GPU Pricing
GPU Cloud Pricing
Simple pricing plans for teams of all sizes,
designed to scale with you.
Pods
Thousands of GPUs across 30+ regions. Simple pricing plans for teams of all sizes,
designed to scale with you.
designed to scale with you.
GPU
32GB VRAM
Serverless
Cost effective for every inference
workload. Save 25% over other Serverless
cloud providers on flex workers alone.
workload. Save 25% over other Serverless
cloud providers on flex workers alone.
GPU
Flex
Workers that scale up during traffic spikes and return to idle after completing jobs. Cost-efficient and ideal for bursty workloads.
Active
Always-on workers that eliminate cold starts. Billed continuously but come with up to 30% discount.
8.64
/s
6.84
/s
180GB
B200
Maximum throughput for big models.
5.58
/s
4.46
/s
141GB
H200
Extreme throughput for big models.
4.18
/s
3.35
/s
80GB
H100
PRO
Extreme throughput for big models.
2.72
/s
2.17
/s
80GB
A100
High throughput GPU, yet still very cost-effective.
3.996
/s
31.284
/s
96GB
RTX 6000 Pro
PRO
High throughput for large model inference workloads.
1.9
/s
1.33
/s
48GB
L40, L40S, 6000 Ada
PRO
Extreme inference throughput on LLMs like Llama 3 7B.
1.22
/s
0.85
/s
48GB
A6000, A40
A cost-effective option for running big models.
1.58
/s
1.11
/s
32GB
5090
PRO
Extreme throughput for small-to-medium models.
1.1
/s
0.77
/s
24GB
4090
PRO
Extreme throughput for small-to-medium models.
0.69
/s
0.48
/s
24GB
L4, A5000, 3090
Great for small-to-medium sized inference workloads.
0.58
/s
0.4
/s
16GB
A4000, A4500, RTX 4000, RTX 2000
The most cost-effective for small models.
Instant Clusters
Launch multi-GPU clusters in minutes with no commitments—scale up to 64 GPUs, attach shared storage, and pay only for what you use.
GPU
Per second
Per hour
H200 SXM
A100 SXM
H100 SXM
L40S
B200
Reserved Clusters
Dedicated GPU clusters with guaranteed availability, custom configurations, SLA-backed uptime, and discounted rates for enterprises scaling to 10,000+ GPUs.
GPU
1mo
3mo
6mo
12mo
12mo+
Storage
Flexible and persisitent storage options starting at $0.05/GB/mo with standard and high-performance tiers.
Storage Type
Container Disk
$0.10/GB/mo
Volume Disk
Idle - $0.20/GB/mo
Network Storage (Standard)
Under 1TB - $0.07/GB/mo
Over 1TB - $0.05/GB/mo
Network Storage (High-Performance)
$0.14/GB/mo
Public Endpoints
Instant access to pre-deployed AI models via API—no infrastructure setup required.
Model Name
Audio
Pruna / Whisper V3 Large
$0.05 per 1000 characters
resembleai / Chatterbox Turbo
$0.00 per 1000 characters.
minimax / Minimax Speech 02 HD
$0.05 per 1000 characters
minimax / Minimax Speech 02 HD
$0.05 per 1000 characters
Image
bytedance / Seedream 4.0 Edit
$0.0270 per request
bytedance / Seedream 4.0 T2I
$0.0270 per request
google / Nano Banana Edit
$0.0380 per request
google / Nano Banana Pro Edit
$0.14 per request
pruna / Pruna Image T2I
$0.0050 per request
pruna / Pruna Image Edit
$0.01 per request
alibaba / WAN 2.6 T2I
$0.03 per request
qwen / Qwen Image Edit 2511
$0.02 per request
qwen / Qwen Image Edit 2511 LoRA
$0.025 per request
Tongyi-MAI / Z Image Turbo
$0.0050 per request.
Language
deep-cogito / Deep Cogito v2 Llama 70B
$0.00001 per 1m tokens
qwen / Qwen3 32B AWQ
$10.00 per 1m tokens
minimax / Minimax Speech 02 HD
$0.05 per 1000 characters
minimax / Minimax Speech 02 HD
$0.05 per 1000 characters
ibm / IBM Granite 4.0 H Small
$1.00 per 1m tokens
Video
Bytedance / Seedance 1.0 pro
5s: $0.12(480p) per request
Alibaba / Wan 2.2 I2V 720p
5s: $0.30 per request
Alibaba / Wan 2.2 T2V 720p
5s: $0.30 per request
Alibaba / Wan 2.1 I2V 720p
$0.30 per request
Alibaba / Wan 2.1 T2V 720p
$0.30 per request
kwaivgi / Kling v2.6 Standard Motion Control
1-3s $0.21 per request
Alibaba / WAN 2.6 T2V
5s: $0.50 per request
bytedance / Seedance V1.5 Pro I2V
$0.024 per second
kwaivgi / Kling Video O1 R2V
$0.112 per second
Alibaba / Wan 2.6 I2V
5s: $0.50 per request
Gain additional savings with reservations.
Save more with long-term commitments. Speak with our team to reserve discounted active and flex workers.
.svg)