Sign in
async jobs

Submit an async finetune job

Changed on

Queues a finetune job and returns immediately with its job_id. The job runs in a sandbox; poll GET /v2/finetune/jobs/{job_id} for its state and result. Accepts the same body as the synchronous endpoint plus an optional job_options.

post/v2/finetune/async

Request

  • Base URL: https://api.nixtla.io
  • URL: https://api.nixtla.io/v2/finetune/async
  • Auth: HTTP bearer

Request body

freqstring required

The frequency of the data represented as a string. 'D' for daily, 'M' for monthly, 'H' for hourly, and 'W' for weekly frequencies are available.

modelstring

Model to use as a string. Common options are (but not restricted to) timegpt-1 and timegpt-1-long-horizon. Full options vary by different users. Contact support@nixtla.io for more information. We recommend using timegpt-1-long-horizon for forecasting if you want to predict more than one seasonal period given the frequency of your data.

finetune_stepsinteger

The number of tuning steps used to train the large time model on the data. Set this value to 0 for zero-shot inference, i.e., to make predictions without any further model tuning.

finetune_loss'default' | 'mae' | 'mse' | 'rmse' | 'mape' | 'smape' | 'poisson'

The loss used to train the large time model on the data. Select from ['default', 'mae', 'mse', 'rmse', 'mape', 'smape', 'poisson']. It will only be used if finetune_steps is larger than 0. Default is a robust loss function that is less sensitive to outliers.

finetune_depth1 | 2 | 3 | 4 | 5

The depth of the finetuning. Uses a scale from 1 to 5, where 1 means little finetuning, and 5 means that the entire model is finetuned. Note that this parameter is only effective for timegpt-1 and timegpt-1-long-horizon models; it has no effect on the other models. By default, the value is set to 1.

output_model_idstring nullable

ID to assign to the finetuned model

finetuned_model_idstring nullable

ID of previously finetuned model

hist_exoginteger[] nullable

Zero-based indices of the exogenous features to treat as historical.

multivariateboolean

Compute multivariate predictions across a batch of multiple time series. Requires all time series with overlapping dates. Note that this is only effective for timegpt-2.1 model and it has no effect on the other models. By default, the value is set to False.

model_parametersobject nullable

Optional dictionary of parameters to customize the behavior of the large time model.

Response

Successful Response

job_idstring required

Identifier for the accepted job. Prefixed per task (e.g. fc- for forecast).

Example response

{
  "job_id": "fc-4f2a1c9e8b7d4a6f9c3e1b5d7a9f2c4e"
}

Changes