Changelog
See our latest feature releases, product improvements and bug fixes
Introducing the Baseten Delivery Network (BDN)
We just launched the Baseten Delivery Network (BDN), designed to make cold starts 2-3x faster for large models.
Mar 16, 2026Regional environments
Route inference traffic exclusively within a designated geographic region to meet data residency and compliance requirements like GDPR.
Mar 13, 2026CI/CD for model deployments
Automate Truss deployments with the Truss Push Action. Deploy on merge, validate on pull request, or deploy multiple models in parallel.
Mar 7, 2026Truss 0.15.2
Added --no-cache flag to truss push to force a full rebuild without using cached Docker layers. This is useful when debugging build issues or ensuring a clean image. The flag is CLI-only and cannot...
Mar 6, 2026Environment-scoped API keys
You can now restrict API keys to specific environments and models, giving you more control over how your team accesses Baseten resources.
Mar 4, 2026Truss support for pyproject.toml and uv.lock
Truss now supports pyproject.toml and uv.lock as dependency formats in addition to requirements.txt. You can use any of these formats as the requirements_file in your Truss and Chains config. For...
Mar 4, 2026Retrieve billing usage via API
You can now query your billing usage programmatically using the new GET /v1/billing/usage_summary endpoint. Pass a date range of up to 31 days to get a breakdown of costs across Dedicated Inference,...
Mar 2, 2026Deployment labels on push
You can now attach labels to deployments at push time using the --labels flag. Labels are key-value pairs passed as a JSON string that are stored with the deployment.
Feb 26, 2026Truss upgrades and rollbacks
Truss can now upgrade itself directly from the CLI. Use the new truss upgrade command to update to the latest version. Truss will detect your package manager (supports uv, pip, pipx, and anaconda)...
Feb 25, 2026Monitor concurrent inference requests
Track the number of in-progress inference requests across your deployments, including both requests currently being serviced and those waiting in the queue. This is the key indicator used to drive...