P

TabPFN-3.5

Model directory
Prior-Labs/tabpfn_3_5

TabPFN-3.5 non-commercial model license | Upstream checkpoint

Prior Labs’ September 2026 tabular foundation model can forecast through the first-party time-series adapter. Known-future covariates are supported; multiple targets are forecast independently. Managed API, SAP and cloud deployment options use provider-specific variants and terms.

Where to run this model

Compute availability, hardware requirements, and pricing depend on the execution provider.

Hugging Face · Weights & deployment

Get model weights, deployment instructions, and current provider listings.

  • Retrocast · The Forecasting Company

    managed service · Family / provider variant · Source checked 2026-10-06

    Forecast through the managed API using tabpfn-ts. The provider controls the deployed variant and request limits.

  • Prior Labs API

    managed service · Family / provider variant · Source checked 2026-10-06

    Use the managed TabPFN client with the time-series adapter. Select the provider model version explicitly.

  • AWS SageMaker · Prior Labs

    managed deployment · Family / provider variant · Source checked 2026-10-06

    Deploy a TabPFN offering in your AWS account. Check the selected marketplace variant and license.

  • SAP AI Core · TabPFN-3.5 Plus

    managed service · Family / provider variant · Source checked 2026-10-06

    SAP offers TabPFN-3.5 Plus through AI Core, distinct from the downloadable base checkpoint.

  • Azure AI Foundry · Prior Labs

    provider listing · Family / provider variant · Source checked 2026-10-06

    Prior Labs documents enterprise Azure deployment. Confirm the available variant with the provider.

Hugging Face provider mappings checked 2026-10-06. No Inference Provider mapping was listed for this checkpoint.

Model Classification

Family

TabPFN

Type

n/a

Capabilities

forecastingzero-shot

Tags

model-releasecovariates

Specifications

Parameters
n/a
Architecture
in-context tabular Transformer with a time-series regression adapter
Context length
n/a
Max context
n/a
Minimum history
n/a
Recommended history
n/a
Input step
n/a
Required target series
1
Temperature
Ignored
Top P
Ignored
Max output
n/a
License
TabPFN-3.5 non-commercial model license