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