News icon

Batch Inference is now generally available on Runpod Serverless

Rent NVIDIA RTX PRO 4000 GPUs from $0.57/hr

Blackwell workstation GPU with 24 GB of ECC GDDR7 on a 192-bit bus, 8,960 CUDA cores and 672 GB/s of memory bandwidth.

On-demand GPU pricing

GPU
VRAM
Secure Cloud $/hr
Community Cloud $/hr
Availability
RTX PRO 4000
24 GB VRAM
0.57
Varies by region

On-demand, per GPU hour. Rates mirror the Runpod catalog.

Deploy this GPU in the Runpod console

Powering the next generation of AI & high-performance computing.

Engineered for large-scale AI training, deep learning, and high-performance workloads, delivering unprecedented compute power and efficiency.

NVIDIA Blackwell architecture

Fifth-generation Tensor Cores and a second-generation Transformer Engine, including FP4 for quantized serving.

24 GB GDDR7 with ECC

24 GB on a 192-bit interface with ECC, enough for an 8B model at FP16 or a quantized model in the 30B class.

Low power draw

A 140 to 145 W board, which is a fraction of what the datacenter cards draw for workloads that fit in 24 GB.

PCIe Gen5 host interface

PCIe Gen5 to the host, useful when loading large images or streaming data rather than keeping it all in VRAM.

Why rent the RTX PRO 4000 instead of buying?

Blackwell features at a 24 GB price

FP4 and fifth-generation Tensor Cores on a card priced below the 32 GB and 48 GB tiers.

Pay only for what you use

Runpod bills Pods per second with no minimum, so short inference runs cost only the seconds they take.

Deploy in seconds

Provision from the console in under 30 seconds, run any standard Docker image, and terminate when the job finishes.

Key specs at a glance.

Performance benchmarks that push AI, ML, and HPC workloads further.

Memory Bandwidth

672

GB/s

CUDA Cores

8960

cores

Memory Interface

192

bit

Popular use cases.

Designed for demanding workloads. Learn if this GPU fits your needs.

Inference workload illustration

Inference

Serve inference for image, text, and audio generation at any scale.

Fine-tuning workload illustration

Fine-tuning

Train custom models on your specific datasets.

AI agents workload illustration

Agents

Build intelligent agent-based systems and workflows.

Compute-heavy workload illustration

Compute-heavy tasks

Run compute-heavy workloads like rendering and simulations.

Ready for your most demanding workloads.

Essential technical specifications to help you choose the right GPU for your workload.

Specification
Details
Great for...
Memory Bandwidth
672 GB/s
Keeping 24 GB of weights and activations fed during decode, which is where most single-card inference is limited.
CUDA Cores
8960 cores
Mixed-precision inference and light fine-tuning of models that fit inside 24 GB.
Memory Interface
192 bit
Sustaining 672 GB/s to 24 GB of GDDR7, which is what sets decode speed on models that fit on one card.
"The Runpod team has clearly prioritized the developer experience to create an elegant solution that enables individuals to rapidly develop custom AI apps or integrations while also paving the way for organizations to truly deliver on the promise of AI."

Amjad Masad

"Runpod is the only place I can deploy high-end GPU models instantly. No sales calls, no rate limits, no nonsense."

Daniel Chang

“The main value proposition for us was the flexibility Runpod offered. We were able to scale up effortlessly to meet the demand at launch.”

Josh Payne

“Runpod helped us scale the part of our platform that drives creation. That’s what fuels the rest. Image generation, sharing, remixing. It starts with training.”

Matty Shimura

Powerful GPUs. Globally available. Reliability you can trust.

30+ GPUs, 31 regions, instant scale. Fine-tune or go full Skynet. We’ve got you.

Community Cloud
$/hr
Secure Cloud
$0.57/hr
Unique GPU Models
Community Cloud
25
Secure Cloud
19
Global Regions
Community Cloud
17
Secure Cloud
14
Network Storage
Community Cloud
Secure Cloud
Enterprise-Grade Reliability
Community Cloud
Secure Cloud
Savings Plans
Community Cloud
Secure Cloud
24/7 Support
Community Cloud
Secure Cloud
Delightful Dev Experience
Community Cloud
Secure Cloud

12,380,000,000

Requests since launch & 1M+ developers worldwide

Build what’s next.

Build, train, and scale AI workloads on Runpod with cloud GPUs, Serverless, and Clusters.

Star field background