"Inference Engineering" is now available. Get your copy here

Changelog

See our latest feature releases, product improvements and bug fixes

Feb 26, 2026

Truss 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, 2026

Monitor 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...

Feb 25, 2026

OIDC authentication support

Eliminate the need for long-lived cloud IAM credentials in your Baseten deployments. Supports AWS S3 and ECR, and Google Cloud Storage and Artifact Registry using short-lived tokens scoped to a...

Feb 21, 2026

Model API Deprecation Notice (Kimi K2 0905, Kimi K2 Thinking, DeepSeek v3.2)

The Kimi K2 0905, Kimi K2 Thinking and DeepSeek v3.2 Model API(s) will be deprecated at 5pm PT March 6th.

Feb 20, 2026

Updates to truss push in 0.14.0

In truss 0.14.0 the default behavior for truss push and truss chains push deploys a published deployment.

Feb 20, 2026

GLM 5 available on Baseten

GLM 5 takes the intelligence from its predecessors and layers in long-horizon agentic capabilities and complex systems engineering. You can deploy GLM 5 in one click with our Model APIs; dedicated...

Feb 18, 2026

Minimax M2.5 available on Baseten

MiniMax's new frontier agentic model M2.5 is now available on Baseten.

Feb 8, 2026

Action Required: Upgrade to Truss 0.13.3

Due to a change in downstream dependencies, some Truss configurations are failing to deploy on versions older than 0.13.3. We've resolved these issues in 0.13.3 with additional dependency pinning.

Feb 7, 2026

Model API Deprecation (Qwen3 Coder 480B A35B Instruct)

The Qwen3 Coder Model API was deprecated at 5pm PT February 6th. The model ID is currently inactive and will return an error for all requests.

Jan 27, 2026

Model API Deprecation Notice (Qwen3 Coder 480B A35B Instruct)

The Qwen3 Coder Model API will be deprecated at 5pm PT February 6th.