Pricing

Empower Your AI Journey

Whether you need compute power or inference capabilities, Hyperbolic has you covered. Rent GPUs, share resources, or access state-of-the-art AI models.

GPU Marketplace

Join the collaborative future of AI. Rent or supply GPUs and make a difference.

Rent & Accelerate: Boost Your AI Projects

Access high-performance GPUs at affordable rates and bring your ideas to life.

  1. Flexible usage - pay only for what you use

  2. More affordable than AWS

  3. Grow with the Hyperbolic network

  4. 100% money back guarantee if GPU comes offline

Rent GPUsRent GPUs
GPU Type
Prices Start From (per GPU hour)
H100 SXM
A100 PCIe
RTX 4090

Note: Pricing is refreshed weekly based on the best available rates from suppliers on our platform.

AI Inference

Access powerful inference engines and bring your models to life.

Basic Tier

Perfect for individuals and small teams to get started for free

Pro Tier

Deposit $5 or more into your account to enjoy a higher rate limit, premium support, and access for small teams to get started for free

Enterprise Tier

Private deployments and model optimization at scale. Deposit $5 or more into your account to enjoy a higher rate limit, premium support, and access for small teams to get started for free

Rate Limit60 RPM600 RPMUnlimited
IP Address Limit100/min100/minUnlimited
Access to AI ModelsFull precision (BF16) SOTA open-source modelsFull precision (BF16) SOTA open-source modelsFull precision (BF16) SOTA open-source models + custom models
Pricing ModelPay-as-you-goPay-as-you-goCustom Hourly pricing billed by GPU Type
Dedicated SupportAvailable Upon Request
Dedicated Instances
Fine-tuning Services
Full Control Over Your Data
Get StartedGet Started
Upgrade NowUpgrade Now
Contact UsContact Us

Serverless Endpoints Pricing

Explore our range of AI models tailored for diverse language tasks and applications. From specialized instruction-following models to versatile base models, find the right tool for your AI needs.

Instruct Models
Fine-tuned models designed to follow specific instructions and generate targeted responses.

Qwen2-VL-72B-Instruct

Qwen_Qwen2-VL-72B-Instruct

Qwen2.5-Coder-32B

Qwen_Qwen2.5-Coder-32B-Instruct

Llama-3.2-3B

meta-llama_Llama-3.2-3B-Instruct

Qwen2.5-72B

Qwen_Qwen2.5-72B-Instruct

DeepSeek-V2.5

deepseek-ai_DeepSeek-V2.5

Llama-3-70B

meta-llama_Meta-Llama-3-70B-Instruct

Hermes-3-70B

NousResearch_Hermes-3-Llama-3.1-70B

Llama-3.1-405B

meta-llama_Meta-Llama-3.1-405B-Instruct

Llama-3.1-70B

meta-llama_Meta-Llama-3.1-70B-Instruct

Llama-3.1-8B

meta-llama_Meta-Llama-3.1-8B-Instruct

Note: Pricing is refreshed weekly based on the best available rates from suppliers on our platform.

Base Models

Foundational models that can be adapted for a wide range of language tasks and fine-tuning

Llama 3.1 8B (BF16)

$0.1 per 1M tokens

Llama 3.1 8B (BF16)

$0.1 per 1M tokens

Note: Pricing is refreshed weekly based on the best available rates from suppliers on our platform.

Text-to-Image Pricing Calculator

Enter image dimensions, model type, and steps to estimate the generation cost.

px
px
Estimated Price:$0/Image

Base Rate for SD family and Flux Dev: $0.01 for 1024x1024 pixels with 25 steps.

Base Rate for Flux Pro: $0.05 for 1024x1024 pixels with 50 steps.

Price scales with image size and number of steps

Formula: Base Rate * (width/1024) * (height/1024) * (steps/25)

Pixtral-12B

mistralai_Pixtral-12B-2409

Qwen2-VL-72B-Instruct

Qwen_Qwen2-VL-72B-Instruct

Qwen2-VL-7B-Instruct

Qwen_Qwen2-VL-7B-Instruct

Melo TTS

$5.00 per 1M characters