Google Vertex AI

Anthropic provides model access through its own API platform and cloud service channels such as Amazon Bedrock and Google Cloud Vertex AI

在Hugging Face、OpenAI API、Google Vertex AI等平台成熟后，调用高性能预训练模型的门槛已降至只需几行Python代码

The default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.

The default models for multiple providers were switched to Claude Haiku 5.5, including Google Vertex AI (changed from Claude Sonnet 5.5 to Claude Haiku 5.5), Cortecs, DevPass, Eden AI, GitHub Copilot, LLM Gateway, NanoGPT, OpenCode Go, Requesty, and Vivgrid.

The mainstream cloud platforms AWS SageMaker, Google Vertex AI, and Azure ML all provide managed pipelines from training to deployment.

For teams already running Claude Code on Bedrock or Vertex, they can enable Monitor capabilities without migrating to the official API.

Before version 2.1.310, the Monitor tool was unavailable on Amazon Bedrock, Google Vertex AI, and Azure AI Foundry.

Configuring Monitor on Vertex and Foundry relies on the access control systems of Google Cloud and Azure, respectively.

Under the cloud platform access model, some new features often launch first on Anthropic's official API and are then gradually adapted to each cloud platform, so there is a time lag in feature availability.

Third-party platforms were less affected by the incorrect routing: on Amazon Bedrock, misrouted traffic peaked at 0.18% of all Sonnet 4 requests; on Google Vertex AI, fewer than 0.0004% of requests were affected between August 27 and September 16, 2025.

Cline itself does not train models, but acts as a client forwarding requests to various providers (such as OpenRouter, GitHub Copilot, Google Vertex AI, DigitalOcean, etc.).

The default models of providers including 302.AI, Cortecs, CrossModel, DevPass, DigitalOcean, Eden AI, GitHub Copilot, Google Vertex AI, LLM Gateway, Meta, Moark, NanoGPT, NEAR AI Cloud, Neuralwatt, Novita AI, Ofox, OpenCode Go, Requesty, and Vivgrid have changed, with most switching to Claude Haiku 5.5 or Muse Wonder 1.0.

The Claude apps gateway is an intermediary proxy layer provided by Anthropic for enterprise customers, responsible for routing Claude Code requests to cloud upstreams such as AWS Bedrock, Google Vertex AI, and Azure AI Foundry, while uniformly handling authentication, rate limiting, failover, and auditing.

Supporting 500+ models typically means the tool achieves broad model access through compatibility with the OpenAI API standard, Anthropic API, Google Vertex AI, and local inference frameworks such as Ollama.

If data sovereignty and cost control are the top priorities, self-hosted open-source solutions such as LiteLLM should be chosen; for out-of-the-box usability and broad model coverage, OpenRouter or Together AI should be chosen; large enterprises requiring compliance and stability should choose Bedrock or Vertex AI.

Google Vertex AI supports multi-model integration and provides CMEK (Customer-Managed Encryption Keys), VPC Service Controls, and Data Residency guarantees.

Claude Code version 2.1.310 extends the Monitor tool and plugin monitoring capability to Amazon Bedrock, Google Vertex AI, and Azure AI Foundry.

The focus of this round of Google Vertex AI updates is introducing more large language models (LLMs) and diffusion models, giving developers greater freedom of combination and thereby covering richer multimodal scenarios.