FAQ

No, TimeGPT is not based on any large language model. While it follows the same principle of training a large transformer model on a vast dataset, its architecture is specifically designed to handle time series data and it has been trained to minimize forecasting errors.

To get started with TimeGPT, you need to register for an account here. You will receive an email asking you to confirm your signup. After confirming, you will be able to access your dashboard, which contains the details of your account.

For a more in-depth understanding of TimeGPT, please refer to the research paper. While certain aspects of the model’s architecture remain confidential, registration for TimeGPT is open to all. New users receive $1,000 USD in free credits and subsequent usage fees are based on token consumption. For more details, please refer to the Pricing and Billing section

• Through the Python SDK

• Via the TimeGPT API. For instructions on how to call the API using different languages, please refer to the API documentation

Both methods require you to have a API key, which is obtained upon registration and can be found in your dashboard under API Keys.

An API key is a unique string of characters that serves as a key to authenticate your requests when using the Nixtla SDK. It ensures that the person making the requests is authorized to do so.

To integrate your API key into your development workflow, please refer to the tutorial on Setting Up Your API Key.

If you want to check the status of your API key, you can use the validate_api_key method of the NixtlaClient class.

nixtla_client = NixtlaClient( api_key = 'my_api_key_provided_by_nixtla' )

nixtla_client.validate_api_key()

If your key is validating correctly, this will return

INFO:nixtla.nixtla_client:Happy Forecasting! :), If you have questions or need support, please email [email protected]

True

When you validate your API key and it returns False:

• If you are targeting an Azure endpoint, getting False from the NixtlaClient.validate_api_key method is expected. You can skip this step when taregting an Azure endpoint and proceed diretly to forecasting instead.
• If you are not taregting an Azure endpoint, then you should check the following:
  • Make sure you are using the latest version of the SDK (Python or R).
  • Check that your API key is active in your dashboard by visiting https://dashboard.nixtla.io/
  • Consider any firewalls your organization might have. There may be restricted access. If so, you can whitelist our endpoint https://api.nixtla.io/.
    • To use Nixtla’s API, you need to let your system know that our endpoint is ok, so it will let you access it. Whitelisting the endpoint isn’t something that Nixtla can do on our side. It’s something that needs to be done on the user’s system. This is a bit of an overview on whitelisting.
    • If you work in an organization, please work with an IT team. They’re likely the ones setting the security and you can talk with them to get it addressed. If you run your own systems, then it’s something you should be able to update, depending on the system you’re using.

TimeGPT accepts pandas dataframes in long format with the following necessary columns:

• ds (timestamp): timestamp in format YYYY-MM-DD or YYYY-MM-DD HH:MM:SS.
• y (numeric): The target variable to forecast.

(Optionally, you can also pass a DataFrame without the ds column as long as it has DatetimeIndex)

TimeGPT also works with distributed dataframes like dask, spark and ray.

Yes. For guidance on forecasting multiple time series at once, consult the Multiple Series tutorial.

Yes. For instructions on how to incorporate exogenous variables to TimeGPT, see the Exogenous Variables tutorial. For incorporating calendar dates specifically, you may find the Holidays and Special Dates tutorial useful. For categorical variables, refer to the Categorical Variables tutorial.

Yes. To learn how to use TimeGPT for anomaly detection, refer to the Anomaly Detection tutorial.

Yes. To learn how to use TimeGPT for cross-validation, refer to the Cross-Validation tutorial.

Yes. To find out how to forecast historical data using TimeGPT, see the Historical Forecast tutorial.

Yes. For more information, explore the Prediction Intervals and Quantile Forecasts tutorials.

Yes. When dealing with large datasets that contain hundreds of thousands or millions of time series, we recommend using a distributed backend. TimeGPT is compatible with several distributed computing frameworks, including Spark, Ray, and Dask. Both the TimeGPT SDK and API don’t have a limit on the size of the dataset as long as a distributed backend is used.

