惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

I
InfoQ
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
Apple Machine Learning Research
Apple Machine Learning Research
月光博客
月光博客
B
Blog
罗磊的独立博客
GbyAI
GbyAI
博客园 - 三生石上(FineUI控件)
雷峰网
雷峰网
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
Microsoft Security Blog
Microsoft Security Blog
宝玉的分享
宝玉的分享
The GitHub Blog
The GitHub Blog
人人都是产品经理
人人都是产品经理
博客园 - Franky
有赞技术团队
有赞技术团队
WordPress大学
WordPress大学
博客园 - 聂微东
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
V
Visual Studio Blog
MyScale Blog
MyScale Blog
Google DeepMind News
Google DeepMind News
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Oracle Cloud Just Made LiteLLM a Native Provider for OCI ...
Paul Twist · 2026-06-26 · via DEV Community
Cover image for Oracle Cloud Just Made LiteLLM a Native Provider for OCI Generative AI

Paul Twist

Oracle Cloud announced this week that LiteLLM is now a first-class provider for Oracle Generative AI Infrastructure. Not a community plugin, not a third-party wrapper. Native support.

Original announcement from Oracle Cloud on LinkedIn

What this actually means

You can now route requests to models hosted on Oracle's Generative AI Infrastructure through LiteLLM. The gateway handles OCI Signature v1 request signing and all the production controls you'd expect, budgets, rate limits, caching, guardrails.

The model catalog on OCI is broader than most people realize:

  • Meta Llama 4 (Maverick, Scout, 3.3, 3.2 vision)
  • xAI Grok (Grok 4, Grok 3, Grok Code)
  • Cohere Command (Command A, Command R+)
  • Cohere Embed (v4, v3)
  • Google Gemini (via OCI)
  • OpenAI models (via OCI)

So if you're running on OCI already, you don't need a separate model gateway. Point LiteLLM at your OCI tenancy and go.

Quick setup

model_list:
  - model_name: grok-4
    litellm_params:
      model: oci_genai/xai.grok-4
      oci_config_path: /path/to/oci/config

import litellm

response = litellm.completion(
    model="oci_genai/xai.grok-4",
    messages=[{"role": "user", "content": "explain OCI networking"}]
)

That's it. LiteLLM handles the OCI auth signing, retries, and all gateway features automatically.

Why this matters

Oracle joining as a native provider brings LiteLLM's supported provider count past 100. But the real value is for teams already on OCI. Instead of building custom integrations for each model family Oracle hosts, you get a single OpenAI-compatible API with full spend tracking and access controls.

The architecture is clean. Application code talks to LiteLLM, LiteLLM handles vendor adapters and request signing, Oracle handles inference. No middleware, no extra hops.

Full OCI provider docs


Oracle is the latest in a streak of cloud providers building native LiteLLM integrations. AWS did the same thing with Bedrock AgentCore earlier this month, and Cisco integrated AI Defense as a guardrail layer. The pattern is clear, these teams want a unified gateway that already has the enterprise controls built in, rather than building their own.