Releasesby IbisNew tutorial: Route Model Requests Across OCI Regions
Update10 days agoUnverifiedAdded Oct 18, 2026
A new tutorial for OCI Generative AI shows how to route on-demand model requests across OCI regions using a routing profile. Learn step by step how to select a model and its target serving regions, create a routing profile, and use the same profile in Python applications that call the Chat Completions and Responses API.
Topics: Streaming, Developer tools, Regions
More Oracle Cloud Infrastructure releases
Every Oracle Cloud Infrastructure releaseUpdated Certified Components for IAM E-Business Suite Asserter
Oracle Cloud Infrastructure (OCI) Identity and Access Management (IAM) has updated the certified components for E-Business Suite Asserter single sign-on (SSO) integration.
Introducing the Public Safety and Security Service and Oracle Radio
Oracle Public Safety and Security service is now generally available in these regions: US East (Ashburn) us-ashburn-1 US West (Phoenix) us-phoenix-1 This Oracle Cloud Infrastructure (OCI) service provides isolated environments for authorized teams to communicate using Oracle Radio mobile and browser applications.
Priority processing is now available for Grok 4.20 and Grok 4.3
Priority processing is now available for the following xAI Grok models in OCI Generative AI: Grok 4.20 Reasoning : xai.grok-4.20-0309-reasoning Grok 4.20 Non-Reasoning : xai.grok-4.20-0309-non-reasoning Grok 4.20 Multi-Agent : xai.grok-4.20-multi-agent-0309 Grok 4.3 : xai.grok-4.3 These models are available in on-demand mode.
Import Alibaba Qwen3.8-Flash-Next into OCI Generative AI
You can now import the Qwen/Qwen3.8-Flash-Next model into OCI Generative AI, create endpoints for it, and use it in the Generative AI service. In OCI Generative AI, use the following details for this model: Model capability: IMAGE_TEXT_TO_TEXT Minimum dedicated AI cluster unit shapes: H100_X8 and H200_X4 For the complete list of models that you can import...
Import Xiaomi MiMo V2.6 Pro RL into OCI Generative AI
You can now import the XiaomiMiMo/MiMo-V2.6-Pro-RL model into OCI Generative AI, create endpoints for it, and use it in the Generative AI service. In OCI Generative AI, use the following details for this model: Model capability: IMAGE_TEXT_TO_TEXT Minimum dedicated AI cluster unit shape: H200_X8 For the complete list of models that you can import, see...
Expanded hardware support for imported models in OCI Generative AI
OCI Generative AI model import now supports more hardware options for the following models. The following table lists the minimum dedicated AI cluster unit shape for each supported hardware family.
Import NVIDIA Nemotron 3 Ultra FP8 into OCI Generative AI
You can now import the RedHatAI/NVIDIA-Nemotron-3-Ultra-550B-A55B-FP8-dynamic model into OCI Generative AI, create endpoints for it, and use it in the Generative AI service.
Sign and verify model artifact signatures
OCI Data Science now offers model artifact signature and integrity verification. You can create a signature for a model artifact using an OCI Vault key and associate that signature with a model deployment. When creating a model deployment, select an available signature for the model artifact.
Also shipped on Oct 14, 2026
Oracle in October 2026Workspace-level package repositories for Databricks Apps are generally available
Workspace admins can now configure default Python and npm package repositories for Databricks Apps. Apps inherit the workspace configuration while still allowing app-level overrides. See Configure default package repositories .
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA)
The Apache Hive catalog endpoint in the Lakehouse runtime catalog is now generally available (GA). This integration lets you use the metastore as a serverless, central metadata layer, enabling seamless data sharing and unified querying across Apache Spark, Apache Hive, and BigQuery.
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA)
Metadata migration from Dataproc Metastore to Lakehouse is now generally available (GA). You can perform a one-time backfill migration or dry run to migrate metadata from a Dataproc Metastore service to an Apache Iceberg REST catalog endpoint or a Hive catalog endpoint using the Google Cloud console, the gcloud CLI, or the REST API.
Conversational analytics now lets you create a conversation with all of the data sources in multiple...
Conversational analytics now lets you create a conversation with all of the data sources in multiple projects, or create a conversation with a dataset . These features are generally available (GA).
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise
You can publish a BigQuery Conversational Analytics agent in Gemini Enterprise . This feature is now generally available (GA).
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the...
The AI.AGG function now supports the output_schema argument, which lets you specify the schema of the function output as a comma-separated list of fields. This feature is generally available (GA).