Average Ratings 0 Ratings
Average Ratings 0 Ratings
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.
Description
Timestral represents a suite of time-series foundation models along with a Python inference toolkit designed to create multivariate probabilistic forecasts based on historical data sequences. It comes in four different model sizes—5M, 28M, 123M, and 209M parameters—that are capable of handling past-only, known-future, and categorical covariates, providing quantile forecasts while accommodating context windows as extensive as 32,768 time steps. Users have the flexibility to load pretrained weights either from the Hugging Face Hub or directly from local files, enabling them to perform inference on both CPU and GPU. Such forecasts can be seamlessly integrated into various applications, including monitoring systems, capacity planning, energy management, supply chain logistics, financial risk assessment, or maintenance operations. Furthermore, Timestral offers zero-shot forecasting capabilities and can be tailored to specific domain data through the Mistral Forge. This package is primarily aimed at data scientists, machine learning engineers, and collaborative teams focused on developing robust forecasting solutions; the repository code is licensed under Apache 2.0, while the model weights are governed by a separate Modified MIT license. With its comprehensive features, Timestral is positioned to significantly enhance the accuracy and efficiency of predictive analytics in numerous industries.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Integrations
Amazon Web Services (AWS)
Yes
Anthropic
Yes
Claude Code
Yes
Cline
Yes
Cursor
Yes
Datadog
Yes
Google Cloud Platform
Yes
Microsoft Azure
Yes
Mistral Forge
No
OpenAI
Yes
Integrations
Amazon Web Services (AWS)
No
Anthropic
No
Claude Code
No
Cline
No
Cursor
No
Datadog
No
Google Cloud Platform
No
Microsoft Azure
No
Mistral Forge
Yes
OpenAI
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
Pricing Details
No price information available.
Free Trial
No
Free Version
Yes
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
No
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
NEXTBIT 256, S.L.
Founded
2021
Country
Spain
Website
www.nextbit256.com
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
github.com/mistralai/timestral