Forecasting platforms & libraries · Nixtla

Nixtla

Open-source statistical/ML forecasting libraries plus TimeGPT, a hosted foundation model for time series.

Visit Nixtla Alternatives

Nixtla is both an open-source ecosystem and a commercial product. Its open-source libraries — StatsForecast, MLForecast and NeuralForecast — provide fast, production-oriented implementations of statistical models (AutoARIMA, AutoETS, AutoCES, Theta), gradient-boosting forecasters, and neural forecasting models, engineered to fit millions of individual time series in parallel rather than one series at a time, which is where they distinguish themselves from libraries built around a single-series workflow. On top of that, Nixtla offers TimeGPT, a hosted, pre-trained foundation model for forecasting and anomaly detection accessed via API, aimed at teams that want a forecast without training their own model. TimeGPT supports multiple series, external variables, fine-tuning and prediction intervals. The open-source libraries are free; TimeGPT is a paid, quote-based enterprise subscription.

At a glance

Vendor Nixtla
Pricing model Free tier + paid plans
Free tier Yes
Deployment Cloud, Self-hosted
Open source Yes (Apache-2.0)
Best for Teams forecasting at very large scale (thousands to millions of series) or wanting a no-training hosted forecasting API.

Pricing

Open-source libraries (StatsForecast, MLForecast, NeuralForecast) are free; TimeGPT is a custom enterprise subscription with no published price list.

Pricing has not been verified yet — see the vendor's site.

Features

  • AutoARIMA, AutoETS, AutoCES and Theta statistical models at scale
  • Parallelized fitting across millions of time series
  • TimeGPT hosted foundation model for zero-training forecasting
  • Anomaly detection via TimeGPT
  • Fine-tuning of TimeGPT on custom data
  • External regressor and prediction-interval support
  • Python-first API across the ecosystem

Integrations

Profile last reviewed September 21, 2026

Head to head

Alternatives

Prophet Open-source forecasting library designed to be easy to use on business time series with holidays and seasonality. Darts Open-source Python library offering one unified API across dozens of classical, ML and deep-learning forecasting models. AutoGluon Open-source AutoML library from AWS that automates model selection and ensembling, including a time-series forecasting module.

Nixtla in the index now

Terms to know

Time series forecasting Predicting future values of a metric using patterns found in its own historical sequence over time. Demand forecasting Estimating future customer demand for a product so inventory, production and staffing can be planned ahead. Predictive analytics Analytics that uses historical data and statistical models to estimate what is likely to happen next. Anomaly detection Identifying data points or patterns that deviate significantly from expected or normal behavior. Large language model (LLM) A neural network trained on vast amounts of text to predict and generate language, the technology behind most modern AI assistants.

Related guides

How to choose a forecasting platform or library Pick a time-series forecasting library by how many series you're forecasting and how much modeling control your team wants. How to forecast demand Baselines worth beating, where seasonality and model choice actually matter, and how to judge accuracy honestly. Time series analysis, explained How analysts model data ordered in time — the patterns forecasting methods look for, the pitfalls, and where the data actually lives.