Loading Comparison
Fetching pricing data and provider information...
Compare GPU and LLM inference API pricing between Deep Infra and Paperspace. Find the best rates for AI training, inference, and ML workloads.
Provider 1
Provider 2
Average Price Difference: $3.02/hour between comparable GPUs
| GPU Model ↑ | Deep Infra Price | Paperspace Price | Price Diff ↕ | Sources |
|---|---|---|---|---|
A100 SXM 80GB VRAM • Deep InfraPaperspace | ↓$2.29(72.0%) | |||
A100 SXM 80GB VRAM • $0.89/hour Updated: 9/17/2026 ★Best Price $3.18/hour Updated: 9/17/2026 Price Difference:↓$2.29(72.0%) | ||||
B200 180GB VRAM • Deep Infra | Not Available | — | ||
B200 180GB VRAM • | ||||
H100 SXM 80GB VRAM • Deep InfraPaperspace | ↓$3.75(63.0%) | |||
H100 SXM 80GB VRAM • $2.20/hour Updated: 9/17/2026 ★Best Price $5.95/hour Updated: 9/17/2026 Price Difference:↓$3.75(63.0%) | ||||
H200 141GB VRAM • Deep Infra | Not Available | — | ||
H200 141GB VRAM • | ||||
HGX B300 288GB VRAM • Deep Infra | Not Available | — | ||
HGX B300 288GB VRAM • | ||||
Quadro P4000 8GB VRAM • Paperspace | Not Available | — | ||
Quadro P4000 8GB VRAM • | ||||
Quadro P5000 16GB VRAM • Paperspace | Not Available | — | ||
Quadro P5000 16GB VRAM • | ||||
Quadro RTX 4000 8GB VRAM • Paperspace | Not Available | — | ||
Quadro RTX 4000 8GB VRAM • | ||||
Quadro RTX 5000 16GB VRAM • Paperspace | Not Available | — | ||
Quadro RTX 5000 16GB VRAM • | ||||
RTX A4000 16GB VRAM • Paperspace | Not Available | — | ||
RTX A4000 16GB VRAM • | ||||
RTX A5000 24GB VRAM • Paperspace | Not Available | — | ||
RTX A5000 24GB VRAM • | ||||
RTX A6000 48GB VRAM • Paperspace | Not Available | 8x GPU | — | |
RTX A6000 48GB VRAM • | ||||
Tesla V100 32GB VRAM • Paperspace | Not Available | 8x GPU | — | |
Tesla V100 32GB VRAM • | ||||
A100 SXM 80GB VRAM • Deep InfraPaperspace | ↓$2.29(72.0%) | |||
A100 SXM 80GB VRAM • $0.89/hour Updated: 9/17/2026 ★Best Price $3.18/hour Updated: 9/17/2026 Price Difference:↓$2.29(72.0%) | ||||
B200 180GB VRAM • Deep Infra | Not Available | — | ||
B200 180GB VRAM • | ||||
H100 SXM 80GB VRAM • Deep InfraPaperspace | ↓$3.75(63.0%) | |||
H100 SXM 80GB VRAM • $2.20/hour Updated: 9/17/2026 ★Best Price $5.95/hour Updated: 9/17/2026 Price Difference:↓$3.75(63.0%) | ||||
H200 141GB VRAM • Deep Infra | Not Available | — | ||
H200 141GB VRAM • | ||||
HGX B300 288GB VRAM • Deep Infra | Not Available | — | ||
HGX B300 288GB VRAM • | ||||
Quadro P4000 8GB VRAM • Paperspace | Not Available | — | ||
Quadro P4000 8GB VRAM • | ||||
Quadro P5000 16GB VRAM • Paperspace | Not Available | — | ||
Quadro P5000 16GB VRAM • | ||||
Quadro RTX 4000 8GB VRAM • Paperspace | Not Available | — | ||
Quadro RTX 4000 8GB VRAM • | ||||
Quadro RTX 5000 16GB VRAM • Paperspace | Not Available | — | ||
Quadro RTX 5000 16GB VRAM • | ||||
RTX A4000 16GB VRAM • Paperspace | Not Available | — | ||
RTX A4000 16GB VRAM • | ||||
RTX A5000 24GB VRAM • Paperspace | Not Available | — | ||
RTX A5000 24GB VRAM • | ||||
RTX A6000 48GB VRAM • Paperspace | Not Available | 8x GPU | — | |
RTX A6000 48GB VRAM • | ||||
Tesla V100 32GB VRAM • Paperspace | Not Available | 8x GPU | — | |
Tesla V100 32GB VRAM • | ||||
| Model ↑ | Deep Infra | Paperspace | Input Diff ↕ |
|---|---|---|---|
Anthropic | $10.00 in $50.00 out | Not available | — |
Anthropic | $1.00 in $5.00 out | Not available | — |
Anthropic | $5.00 in $25.00 out | Not available | — |
Anthropic | $5.00 in $25.00 out | Not available | — |
Anthropic | $5.00 in $25.00 out | Not available | — |
Anthropic | $3.00 in $15.00 out | Not available | — |
Anthropic | $3.00 in $15.00 out | Not available | — |
DeepSeek | $0.500 in $2.15 out | Not available | — |
DeepSeek | $0.320 in $0.890 out | Not available | — |
DeepSeek | $0.250 in $0.950 out | Not available | — |
DeepSeek | $0.260 in $0.380 out | Not available | — |
