Serving Options

Deploy your ComfyUI workflows or finetuned models as production grade APIs.

Public

For AI creators who want to publish their work

Free + processing fees

Your product will be accessible on our marketplace and as an API

2 free deployed products (APIs)
Auto-generated interface for your API
Additional products: $7/month
Processing fee: $0.0005/second
Deploy up to 40 Gb of models per product
5% transaction fee on products discovered & used on the Nodehaus marketplace

Private

Host your AI products as private APIs on Nodehaus

$89 /product/month + processing fees

Full control over usage, data, and access permissions

Private API with access control
Auto-generated interface for your API
Includes up to 50,000 processing seconds*
Additional processing: $0.00025/second
Deploy up to 40 Gb of models per product
Priority support

Model Finetuning

Finetune image and text models on your own data. Manage your models and datasets in one place.

Available Models

Models are priced per finetuning job

Flux.1-dev

Image

Next-generation text-to-image model for high-quality, diverse image synthesis

Best for: Photorealistic rendering, artistic creation, concept visualization

LoRa $9

Full

Lumina-Image-2.0

Image

Advanced image generation focusing on photorealism and fine details

Best for: Highly realistic images, texture generation, style transfer

LoRa $9

Full $19

Flex.1-alpha

Image

Versatile text-to-image model adaptable to various artistic styles and concepts

Best for: Creative image generation and visual content creation

LoRa $9

Full $19

Llama-3.1-8B

LLM

Lightweight, efficient language model, now with updated finetuning options

Best for: Content generation, customer support, summarization, RAG

LoRa $14

Full $230

Mistral-7B-v0.1

LLM

High-performance 7B model, excellent for a balance of speed and capability

Best for: Chatbots, summarization, code generation, creative writing

LoRa $14

Full $230

DeepSeek-V2-Lite

LLM

State-of-the-art model with a focus on reasoning, math, and coding

Best for: Advanced code generation and complex problem solving

LoRa $19

Full $260

More coming soon...

Storage

50Gb free models and datasets storage
Additional storage: $0.08/Gb/month

Datasets

Manage your datasets in one place

Frequently Asked Questions

What are processing seconds?

Processing seconds measure the GPU time used to handle requests. Different GPU types have different performance characteristics, which will affect the processing time. This is different from 'starting' time, which is the time a request spends in the queue before being processed. You will not be charged for 'starting' time.

I want to finetune on a model that is not available on Nodehaus?

We're always testing and adding new models to Nodehaus. If you have a specific model that is not available yet, you can reach out to us and we'll see what we can do.

How many processing seconds are included in the private products?

Each private product includes the following amounts of processing seconds based on GPU type:

GPU Type	Included Processing
Standard GPUs	50,000 seconds
80 GB GPUs	30,000 seconds
80 GB PRO GPUs	20,000 seconds
140 GB GPUs	12,000 seconds

Additional processing time is billed at the rates specified in the pricing plan.

Can I switch between plans?

Yes, you can upgrade or downgrade your plan at any time. Changes will be applied at the start of your next billing cycle.

What payment methods do you accept?

We accept all major credit cards.

Need custom pricing for your enterprise?

Contact our sales team for volume discounts and custom solutions tailored to your needs.