Lium
5.0 out of 5 starsAverage Ratings 1 Rating
Average Ratings 0 Ratings
Description
lium.io gives developers, researchers and AI agents on-demand access to NVIDIA GPU capacity from independent providers. Rent a single GPU or a full 8-GPU node for training, fine-tuning, inference and batch workloads, with SSH and Jupyter access.
Use the web, CLI, Python SDK, API or MCP integration to deploy. Per-second billing and usage-based marketplace rates make short jobs practical, without a minimum commitment. Secure and Spot options let you choose capacity for your workload. Live prices and availability are published on the marketplace.
New accounts can receive $5 of credit after signup checks. GPU providers set their own rental prices and earn 95% of rental revenue plus bonuses. List capacity in the provider portal; developer guides are in the documentation.
Description
Nextbit Inference provides open-weight AI models accessible via API endpoints that align with the request formats utilized by OpenAI and Anthropic. Developers can browse a catalog of models and seamlessly call them using standard client libraries, all under a token-based pricing structure. The service features options for shared serverless inference as well as dedicated single-tenant endpoints that come with guaranteed capacity. Additionally, Nextbit facilitates model fine-tuning and deployment services for both fine-tuned and customer-supplied models. This platform caters specifically to AI and machine-learning engineers focused on developing applications, agents, and efficient production inference workflows. Clients have the flexibility to select between EU or global endpoints; dedicated deployments can be tailored to meet specific data-location and infrastructure requirements. The API is designed to integrate smoothly into existing development processes, and the serverless inference option enables users to leverage GPU-backed model serving while eliminating the burdens of managing the underlying infrastructure. This comprehensive offering empowers developers to innovate rapidly and effectively in the fast-evolving AI landscape.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Amazon Web Services (AWS)
No
Anthropic
No
Claude Code
No
Cline
No
Cursor
No
Datadog
No
Google Cloud Platform
No
Microsoft Azure
No
OpenAI
No
Prometheus
No
Integrations
Amazon Web Services (AWS)
Yes
Anthropic
Yes
Claude Code
Yes
Cline
Yes
Cursor
Yes
Datadog
Yes
Google Cloud Platform
Yes
Microsoft Azure
Yes
OpenAI
Yes
Prometheus
Yes
Pricing Details
$0.40 per GPU per hour
Usage-based marketplace pricing, billed per second. Providers set their own GPU-hour rates, which vary with supply. Check the live pricing page for current rates and availability. No minimum commitment. New accounts can receive $5 of credit after passing signup checks.
Free Trial
Yes
Free Version
No
Pricing Details
$0.075/1M input tokens
Serverless inference is billed per million input and output tokens at model-specific rates; Gemma 3 12B starts at $0.075 per million input tokens and $0.15 per million output tokens. Dedicated Inference uses a fixed monthly fee paid upfront, with 6-, 12-, 18-, or 24-month commitments and capacity-based tiers.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
lium.io
Website
lium.io
Vendor Details
Company Name
NEXTBIT 256, S.L.
Founded
2021
Country
Spain
Website
www.nextbit256.com