB VRAM • | ||||
RTX 4000 Ada 20GB VRAM • Vast.ai | Not Available | — | ||
RTX 4000 Ada 20GB VRAM • | ||||
A10 24GB VRAM • Amazon AWS | Not Available | — | ||
A10 24GB VRAM • | ||||
A100 SXM 80GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
A100 SXM 80GB VRAM • $2.74/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
H100 SXM 80GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
H100 SXM 80GB VRAM • $6.88/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
H200 141GB VRAM • Amazon AWS | 8x GPU | Not Available | — | |
H200 141GB VRAM • $7.91/hour 8x GPU configuration Updated: 8/31/2026 ★Best Price Not Available | ||||
L4 24GB VRAM • Amazon AWS | Not Available | — | ||
L4 24GB VRAM • | ||||
L40S 48GB VRAM • Amazon AWS | Not Available | — | ||
L40S 48GB VRAM • | ||||
Quadro P4000 8GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
Quadro P4000 8GB VRAM • | ||||
Quadro RTX 6000 24GB VRAM • Vast.ai | Not Available | — | ||
Quadro RTX 6000 24GB VRAM • | ||||
RTX 3070 8GB VRAM • Vast.ai | Not Available | — | ||
RTX 3070 8GB VRAM • | ||||
RTX 3070 Ti 8GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
RTX 3070 Ti 8GB VRAM • | ||||
RTX 3080 10GB VRAM • Vast.ai | Not Available | 2x GPU | — | |
RTX 3080 10GB VRAM • | ||||
RTX 3080 Ti 12GB VRAM • Vast.ai | Not Available | — | ||
RTX 3080 Ti 12GB VRAM • | ||||
RTX 3090 24GB VRAM • Vast.ai | Not Available | — | ||
RTX 3090 24GB VRAM • | ||||
RTX 3090 Ti 24GB VRAM • Vast.ai | Not Available | — | ||
RTX 3090 Ti 24GB VRAM • | ||||
RTX 4000 Ada 20GB VRAM • Vast.ai | Not Available | — | ||
RTX 4000 Ada 20GB VRAM • | ||||
| Model ↑ | Amazon AWS | Vast.ai | Input Diff ↕ |
|---|---|---|---|
Anthropic | $0.250 in $1.25 out | Not available | — |
Anthropic | $0.800 in $4.00 out | Not available | — |
Anthropic | $3.00 in $15.00 out | Not available | — |
Anthropic | $3.00 in $15.00 out | Not available | — |
Anthropic | $1.10 in $5.50 out | Not available | — |
Anthropic | $15.00 in $75.00 out | Not available | — |
Anthropic | $5.50 in $27.50 out | Not available | — |
Anthropic | $5.50 in $27.50 out | Not available | — |
Anthropic | $3.30 in $16.50 out | Not available | — |
Google | $0.090 in $0.290 out | Not available | — |
Google | $0.230 in $0.380 out | Not available | — |
Google | $0.040 in $0.080 out | Not available | — |
Zhipu | $0.600 in $2.20 out | Not available | — |
Zhipu | $1.00 in $3.20 out | Not available | — |
OpenAI | $0.150 in $0.600 out | Not available | — |
Explore how these providers compare to other popular GPU cloud services
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Amazon AWS with another leading provider
Compare Vast.ai with another leading provider
Extensive network of data centers across multiple regions worldwide
Flexible pricing model with no upfront commitments required
Comprehensive security tools and compliance certifications
Automatically adjust resources based on demand
Extensive ecosystem of services that work seamlessly together
Comprehensive suite of tools for development, deployment, and management
Prices set by supply and demand across the platform with no list prices or hidden fees
GPU Cloud for full control, Serverless for zero-ops inference, Clusters for large-scale training
CLI, Python SDK, and REST API for programmatic GPU provisioning, installed together via a single package
API-native workflow intended for AI agents to search, procure, and release compute autonomously
Prebuilt templates for popular open-source models, plus custom templates any GPU can run with one click
Scale from $5 to 20,000 GPUs across 40+ data centers without contracts or minimums
Virtual servers in the cloud with a wide range of instance types.
Fully managed container orchestration service.
Managed Kubernetes service for container orchestration.
On-demand instances across 40+ data centers and 20,000+ GPUs
Deploy models as endpoints with autoscaling to zero
Dedicated multi-node GPU clusters with InfiniBand networking
Pay for compute capacity by the second with no long-term commitments.
Use spare EC2 capacity at up to 90% off the On-Demand price.
Save up to 72% compared to On-Demand pricing with a 1 or 3-year commitment.
Save up to 72% on compute usage with a 1 or 3-year commitment to a consistent amount of usage.
Reserve accelerated compute capacity for a future start date and a defined duration; billed as an upfront reservation fee plus an operating system fee.
Guaranteed uptime with per-second billing. Best for production workloads.
50%+ cheaper preemptible instances. Best for fault-tolerant batch training.
Up to 50% off with 1, 3, or 6 month commitments. Guaranteed capacity with volume discounts.
Endpoint rates billed only for compute time, with no charge while workers are scaled to zero.
Create an AWS account to access the cloud platform.
Select from EC2, Lambda, or container services based on your workload needs.
Configure and launch your first compute instance or container.
Configure security groups and access controls for your resources.
Use AWS CloudWatch and Compute Optimizer to monitor performance and reduce costs.
Start with as little as $5 and grab an API key from the console. No contracts, no sales calls.
Filter by model, VRAM, price, and availability via the console or API
Launch instances in seconds. Scale up or down programmatically.
39 geographic regions and 123 availability zones worldwide.
Basic (free), Developer, Business, Enterprise support plans with varying response times and features. Extensive documentation, forums, and training resources.
40+ data centers with global coverage including community and enterprise providers
24/7 support chat in the console, email support at contact@vast.ai, Discord community, and documentation covering the CLI, SDK, and REST API