Love that this is a home‑grown Mexican project with world‑class engineering.  Its models are impressively easy to use with a pair of lines of code, fast and cost‑efficient, and the catalogue is highly diverse: from classic statistical baselines, through machine‑learning methods, all the way to neural and foundation models like TimeGPT. I have more experience using the statsforecast library, which, if you’ve ever used Dr Rob Hyndman’s revered `forecast` package in R, you’ll feel right at home: the API feels familiar while adding many modern conveniences. Besides these, extras such as a rich suite of error metrics, built‑in cross‑validation, statistical feature generators, scalable execution on both Pandas and PySpark, probabilistic forecast intervals, and even an integrated AI assistant in its webpage to make everyday time‑series work delightfully productive. Review collected by and hosted on G2.com.

Cross‑validation, while powerful, is still hard to configure and not very intuitive. Despite the handy AI helper, clearer in‑line documentation and more usage examples would save time, particularly, when AI hallucinations forces you to double‑check primary sources. Finally, it baffles me that the library isn’t far more popular already; something this good deserves a wider crowd! Review collected by and hosted on G2.com.

user friendly, great performance, zero-shot Review collected by and hosted on G2.com.

nothing in particular, so all good!!!!!! Review collected by and hosted on G2.com.

We didn't have the resources to create forecasts in house as we don't employ data scientists, when I heard a data scientist friend saying he is using that on a day to day basis decided to try it and it has been great. We fully depend on it now, the onboarding was pretty simple and so far pretty reliable. I don't think it took us more than a week from first call to having it in use in a few pipelines.

Customer support has been nice, we like to think we are easy customers but nevertheless they offered calls with the tech team to help with the implementation. Integration was very simple though, so we didn't use those. Review collected by and hosted on G2.com.

It would be nice to have the API docs available, we are using the SDK so it isn't an issue but we have a few ideas we had to wait on because those haven't been released yet. Review collected by and hosted on G2.com.

I really appreciate how straightforward Nixtla makes the time-series forecasting process. It's much simpler to use and integrate into my code than building everything from the ground up. I've incorporated their tools into just about every forecasting pipeline I work on in one way or another. Review collected by and hosted on G2.com.

The main drawback I find with Nixtla is that it could offer more features. While it already supports all the top models, I hope that additional options will be introduced to StatsForecast and MLForecast in the future. Review collected by and hosted on G2.com.

I really appreciate how you can start with a pandas dataframe and rapidly explore a wide range of models, from traditional statistical approaches to advanced Neural Networks. The selection of models available is truly impressive. I also value the inclusion of Tuning and Hierarchical Reconciliation features, which are quite uncommon. Review collected by and hosted on G2.com.

It's limited to mainly just modeling and a subset of feature engineering tasks. It would be nice if it was a more end to end package to keep the flow consistent for the data scientist. Review collected by and hosted on G2.com.

Nixtla's TimeGPT provided a streamlined integration that uses a 7-day historical dataset to forecast pollution levels 24 hours ahead. This 'monitoring + forecasting' approach combines continuous sensor monitoring with advanced predictive analytics, enabling automated alerts and proactive management (Oizom)

•

Leveraged an hourly 7-day historical dataset to accurately predict next-day pollution levels

•

Seamless integration with Oizom's existing dashboard, boosting user engagement

•

Implemented within 1 week, significantly reducing development complexity Review collected by and hosted on G2.com.

No downsides, it was a very straightforward integration. Review collected by and hosted on G2.com.

Its simple to use either via the api or as a MS Excel plugin. I have used both, but for our use it turns out using Excel to visualize with other data is efficient. Review collected by and hosted on G2.com.

It would be nice if they had some sort of "chat" like interface or direct use by another LLM. Review collected by and hosted on G2.com.

Their stack it's in python, regularly maintained, consistent data structures and design patterns across libraries, which reduces engineering/implementation time, but also a wide range of classical methods for time series analysis, uncertainty quantification, along with novel developments , especially in the deep learning domain. The community is highly supportive, not only the engineering team from Nixtla, and most importantly, OPEN SOURCE. Review collected by and hosted on G2.com.

Not sure what you are asking about, things work well here. Review collected by and hosted on G2.com.

The modular design and scalability. Nixtla’s libraries integrate seamlessly into existing ML pipelines and handle thousands of time series efficiently. The APIs are consistent across models, which makes experimentation and deployment straightforward. Review collected by and hosted on G2.com.

Some functions still lack detailed parameter explanations, and version updates occasionally introduce minor breaking changes. Review collected by and hosted on G2.com.

As an aerodynamics engineer, I work with time series data daily, from wind tunnel tests to system performance metrics. TimeGPT has been a game-changer, letting me quickly create accurate forecasts without building models from scratch. Integration into our Python workflows was effortless, and we were up and running in hours. We now rely on it weekly for everything from rapid prototyping to system monitoring. Uploading data, generating forecasts, and analyzing results is very easy, and it performs impressively even with complex, noisy datasets. Nixtla’s customer support is outstanding , very responsive, knowledgeable, and quick to act on feedback. Review collected by and hosted on G2.com.

Overall, nothing significant to dislike. Occasionally, very specific forecasting scenarios require extra tweaking, though support has always been fast and effective. Review collected by and hosted on G2.com.