nixtla
Python SDK for Nixtla API (TimeGPT)
Decision gist · record as of 2026-08-14
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.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- 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.
- Low install friction with a pure Python wheel and nine runtime dependencies.
License · maintenance · safety
Apache Software License 2.0 (permissive) — Licensed under Apache Software License 2.0 (permissive), allowing commercial use, modification, and distribution with minimal restrictions.
last release 2026-07-21 (24 days) · last repo commit 2026-08-14 · 3,987 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 125,589 downloads/mo, #11,808 on PyPI
Alternatives
Verify before relying
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)- 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.
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 on this page. Verify before relying on it.
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
nixtla on PyPI
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.
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.
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)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 the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 9 packagesannotated-typeshttpxnarwhalsorjsonpandaspydantictenacitytqdmutilsforecast |
| Maintenance | Actively maintained 24 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 125,589 / month, #11,808 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 4 - BetaIntended Audience :: DevelopersLicense :: OSI Approved :: Apache Software LicenseNatural Language :: EnglishProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13 |
Evidence: nixtla-0.8.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “time series forecasting API”
- nixtlaPython SDK for accessing TimeGPT, a foundation model for time series…
- sktimesktime provides a unified interface for time series machine learning…
- timesfmTimesFM is a pretrained time-series foundation model from Google…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also neuralforecast · sktime · statsforecast · timesfm · coreforecast · adtk · chronos-forecasting · tbats · asknews · anomalo