← ← Back to all products
Keras
Active
Frameworks Latest Version: 3.14.1 Latest Release: May 7, 2026
Keras is a high-level multi-backend deep learning API (Keras 3) running on JAX, TensorFlow, PyTorch or OpenVINO. Only the latest minor is maintained. Keras 3.x requires Python 3.11+ and needs one backend installed; GPU/CUDA support comes from the chosen backend.
Versions
10
Latest Version
3.14.1
Active Support
1
EOL
9
Lifecycle Timeline
Today ↓
3.14
3.14
3.13
3.13
3.12
3.12
3.11
3.11
3.10
3.10
3.9
3.9
3.8
3.8
3.7
3.7
3.6
3.6
3.5
3.5
Active SupportSecurity SupportEOL
Versions
| Release | Release Date | Active Support | EOL | Latest Version | LTS | Status |
|---|---|---|---|---|---|---|
| 3.14 | Apr 3, 2026 | Yes | No | 3.14.1 | No | Active |
| 3.13 | Dec 17, 2025 | No | Yes | 3.13.2 | No | EOL |
| 3.12 | Oct 27, 2025 | No | Yes | 3.12.2 | No | EOL |
| 3.11 | Jul 30, 2025 | No | Yes | 3.11.3 | No | EOL |
| 3.10 | May 20, 2025 | No | Yes | 3.10.0 | No | EOL |
| 3.9 | Mar 4, 2025 | No | Yes | 3.9.2 | No | EOL |
| 3.8 | Jan 7, 2025 | No | Yes | 3.8.0 | No | EOL |
| 3.7 | Nov 25, 2024 | No | Yes | 3.7.0 | No | EOL |
| 3.6 | Oct 3, 2024 | No | Yes | 3.6.0 | No | EOL |
| 3.5 | Aug 12, 2024 | No | Yes | 3.5.0 | No | EOL |
Frequently Asked Questions
Which versions of Keras have reached end of life?
The following Keras versions have reached end of life and no longer receive security updates: 3.13, 3.12, 3.11, 3.10, 3.9, 3.8, 3.7, 3.6 (and 1 more). It is recommended to upgrade to a supported version.
Is it safe to continue using Keras 3.13?
Keras 3.13 has reached end of life and no longer receives security patches or bug fixes. Continuing to use it may expose your systems to known vulnerabilities. We strongly recommend upgrading to a supported version.
What is the latest version of Keras?
The latest version of Keras is 3.14.1, released in the 3.14 release cycle.
How many versions of Keras are currently supported?
Keras currently has 1 actively supported version(s): 3.14.
When does Keras 3.14 reach end of life?
Keras 3.14 does not have a specific end-of-life date announced yet.
What should I do when Keras reaches end of life?
When a Keras version reaches end of life, you should: 1) Plan your migration to a supported version as soon as possible. 2) Review the release notes for breaking changes. 3) Test your applications thoroughly in a staging environment. 4) Update your dependencies to ensure compatibility with the new version.