DeepSeek | $0.060 in $0.180 out | Not available | — |
DeepSeek | $0.440 in $1.32 out | Not available | — |
DeepSeek | $1.30 in $2.60 out | Not available | — |
DeepSeek | $0.200 in $0.600 out | Not available | — |
Explore how these providers compare to other popular GPU cloud services
Compare Deep Infra with another leading provider
Compare Deep Infra with another leading provider
Compare Deep Infra with another leading provider
Compare Deep Infra with another leading provider
Compare Deep Infra with another leading provider
Compare Deep Infra with another leading provider
OpenAI-compatible API for 100+ models including DeepSeek, Qwen, Llama 4, Claude, and Gemini families with autoscaling
B200 instances with SSH access spin up in about 10 seconds and bill hourly
Deploy your own Hugging Face models onto dedicated A100, H100, H200, B200, or B300 GPUs
Published per-GPU hourly rates for A100, H100, H200, B200, and B300 with competitive pricing
Runs on its own inference-optimized hardware in US-based data centers rather than rented capacity
Support for text generation, vision and OCR, embeddings and reranking, image, video and music generation, and speech recognition and synthesis
Interactive Jupyter notebooks with a free tier, pre-configured templates, and access to powerful GPUs.
Serve machine learning models as scalable API endpoints.
High-performance virtual machines with a wide variety of NVIDIA GPUs for demanding workloads.
Features for teams to collaborate on projects, including shared drives and SSO.
Offers persistent storage that can be shared across different machines and notebooks.
Programmatic access to the Paperspace platform to automate workflows.
Hosted model APIs with autoscaling on Deep Infra's own inference infrastructure.
On-demand GPU nodes with SSH access for custom workloads.
Multi-node B200 and B300 clusters with SSH access for training and full-control workloads.
Virtual machines with a wide range of NVIDIA GPUs for various workloads.
Managed Jupyter notebooks for interactive development and experimentation.
A serverless product for deploying trained models as REST APIs.
OpenAI-compatible inference APIs billed per input and output token, with no idle GPU time or minimums
Published transparent hourly pricing for A100, H100, H200, B200, and B300 GPUs with pay-as-you-go billing
Non-LLM models are billed for inference execution time rather than per token
Prompt-cached input tokens are billed at a lower rate than uncached input tokens
Flexible hourly billing for dedicated instances with no prepayments, contracts, or minimums required
Sign up (GitHub-supported) and open the Deep Infra dashboard
Add a payment method to unlock GPU rentals and API usage
Choose serverless APIs or dedicated A100, H100, H200, B200, or B300 instances
Start instances with SSH access or call the OpenAI-compatible API endpoints
Track spend and instance status from the dashboard and shut down when idle
Sign up for a Paperspace account. You can start with a free plan.
Select the product that best fits your needs, such as Gradient Notebooks for interactive development or Core Machines for more control.
Choose a pre-configured template for your desired framework and select a GPU or CPU instance.
Launch your machine or notebook and begin building, training, or deploying your AI applications.
Runs on self-operated, inference-optimized infrastructure in US-based data centers; no international region list is published.
Documentation site, dashboard guidance, Discord community, feedback email (feedback@deepinfra.com), and contact-sales options.
Data centers are located in the US (Secaucus, NJ and Santa Clara, CA) and Europe (Amsterdam, NL).
Support is available through a community forum, extensive documentation, and a support ticket system.