USASI
Model release

Chronos-2

Release in the Chronos (time series models) family · version Chronos-2 (amazon/chronos-2, 120M)

Maintained by Amazon (Amazon Web Services)187

Chronos-2 is a 120M-parameter, encoder-only time-series foundation model from Amazon, released on October 20, 2025. Inspired by the T5 encoder, it produces multi-step quantile forecasts and uses group attention to learn in context across related series and covariates, supporting univariate, multivariate, and covariate-informed forecasting with contexts up to 8,192 steps and horizons up to 1,024 steps.13

Last reviewedEntry updated Documented release Oct 20, 2025

Availability and license

Overall availability

Public

Documented as available to the general public. Access conditions and license terms may still apply.21

Availability is separate from permission: read the license before using or redistributing.

Model-disclosure tier

Computed from the checklist below using USASI rubric v0.1. An editorial category, not a certification.
Model-disclosure tier (USASI rubric v0.1): Open-weight

The model parameters for this release can be downloaded by the public. License terms may still restrict use, redistribution, or commercial use.

How tiers are computed

Public materials checklist

Items for a model under USASI rubric v0.1. Unknown means unassessed or insufficient evidence.
Public materials checklist for Chronos-2
ItemStatusNotes and evidence
WeightsCan the general public download the model parameters for this release?PublicWeights (safetensors) are published on Hugging Face without an access gate.2
Inference codeIs code for running the model published?PublicThe Apache-2.0 chronos-forecasting package (version 2.0 or later) provides the Chronos2Pipeline used in the card's examples.136
Training codeIs the code used to train the model published?UnknownThe repository's training scripts are documented for the original Chronos models of March 2024; training code for Chronos-2 was not found.5
Training-data informationPublic = the training data itself can be obtained. Partial = composition or sources are documented without full access.PartialThe card lists subsets of the public Chronos Datasets and GIFT-Eval Pretrain collections plus synthetic univariate and multivariate data; the report describes how the synthetic data was generated, but the synthetic data itself is not documented as released.17
Training recipeAre the training configuration and procedure documented in enough detail to follow?PartialThe technical report describes the architecture, training, and training data at a summary level.7
Evaluation materialsPublic = evaluation code or prompts that let others re-run the evaluations are published. Partial = results only.PartialThe report and card give results on fev-bench, GIFT-Eval, and Chronos Benchmark II; the repository announces the separately released fev benchmarking package, but instructions to re-run all reported Chronos-2 evaluations were not verified.713

What it is useful for

Amazon describes Chronos-2 for zero-shot forecasting without task-specific training, with local inference through the chronos-forecasting package and production deployment through Amazon SageMaker (AutoGluon-Cloud or SageMaker JumpStart); the card states it supports both GPU and CPU inference.18

Run and use notes

Documented facts only. No hardware or performance claims are made without a cited source and stated assumptions.
  • The card documents local installation with pip ("chronos-forecasting>=2.0") and a pandas-based prediction API, and deployment to SageMaker with AutoGluon-Cloud or SageMaker JumpStart.1

Organization context

Provenance and derivatives

Trained by Amazon Web Services on subsets of the Chronos Datasets and GIFT-Eval Pretrain collections and on synthetic data. The architecture is described as inspired by the T5 encoder; no pretrained base model is named.17

Other releases in the Chronos (time series models) family

No other releases in this family have been assessed.

Chronos (time series models) family overview

U.S. eligibility

Project eligibility rests on documented governing or maintaining entities, not on contributors.

Eligible · basis: Documented U.S. control

The model is published by Amazon on Hugging Face and GitHub, and the Chronos-2 report and Amazon's science blog attribute it to Amazon Web Services, a segment of Amazon.com, Inc. Amazon.com, Inc. has its principal executive offices in Seattle, Washington, per its fiscal 2025 Form 10-K.1789

Assessed Sep 29, 2026

Sources

  1. 1.
    amazon/chronos-2 model card (external site: huggingface.co)

    Amazon (Hugging Face) · Model card · accessed Sep 29, 2026

  2. 2.
  3. 3.
    amazon-science/chronos-forecasting README (external site: raw.githubusercontent.com)

    Amazon Science (GitHub) · Repository · accessed Sep 29, 2026

  4. 4.
  5. 5.
    chronos-forecasting scripts directory (training and evaluation) (external site: github.com)

    Amazon Science (GitHub) · Repository · accessed Sep 29, 2026

  6. 6.
    chronos-forecasting on PyPI (JSON metadata) (external site: pypi.org)

    Python Package Index · Release notes · accessed Sep 29, 2026

  7. 7.
  8. 8.
    Introducing Chronos-2: From univariate to universal forecasting (external site: amazon.science)

    Amazon Science · Announcement · published Oct 20, 2025 · accessed Sep 29, 2026

  9. 9.
    Amazon.com, Inc. Form 10-K for the fiscal year ended December 31, 2025 (external site: sec.gov)

    Amazon.com, Inc. (via U.S. Securities and Exchange Commission EDGAR) · Filing · accessed Sep 29, 2026

This listing is not an endorsement, a safety assessment, or a federal approval.

Support Us

Help keep USASI useful.

Optional. No USASI account required. Payment takes place on the linked provider’s website (Buy Me a Coffee).

About supporting this project