Datadog · hosted on Ephemeris
Toto 2 (313M) API
Datadog's forecaster trained heavily on observability metrics. The strongest single member on short horizons in our calibration, and the route-mode choice for multivariate series.
Explicit mode
"model": "toto2-313m"API nametoto2-313m
PublisherDatadog
WeightsDatadog/Toto-2.0-313m
Size313M
LicenceApache-2.0
MultivariateYes
CovariatesNo
Context read4,096 most recent points
01
REST
Call Toto 2 (313M) directly
cURLUTF-8
curl --request POST \
--url https://ephemeris.cascade.industries/api/v1/forecast \
--header "Authorization: Bearer pc_live_your_key" \
--header "Content-Type: application/json" \
--data '{
"mode": "explicit",
"model": "toto2-313m",
"series": [{ "values": [112, 118, 132, 129, 121, 135, 148, 148], "freq": "M" }],
"horizon": 12,
"quantiles": [0.1, 0.5, 0.9]
}'02
Agents
From Claude, Cursor or any MCP client
Add the Ephemeris MCP server, then ask your agent to forecast with toto2-313m. The forecast tool takes mode: "explicit", model: "toto2-313m".
03
Accuracy
How it scores
On GIFT-Eval (97 configurations, official harness), Toto 2 (313M) alone scores CRPS 0.4842 and MASE 0.7038 as a ratio to seasonal naive (lower is better). The Ephemeris ensemble, which includes it, scores 0.4662 and 0.6841. Full benchmark results.
No GPU to run