TimeGPT supports any amount of data for generating point forecasts and is capable of producing results with just one observation per series. When using arguments such as level, finetune_steps, X_df (exogenous variables), or add_history, additional data points are necessary depending on the data frequency. For more details, please refer to the Data Requirements tutorial.

While TimeGPT does not have a maximum forecast horizon, its performance will decrease as the horizon increases. When the forecast horizon exceeds the season length of the data (for example, more than 12 months for monthly data), you will get this message: WARNING:nixtla.nixtla_client:The specified horizon "h" exceeds the model horizon. This may lead to less accurate forecasts. Please consider using a smaller horizon.

For details, refer to the tutorial on Long Horizon in Time Series.

TimeGPT cannot handle missing values or series with irregular timestamps. For more information, see the Forecasting Time Series with Irregular Timestamps and the Dealing with Missing Values tutorial.

The NixtlaClient class has a plot method that can be used to visualize the forecast. This method only works in interactive environments such as Jupyter notebooks and it doesn’t work on Python scripts.

As of now, TimeGPT does not offer support for polars.

TimeGPT is engineered for stability, ensuring consistent results for identical input data. This means that given the same dataset, the model will produce the same forecasts.

TimeGPT was trained on the largest publicly available time series dataset, covering a wide range of domains such as finance, retail, healthcare, and more. This comprehensive training enables TimeGPT to produce accurate forecasts for new time series without additional training, a capability known as zero-shot learning.

While the zero-shot model provides a solid baseline, the performance of TimeGPT can often be improved through fine-tuning. During this process, the TimeGPT model undergoes additional training using your specific dataset, starting from the pre-trained paramaters. The updated model then produces the forecasts. You can control the number of training iterations and the loss function for fine-tuning with the finetune_steps and the finetune_loss parameters in the forecast method from the NixtlaClient class, respectively.

For a comprehensive guide on how to apply fine-tuning, please refer to the fine-tuning and the fine-tuning with a specific loss function tutorials.

No, you do not need to fine-tune every series individually. When using the finetune_steps parameter, the model undergoes fine-tuning across all series in your dataset simultaneously. This method uses a cross-learning approach, allowing the model to learn from multiple series at once, which can improve individual forecasts.

Keep in mind that selecting the right number of fine-tuning steps may require some trial and error. As the number of fine-tuning steps increases, the model becomes more specialized to your dataset, but will take longer to train and may be more prone to overfitting.

Currently, it is not possible to save the fine-tuned parameters for later use. This means you will need to perform fine-tuning each time you submit your data, whether using the Python SDK or the API.

TimeGPT has a flat fee pricing structure with subscription. See our Pricing page for information and find a plan for your needs. We have a subscription plan to meet your needs. You can cancel anytime.

Start for Free
*No credit card needed. Free plan available.

For pricing of TimeGEN-1 on Azure, see the pricing page.

Yes! You can use TimeGPT with our Starter subscription plan, with 50 API calls/month for free. We do also provide some discounted options for academic research. If you would like to learn more, please email us at [email protected].

One token corresponds to one row of your dataset. When using exogenous variables, a token equals one row multiplied by the number of additional columns, excluding the unique_id and ds columns. For instance, the AirPassengers dataset used in the TimeGPT Quickstart consists of 144 rows, corresponding to 144 tokens. In the Exogenous Variables tutorial, the hourly electricity price dataset has 8,400 rows. Since it contains 9 exogenous variables, this totals 84,000 tokens (8,400 rows x 10 columns, including the target). Additionally, you also need to consider the future values of the exogenous variables, which are in a dataset with 120 rows and 9 columns, adding 1,080 tokens (120 x 9). This results in a total of 85,080 tokens.

Furthermore, regardless of the presence of exogenous variables, you must include the number of fine-tune steps and the forecast horizon in your token count, with each step or forecasted value representing one additional token. For instance, if the forecast horizon is 24 and you have 5 series, this adds 120 additional tokens (24 forecasted values x 5 series).

