Crusoe Updates: September 2026

Track model and hardware releases, API changes, and feature launches.

Managed AI

September 12, 2026000114ModelsBreaking
Serverless Inference model deprecations
Z.ai GLM-5.1, Z.ai GLM-5.2, DeepSeek V3, Qwen3 235B A22B, and Llama 3.3 70B were deprecated for Serverless Inference on September 12, 2026. See Migrate from a deprecated model.
September 11, 2026000113Models
New model available: Qwen3.8-27B
Intelligence Foundry now supports Qwen's Qwen3.8-27B model. See available models for Serverless Inference, Serverless Fine-Tuning, and Self-Serve Deployments.
September 6, 2026000112Models
New models available: GLM-5.3 and GLM-5.3-Flash
Intelligence Foundry now supports Z.ai's GLM-5.3 and GLM-5.3-Flash models, both with a 1M-token context window. See Available models.

September 15, 2026000115Service updateBreaking
Crusoe CSI driver v0.4.11 and earlier deprecated
Crusoe CSI driver versions earlier than v0.4.12 are deprecated and will become unsupported after November 8, 2026. Clusters running in a private network without outbound internet access must upgrade before then. See Upgrade the Crusoe CSI driver.

September 1, 2026000111Feature update
Bug reports via API and CLI
You can now trigger, track, and download bug reports programmatically, in addition to generating them from the Console. Use the new crusoe diagnostics vm commands to collect diagnostics across many instances or from a script. See Diagnostics and the crusoe diagnostics CLI reference.