Gemini Enterprise Agent Platform adds throughput for fine-tuned models
aigcppreviewengineer
feature
The Gemini Enterprise Agent Platform now supports Provisioned Throughput for supervised fine-tuned Gemini 3 model inference. This feature allows users to guarantee inference capacity for these fine-tuned models, which consume more resources than base models. This update is relevant for users leveraging fine-tuned Gemini 3 models for their agent applications.
Features (1) ›
- Gemini Enterprise Agent Platform Provisioned Throughput support for supervised fine-tuned Gemini 3 model inference.
Provisioned Throughput support for supervised fine-tuned Gemini 3 model inference. Provisioned Throughput can be used to assure supervised fine-tuned inference using the same quota. Supervised fine-tuned inference for Gemini 3 models incurs a higher burndown rate compared to base model inference. Learn more here .
Read the original announcement →
https://docs.cloud.google.com/release-notes#June_22_2026
Related releases
- Cloud Load Balancing: Global External Passthrough Network Load Balancer Preview Google Cloud release notes ·
- Google Cloud Managed Service for Apache Kafka: Synthetic Data Generation Google Cloud release notes ·
- Dataflow batch jobs can now be paused on failure Google Cloud release notes ·
- Config Connector 1.154.1 Adds New Alpha Resources and Field Support Google Cloud release notes ·
- Security Command Center: Data Residency & Agent Vulnerability Scanning Preview Google Cloud release notes ·
- Cloud SQL for PostgreSQL: Private Service Connect changes August 2026 Google Cloud release notes ·