Skip to main content

Simple, Transparent Pricing

Pay only for what you use. No monthly commitments.

Dedicated GPU

From $0.53/hr

Your own GPU, billed per 10 min

Serverless

From $0.008/req

No idle costs, pay per execution

Dedicated GPU Instances

Full GPU reserved for your workload. Billed per 10-minute increment. Stop anytime.

CPU Only

$0.15/hour
VRAM
vCPU3
RAM16 GB

Small LLMs (1B-3B), basic inference, API servers, testing

RTX 4090

$0.79/hour
VRAM24 GB
vCPU6
RAM41 GB

7B-13B LLMs, SDXL Images, Flux, Most Popular GPU

L4

$0.53/hour
VRAM24 GB
vCPU12
RAM50 GB

7B-13B LLMs, SDXL Images, Power Efficient

RTX A6000

$0.66/hour
VRAM48 GB
vCPU9
RAM50 GB

30B+ LLMs (quantized 70B), Video Gen, 48GB VRAM

A100 80GB

$1.85/hour
VRAM80 GB
vCPU8
RAM117 GB

70B+ LLMs, Complex Workflows, Fine-tuning

H100

$3.54/hour
VRAM80 GB
vCPU16
RAM188 GB

Lowest Latency Production, Training, Research

All prices include compute, memory, disk, and network.

Serverless — Pay Per Request

No idle costs. Your model scales to zero when not in use.

Text Models

ModelPer Request
Qwen3 4BQuick Response$0.010
Qwen3 8BGeneral Purpose$0.015
DeepSeek R1 8BReasoning$0.015
GLM-Z1 9BBilingual Reasoning$0.015
DeepSeek R1 14BAdvanced Reasoning$0.030
Qwen3 32BPremium Quality$0.050
GLM-Z1 32BPremium Reasoning$0.050

Image Models

ModelPer Request
Flux Schnell$0.010
Flux Dev$0.015
Stable Diffusion XL$0.008
Z-Image Turbo$0.008
Video ModelsComing Soon
Audio ModelsComing Soon

100 free serverless executions with every new account.

Estimate Your Costs

Hours per day4h
1h24h
Days per week5d
1d7d

Daily

$2.12

Monthly

$46

Get Started Free

$1.00 Free Credits

Use code WELCOME2026

50% Bonus on First Purchase

Up to $3 extra credits, applied automatically

100 Free Serverless Requests

Included with every new account

Frequently Asked Questions

How does billing work?
Dedicated GPUs are billed per 10-minute increment — you only pay while your instance is running. Serverless is billed per request with no idle costs. No monthly minimums for either.
Do I need a credit card to start?
No. Use promo code WELCOME2026 to get $1.00 in free credits, and every new account gets 100 free serverless executions.
What if I forget to stop my GPU instance?
Your instance auto-stops when your credit balance reaches $0. You will never be charged beyond your prepaid balance.
Can I use both dedicated GPU and serverless?
Yes. Many teams use serverless for development and burst traffic, then switch to dedicated GPUs for sustained production workloads.
What's included in the GPU price?
Everything: GPU, vCPU, RAM, disk, and network. No hidden fees, no egress charges, no surprise bills.
Which mode should I choose?
Use serverless for low-volume, bursty, or development workloads (pay only when you generate). Use dedicated GPU for sustained production traffic where you need consistent latency and throughput.

Ready to deploy?Start building with AI models today.