---
id: nixtla
version: "0.8.0"
license: Apache Software License 2.0
license_treatment: permissive
maintenance: active
---

# nixtla — Python SDK for Nixtla API (TimeGPT)

License: permissive · Maintenance: active · Downloads: 125.6K/mo

## What it is and what it does

Nixtla is a Python client for TimeGPT, a transformer-based foundation model trained specifically for time series analysis. It provides a low-code interface to forecast future values and detect anomalies in time series data across domains like retail, electricity, finance, and IoT. The package wraps an external API, so you instantiate a client with an API key, pass your data as a pandas DataFrame, and call methods like `forecast()` or `detect_anomalies()` to get results.

The model works zero-shot—it requires no prior training on your specific data—and supports fine-tuning, exogenous variables, prediction intervals, cross-validation, and irregular timestamps. It depends on pandas for data handling, pydantic for configuration, httpx for HTTP calls, tenacity for retry logic, and several utility packages. The package also supports Snowflake deployment via optional extras.

Use it for:

- Forecast electricity demand or retail sales for the next 24 hours with confidence intervals.
- Detect anomalies in IoT sensor streams or financial time series without labeled training data.
- Fine-tune TimeGPT on domain-specific historical data to improve accuracy for your particular use case.
- Integrate forecasting into a web application via the Python SDK without building a custom model.
- Run forecasting directly in Snowflake using stored procedures without exporting data.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Python SDK for accessing TimeGPT, a foundation model for time series forecasting and anomaly detection via API.

Yes, if you need time series forecasting or anomaly detection and have access to an API key. The low install friction, active maintenance, permissive license, and zero-shot capability make it a practical choice for rapid prototyping. The external API dependency and lack of offline capability are trade-offs; verify cost and rate limits before production use.

## Install

pip install nixtla
uv add nixtla
poetry add nixtla

## Installing nixtla

Before you install: Low install friction with a pure Python wheel and nine runtime dependencies. The project is actively maintained with recent releases and 3987 GitHub stars, indicating stable ongoing development.

License in practice: Licensed under Apache Software License 2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions.

Quickstart:

pip install nixtla>=0.7.0

import pandas as pd
from nixtla import NixtlaClient

nixtla_client = NixtlaClient(api_key='YOUR_API_KEY')
df = pd.read_csv('your_timeseries.csv')
fcst_df = nixtla_client.forecast(df, h=24)

Requires a valid API key from Nixtla (available via free trial at nixtla.io). The package cannot function offline without access to the TimeGPT API.

Verify before relying:

- Whether the API key requirement and external service dependency impose practical limitations for offline or air-gapped deployments.
- Performance characteristics and latency expectations when calling the remote TimeGPT API.
- Cost structure and rate limits for API usage beyond the free trial tier.

## Package facts

- License: Apache Software License 2.0 (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 125.6K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

time series forecasting API, anomaly detection in time series, foundation model for forecasting, TimeGPT Python client, zero-shot time series prediction, time-series, forecasting, api-client

[View on SkillFed](https://skillfed.io/packages/nixtla) · [View on PyPI](https://pypi.org/project/nixtla/)