跳到正文- Source: Web search tool (OpenAI guide)
- Source: Vertex AI RAG Engine — Overview and Transformations
- Source: Vertex AI Model Garden — Explore Models
- Source: Vertex AI — VPC Service Controls
- Source: Vertex AI — Standard PayGo and Usage Tiers
- Source: Vertex AI — Provisioned Throughput (Overview and GSU Sizing)
- Source: Vertex AI — Generative AI Locations and Endpoints
- Source: Vertex AI — Generative AI and Data Governance
- Source: Vertex AI — Consumption Options
- Source: Vercel Connect guide and EMA changelog
- Source: Vercel AI Gateway docs (overview, model fallbacks, budgets)
- Source: Timeouts, retries, and backoff with jitter (Amazon Builders' Library)
- Source: Server tools (Claude docs)
- Source: Security Affairs: CISA adds LiteLLM CVE-2026-42271 to KEV
- Source: Security Affairs: CISA adds LiteLLM CVE-2026-42208 to KEV
- Source: RouterBench, a benchmark for multi-LLM routing (Hu et al., 2024)
- Source: RouteLLM, an open-source framework for cost-effective LLM routing (LMSYS blog)
- Source: Portkey AI Gateway docs (fallbacks, retries, simple and semantic cache)
- Source: OpenRouter provider routing and model fallbacks docs
- Source: OpenRouter FAQ (fees, BYOK, free-model limits)
- Source: OpenRouter Auto Router docs
- Source: OpenAI SDK compatibility (Claude docs)
- Source: OpenAI compatibility (Gemini API docs)
- Source: OpenAI — Scale Tier and Reserved Tier pages
- Source: OpenAI — Rate limits guide
- Source: OpenAI — Flex processing guide
- Source: OpenAI — Fast mode (formerly priority processing)
- Source: Migrate to the Responses API (OpenAI guide)
- Source: Microsoft Foundry — What Is Microsoft Foundry?
- Source: Microsoft Foundry — Provisioned throughput billing and cost management
- Source: Microsoft Foundry — Provisioned Throughput (PTU)
- Source: Microsoft Foundry — Guardrails and Controls Overview
- Source: Microsoft Foundry — Foundry Models Overview
- Source: Microsoft Foundry — Determine PTU sizing for a workload
- Source: Microsoft Foundry — Deployment Types
- Source: Microsoft Foundry — Data, Privacy and Security for Models Sold by Azure
- Source: Microsoft Foundry — Configure Network Isolation
- Source: Microsoft Foundry — Azure OpenAI Quotas and Limits
- Source: Microsoft Foundry — Agent Service Overview
- Source: LiteLLM security update, suspected supply-chain incident (March 2026)
- Source: LiteLLM Router docs (routing, retries, fallbacks, cooldowns)
- Source: LiteLLM proxy (AI Gateway) docs: overview, virtual keys, caching
- Source: LiteLLM GitHub security advisories list
- Source: LiteLLM GitHub repository README
- Source: LiteLLM docs: getting started, input params, proxy config.yaml
- Source: LiteLLM docs: callbacks, custom callbacks, proxy logging
- Source: LiteLLM docs: budgets and rate limits (proxy users, teams, keys)
- Source: LiteLLM blog: CVE-2026-42208, SQL injection in LiteLLM Proxy
- Source: Kong AI Gateway docs and AI Proxy Advanced plugin
- Source: Interactions API (Gemini API docs)
- Source: Hybrid LLM, cost-efficient and quality-aware query routing (Ding et al., ICLR 2024)
- Source: Gemini Enterprise Agent Platform — Release Notes (2026)
- Source: Gemini Enterprise Agent Platform — Agent Runtime Overview (formerly Vertex AI Agent Engine)
- Source: Gemini API — Rate limits
- Source: GCP Services & IaC (Notebook)
- Source: Files API (Gemini API docs)
- Source: Files API (Claude docs)
- Source: File search tool (OpenAI guide)
- Source: File Search (Gemini API docs)
- Source: Exponential Backoff and Jitter (AWS Architecture Blog)
- Source: Envoy AI Gateway v1.0 release notes (now Agent Router)
- Source: Conversation state (OpenAI guide)
- Source: Compaction (OpenAI guide)
- Source: Cloudflare AI Gateway docs (features, caching, request handling)
- Source: Cloud Security Alliance research note on LiteLLM CVE-2026-42208
- Source: Claude API overview
- Source: Background mode (OpenAI guide)
- Source: AWS Services Field Guide (Notebook)
- Source: API versions (Claude docs)
- Source: Anthropic API rate limits docs
- Source: Anthropic — Service tiers (Priority Tier)
- Source: Anthropic — Claude API errors
- Source: Amazon Bedrock AgentCore Identity docs
- Source: Amazon Bedrock AgentCore — Overview
- Source: Amazon Bedrock AgentCore — How Runtime Works
- Source: Amazon Bedrock — Service Tiers
- Source: Amazon Bedrock — Provisioned Throughput
- Source: Amazon Bedrock — Overview (User Guide)
- Source: Amazon Bedrock — Knowledge Bases
- Source: Amazon Bedrock — How Tokens Are Counted Against Quotas
- Source: Amazon Bedrock — Guardrails
- Source: Amazon Bedrock — Data Protection and VPC/PrivateLink
- Source: Amazon Bedrock — Cross-Region Inference
- Source: Amazon Bedrock — Agents (Classic)
- Rate Limits and Retries
- Provisioned Throughput
- OpenAI Responses API
- Model Routing and Fallbacks
- LLM Gateways
- LiteLLM
- Google Vertex AI
- Gemini API
- Azure AI Foundry
- Anthropic Messages API
- Amazon Bedrock