toolcompass.

Find your next AI tool

Search by product name or task. Press Escape to close.

NeuralForecast

● Identity checked

Research · Vendor site 2026-10-04

NeuralForecast is Nixtla's open-source Python library of neural forecasting models such as NBEATS, NHITS, TFT, and PatchTST with sklearn-style APIs, probabilistic outputs, and hyperparameter tuning. Nixtla also markets an enterprise TimeGPT engine, while NeuralForecast docs focus on developer-friendly model collections and training utilities.

Updated 2026-10-04View sources
Official website
Category
Research
Free access
NeuralForecast installs free via pip or conda; Nixtla's commercial engine offers a requestable free trial but library usage is open source.
API access
NeuralForecast is a Python library; Nixtla's broader platform documents APIs and a free trial for the managed engine separately.

Is NeuralForecast right for you?

A good fit for

Forecasting practitioners who need a broad neural model zoo with unified sklearn-like interfaces in Python.

Before you choose

Library users must provision their own compute; enterprise TimeGPT pricing is sales-led and separate from OSS installs.

Neural forecasting toolkit

NeuralForecast packages many proven neural forecasting architectures with exogenous variable support, interpretability helpers, and automatic hyperparameter search.

What it can do

Features & capabilities

Unknown is different from unavailable. Each fact carries its own evidence.

CapabilityValueEvidenceChecked
Model collectionIntro docs list implementations including MLP, LSTM, NBEATS, NHITS, TFT, PatchTST, and additional architectures.Facts sourced2026-10-04
Probabilistic forecastingDocumentation highlights quantile losses and parametric distribution adapters for probabilistic outputs.Facts sourced2026-10-04
Install commandsDocs provide pip and conda install instructions for the neuralforecast package.Facts sourced2026-10-04

Understand the total cost

NeuralForecast pricing & plans

Free

Free

NeuralForecast installs free via pip or conda; Nixtla's commercial engine offers a requestable free trial but library usage is open source.

Access
NeuralForecast installs free via pip or conda; Nixtla's commercial engine offers a requestable free trial but library usage is open source.
Explore pricing & history

Alternatives to NeuralForecast

View all ↗

The practical questions

Frequently asked questions

What is NeuralForecast used for?

NeuralForecast is Nixtla's open-source Python library of neural forecasting models such as NBEATS, NHITS, TFT, and PatchTST with sklearn-style APIs, probabilistic outputs, and hyperparameter tuning. Nixtla also markets an enterprise TimeGPT engine, while NeuralForecast docs focus on developer-friendly model collections and training utilities.

Does NeuralForecast have a free plan?

NeuralForecast installs free via pip or conda; Nixtla's commercial engine offers a requestable free trial but library usage is open source.. This record lists ongoing free access; check the plan limits before starting.

How much does NeuralForecast cost?

No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.

Can I use NeuralForecast through an API?

NeuralForecast is a Python library; Nixtla's broader platform documents APIs and a free trial for the managed engine separately.. API access and subscription access may have different terms; consult the linked sources.

What should I check before choosing it?

Library users must provision their own compute; enterprise TimeGPT pricing is sales-led and separate from OSS installs.

Price history

No retained pricing changes yet. A current price alone does not establish a historical trend.

How this profile is supported

Facts apply to the named version and check date. Send a sourced correction if something changed.