Nixtla logo

Nixtla

Foundation model (TimeGPT) and open-source library for time-series forecasting and anomaly detection in just a few lines of code.

-
US Est. 2021 Active AI API / SDK for Developers

Our Verdict

Best forecasting toolkit if you have thousands of series and want zero-shot TimeGPT plus solid OSS fallbacks.

Pros

  • TimeGPT foundation model for zero-shot forecasting
  • Open-source StatsForecast and NeuralForecast libs
  • Handles millions of series efficiently
  • Anomaly detection built into the API

Cons

  • Closed TimeGPT API separate from OSS libraries
  • Forecast quality varies by domain
  • Needs careful feature engineering for edge cases
  • Pricing opaque for high-volume workloads
Best for: Data science teams with large-scale time-series workloads Not for: Single-series forecasts solvable with Prophet or ARIMA locally

When to Use Nixtla

Good fit if you need

  • Running zero-shot time-series forecasting with TimeGPT API
  • Generating demand forecasts without training a custom model
  • Fine-tuning TimeGPT on domain-specific time-series data
  • Forecasting energy, retail, or financial metrics at API scale

Lock-in Assessment

Low 4/5
Lock-in Score
4/5

Nixtla Pricing

Pricing Model
freemium
Free Tier
Yes
Entry Price
Enterprise Available
No
Transparency Score

Beta — estimates may differ from actual pricing

1,000
1001K10K100K1M

Estimated Monthly Cost

$25

Estimated Annual Cost

$300

Estimates are approximate and may not reflect current pricing. Always check the official pricing page.

Project Health

A

Health Score

3.9k 323
Bus Factor

10

Last Commit

today

Release Freq

33d

Open Issues

67

Issue Response

N/A

License

NOASSERTION

Last checked: 2026-04-21

Community Discussion

Comments powered by Giscus (GitHub Discussions). You need a GitHub account to comment.