One Model, Infinite Predictions
Pre-trained tabular foundation models for making predictions on structured data.
Instant, accurate predictions
State-of-the-art predictions in seconds. Skip model selection & tuning.
Industry agnostic
Works with data from any industry across thousands of use-cases.
Data efficiency
With 50% of the data still as good as or better than other methods tuned for hours.
Faster deployment pipelines
No retraining needed; update the context to the model with new data and get updated predictions.
No more pre-processing
Handles missing values, outliers, uninformative features, text, categorical & numerical data.
TabPFN-2.5
TabPFN-2.5 is the newest generation of TabPFN that unlocks scale and speed for tabular foundation models.
Best for: Datasets of up to 50K samples & 2K features.
Available now via API or non-commercial OSS on Hugging Face.
TabPFN Enterprise
TabPFN Enterprise includes the next generation of TabPFN models that go beyond TabPFN-2.5.
TabPFN-TS
TabPFN-TS is the world’s most accurate model for zero-shot time-series forecasting.
TabPFNv2
TabPFNv2 is our open, breakthrough foundation model redefining tabular machine learning.
TabPFN-2.5
TabPFN-2.5 is the newest generation of TabPFN that unlocks scale and speed for tabular foundation models.
Best for: Datasets of up to 50K samples & 2K features.
Available now via API or non-commercial OSS on Hugging Face.
TabPFN Enterprise
TabPFN Enterprise includes the next generation of TabPFN models that go beyond TabPFN-2.5.
TabPFN-TS
TabPFN-TS is our best performing model for zero-shot time-series forecasting.
TabPFNv2
TabPFNv2 is our open, breakthrough foundation model redefining tabular machine learning.
Testimonials
Hitachi is committed to advancing predictive maintenance across our rail networks. Working with Prior Labs and TabPFN helps us accelerate our use of data for reliability and safety while reducing operational overhead.
Complex lung diseases are one of the most challenging areas in medicine. TabPFN allows us to detect across the broad range of the proteome to deliver actionable clinical innformation with greater efficiency, helping us push the boundaries of liquid biopsy and improve diagnostic accuracy at scale.
Using TabPFN for crop yield forecasting will be a game changer. TabPFN gives benchmark performance in a matter of seconds whereas traditional tree-based and kernel-based methods can take up to several days. This is an incredible speed up that will ease operations and allow more efficient forecasting.
Accurately classifying cancer patients and healthy individuals based on the distribution of immune cells in the peripheral blood was a remarkably challenging task — TabPFN made it a reality.
I just plugged it into my Google Sheets and it instantly classifies transactions - what you are doing is very powerful!
Tested…on macadamia yield forecasting data. In summary, quick to run, and with no tuning gave better results than ridge regression and gradient boosting.
For Businesses