For high-frequency data, we recommend trimming the input whenever possible. For example, when working with minute-level data, consider trimming to the most recent hour to reduce costs.

In the Usage section of your dashboard, you can find a detailed record of your token consumption history, helping you track and manage your usage effectively.

An API call is a request made to TimeGPT to perform an action like forecasting or detecting anomalies. API Usage is as follows:

Forecasting:

1. When not requesting historical forecasts (add_history=False)
   • If you do not set num_partitions, all calls to perform forecasting, finetuning, or cross-validation increase the usage by 1. Note that addition of exogenous variables, requesting uncertainity quantification or forecasting multiple series does not increase the usage further.
   • If the API call requires to send more than 200MB of data, the API will return an error and will require you to use the num_partitions parameter in order to partition your request. Every partition will count as an API call, hence the usage will increase by the value you set for num_partitions (e.g. for num_partitions=2, the usage will increase by 2). If you set num_partitions, all calls to perform forecasting, finetuning, or cross-validation increase the usage by num_partitions.
2. When requesting in-sample predictions (add_history=True), the usage from #1 above is multipled by 2.

Examples

1. A user uses TimeGPT to forecast daily data, using the timegpt-1 model. How many API calls are made? (Ans: 1)
2. A user calls the cross_validation method on a dataset. How many API calls are made (Ans: 1)
3. A user decides to forecast on a longer horizon, so they use the timegpt-1-long-horizon model. How many API calls are made (Ans: 1)
4. A user needs to get the in-sample predicitons when forecasting using add_history=True. How many API calls are made (Ans: 2)
5. A user has a very large dataset, with a daily frequency, and they must set num_partitions=4 when forecasting. How many API calls are made (Ans: 4)
6. A user has to set num_partitions=4 and is also interesed in getting the in-sample predicitons (add_history=True) when forecasting. How many API calls are made (Ans: 8)

Anomaly Detection:

1. If you do not set num_partitions, all calls to perform anomaly detection increase the usage by 1. Note that addition of exogenous variables does not increase the usage further.
2. If the API call requires to send more than 200MB of data, the API will return an error and will require you to use the num_partitions parameter in order to partition your request. Every partition will count as an API call, hence the usage will increase by the value you set for num_partitions (e.g. for num_partitions=2, the usage will increase by 2).

Billing is done through Stripe. We’ve partnered with Stripe to handle all payment processing. You can view your invoices and payment history in your dashboard under Billing.

At Nixtla, we take your privacy and security very seriously. To ensure you are fully informed about our policies regarding your data, please refer to the following documents:

• Privacy Notice

• For the Python SDK, please review the license agreement.

• For TimeGPT, please refer to our terms and conditions.

In addtion, we are currently developing a self-hosted version of TimeGPT, tailored for the unique security requirements of enterprise data. This version is currently in beta. If you are interested in exploring this option, please contact us at [email protected].

ApiError: status_code: 401, body: {'data': None, 'message': 'Invalid API key', 'details': 'Key not found', 'code': 'A12', 'requestID': 'E7F2BBTB2P', 'support': 'If you have questions or need support, please email [email protected]'}

Solution: This error occurs when your TimeGPT API key is either invalid or has not been set up correctly. Please use the validate_api_key method to verify it or make sure it was copied correctly from the API Keys section of your dashboard.

ApiError: status_code: 429, body: {'data': None, 'message': 'Too many requests', 'details': 'You need to add a payment method to continue using the API, do so from https://dashboard.nixtla.io', 'code': 'A21', 'requestID': 'NCJDK7KSJ6', 'support': 'If you have questions or need support, please email [email protected]'}

Solution: This error occurs when you have exhausted your free credits and need to add a payment method to continue using TimeGPT. You can add a payment method in the Billing section of your dashboard.

Solution: If you encounter a WriteTimeout error, it means that the request has exceeded the allowable processing time. This is a common issue when working with large datasets. To fix this, consider increasing the num_partitions parameter in the forecast method of the NixtlaClient class, or use a distributed backend if not already in use.