toki 1.0
Zero-shot forecasting.
Forecast multivariate time series in a single API call — no training required. Built for enterprise inference.
Benchmark numbers on this page are placeholders.
Why a foundation model for time series?
Classical forecasting requires training a separate model per dataset and tuning hyperparameters by hand. Lead times are long and maintenance costs are recurring.
Cold-start regimes — new sites, new SKUs — are structurally difficult for models that have not seen comparable history.
Time series foundation models are pre-trained on diverse data and applied zero-shot to any task. toki 1.0 brings this approach to production quality.
What sets it apart
Zero-shot
Use the pre-trained model as-is. No task-specific fine-tuning — call the API and get predictions back.
Multivariate
Forecast multiple series jointly. Cross-series dependencies are captured for sharper results than per-series models.
Covariates
Pass numerical and categorical covariates — holidays, weather, campaign types — alongside the target series.
Cold-start
Generate reasonable forecasts for new series with little history by leveraging patterns learned at scale.
Forecast in a single request
No training required — call the API and get predictions back. Available via SDK or REST.
curl -X POST https://api.toki.neurogica.com/v1/forecast \
-H "Authorization: Bearer $TOKI_API_KEY" \
-d '{
"series": [...],
"horizon": 24
}'from toki import Client
client = Client(api_key="...")
forecast = client.forecast(
series=df,
horizon=24,
)How the model works
Inputs are normalized and patched, processed by a Transformer that captures intra- and inter-series structure, and emitted as a probabilistic forecast.
- 01 / TokenizeTokenizeRange normalization and numeric tokenization
- 02 / PatchPatchSplit series into fixed-length patches
- 03 / TransformerTransformerLearn intra- and inter-series dependencies
- 04 / ForecastForecastEmit quantile-aware forecast distributions
Outperforms baselines, zero-shot
DEMOEvaluated against major open-source time series foundation models on axes equivalent to fev-bench and GIFT-Eval.
fev-bench win-rate
Skill score (higher is better). All numbers are placeholders.
GIFT-Eval ranking
| Rank | Model | Score |
|---|---|---|
| #1 | toki 1.0 | 0.81 |
| #2 | Baseline A | 0.74 |
| #3 | Baseline B | 0.71 |
| #4 | Baseline C | 0.66 |
| Rank | Model | Score |
|---|---|---|
| #1 | toki 1.0 | 0.78 |
| #2 | Baseline A | 0.70 |
| #3 | Baseline B | 0.68 |
| #4 | Baseline C | 0.61 |
Considering a PoC?
Tell us about your use case, data scale, and requirements. Our engineering team will reach out from there.