MongoDB - Build AI That Scales
Mini toolsToto 2.0
By Datadog
Toto 2.0 is a family of time-series foundation models developed by Datadog for multivariate forecasting, especially observability and general forecasting workloads. The collection includes five checkpoints, from 4M to 2.5B parameters, trained with the same recipe and released under Apache 2.0. Toto 2.0 supports zero-shot forecasting, multivariate inputs, probabilistic quantile forecasts, variable horizons and context lengths, using a decoder-only patched transformer architecture.
New
Structured_data
Gen 7
Overview
Toto 2.0 is Datadog’s open-source time-series forecasting model family for multivariate, zero-shot, probabilistic forecasting.
About Datadog
AI-Powered Observability and Security
See inside any stack, any app, at any scale, anywhere.
Industry:
Computer and Network Security
Company Size:
8100
Location:
New York, New York, US
Website:
datadoghq.com
Tools using Toto 2.0
No tools found for this model yet.
Last updated: May 20, 2026
