A lightweight AI application that can generate and display a gallery of images, powered by Stable Diffusion XL model. Built with Vuetify, Lightning AI and Meteron.
Monetize AI
Meteron handles LLM and generative AI metering, load-balancing and storage.
All-in-one AI toolset
Free developers from time-consuming, unnecessary processes that slow your work, so you and your team can focus on building AI powered products.
Metering
Meteron provides a simple, yet powerful metering mechanism. Charge your users per request or per token (or both!).
Elastic scaling
Meteron can queue up and load-balance requests across your servers. Add more servers at any time.
Unlimited Storage
We upload images to the cloud so you will not run out of storage. All major cloud providers are supported.
Any model - text, image
Works with any model. Plug in your Llama, Mistral, Stable Diffusion v1, v2, DALL-E or any other image generation model
Build your AI app
In hours, not weeks. Check out examples on how to build your own projects with Meteron.
A multi-tenant applications where users can register and generate images of their rooms using Controlnet AI model. Assets, queueing and metering are enforced by Meteron. Generation is done by lightning.ai.
A collection of individual function on how to send image generation requests through Meteron, query results, ensure per-user limits, charge per request or per tokens and more.
An ecosystem of integrations
Pricing
Start for free, upgrade at any time.
Monthly
Yearly (-10% coming soon)
Free
$0 / mo
Professional
$39 / mo
Business
$199 / mo
Usage
Usage
Usage
Usage
Admins & Members (coming soon)
Admins & Members
1
Admins & Members
5
Admins & Members
30
Storage (included in plan, you can purchase more)
File Storage
5GB
File Storage
300GB
File Storage
2TB
Image Generations (included in plan, you can purchase more)
Image Generations
1500
Image Generations
10 000
Image Generations
100 000
LLM chat completions (included in plan, you can purchase more)
LLM chat completions
10 000
LLM chat completions
50 000
LLM chat completions
800 000
Features
Features
Features
Features
Per user metering
Per user metering
Per user metering
Per user metering
Credit system
Credit system
Credit system
Credit system
Elastic queue (absorb high demand spikes)
Elastic queue (absorb high demand spikes)
Elastic queue (absorb high demand spikes)
Elastic queue (absorb high demand spikes)
Server concurrency control
Server concurrency control
Server concurrency control
Server concurrency control
Intelligent QoS
Intelligent QoS
Intelligent QoS
Intelligent QoS
Cloud Storage
Cloud Storage
Cloud Storage
Cloud Storage
Performance Tracking
Performance Tracking
Performance Tracking
Performance Tracking
Automatic Load Balancing
Automatic Load Balancing
Automatic Load Balancing
Automatic Load Balancing
Automatic Retries (coming soon)
Automatic Retries
Automatic Retries
Automatic Retries
Custom Cloud Storage (your own S3, GCS, Azure Storage, etc.) (coming soon)
Custom Cloud Storage (your own S3, GCS, Azure Storage, etc.)
Custom Cloud Storage (your own S3, GCS, Azure Storage, etc.)
Custom Cloud Storage (your own S3, GCS, Azure Storage, etc.)
Data Export (coming soon)
Data Export
Data Export
Data Export
FAQs
Do I need to use any special libraries when integrating Meteron?
Nope, you can use your favorite HTTP client such as curl, Python requests, JavaScript fetch libraries. Instead of sending request to your inference endpoint you will send it to the Meteron's generation API. This API can be either blocking or non blocking, returning the reference to the generated image.
How do I tell Meteron where my servers are?
You can do it through the web UI if your servers are static or rarely change. However, we also provide a simple API that you can use to update your servers dynamically. This API can be used to update your servers in real time, for example, when you are using a AI platforms such as lightning.ai, runpod.io, etc.
How does the queue prioritization work?
By default Meteron provides several standard business rules. With each request you can specify priority class (high, medium, low) where high are your VIP users and will not incur any queueing delays. Medium priority class users will incur delays but will always be ahead of low priority users. Low priority requests will be served last, these can be your "free" users that are served when there is no load on the system.
Do I need coding knowledge to use this product?
Meteron is a "low-code" service where some knowledge about HTTP is needed. However, we do provide example on how to integrate Meteron. If you do get stuck, join our Discord server and we will be happy to help out.
Can I host Meteron server myself?
Yes, on-prem licenses are available. You will get a batteries included system that you can run on any cloud provider. Contact us for more info at [email protected].
What forms of payment do you accept?
We accept all major credit cards as well as direct wire transfers.
How does per-user metering work?
When adding model endpoints in Meteron (clusters) you can specify daily and monthly limits. WHen these limits are specified, each time you send an image generation request, add the X-User header with the user ID (or email) and we will ensure that this user cannot go above limits.
