Claude on Vertex AI

The Vertex API for accessing Claude is nearly identical to the Messages API, with two key differences in request format:

• In Vertex, model is not passed in the request body. Instead, it is specified in the Google Cloud endpoint URL.
• In Vertex, anthropic_version is passed in the request body (rather than as a header), and must be set to the value vertex-2023-10-16.

Vertex is also supported by Anthropic's official client SDKs. This guide walks you through making a request to Claude on Vertex AI using one of Anthropic's client SDKs.

Note that this guide assumes you already have a GCP project that is able to use Vertex AI. See Anthropic Claude models on Vertex AI for more information on the setup required and a full walkthrough.

Install an SDK for accessing Vertex AI

First, install Anthropic's client SDK for your language of choice.

Accessing Vertex AI

Model availability

Note that Anthropic model availability varies by region. Search for "Claude" in the Vertex AI Model Garden or go to Anthropic Claude models for the latest information.

API model IDs

Lifecycle terms (Deprecated, Retired) are defined in Model deprecations. Lifecycle dates on partner-operated platforms are set by the partner and can differ from the Claude API schedule. For the current retirement date of any model on Vertex AI, see Google Cloud's documentation for Claude models on Vertex AI.

Making requests

Before running requests you may need to run gcloud auth application-default login to authenticate with GCP.

The following examples show how to generate text from Claude on Vertex AI:

from anthropic import AnthropicVertex

project_id = "MY_PROJECT_ID"
region = "global"

client = AnthropicVertex(project_id=project_id, region=region)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)

See the client SDKs and the official Vertex AI docs for more details.

Claude is also available through Amazon Bedrock, Claude Platform on AWS, and Microsoft Foundry.

Data retention

Data handling for this offering is governed by Google Cloud Vertex AI. For details, see Vertex AI and zero data retention.

Activity logging

Vertex provides a request-response logging service that allows customers to log the prompts and completions associated with your usage.

Anthropic recommends that you log your activity on at least a 30-day rolling basis in order to understand your activity and investigate any potential misuse.

Feature support

For the full feature list with Vertex AI availability, see Features overview.

Supported feature highlights

• Messages API
• Prompt caching
• Extended thinking
• Tool use, including the Bash tool, Computer use tool, Memory tool, and Text editor tool
• Web search tool
• Citations
• Structured outputs

Features not supported

• Input sources (URL sources for images and documents, Files API)
• Server-side tools (code execution, web fetch, advisor)
• Agent infrastructure (Agent Skills, MCP connector, programmatic tool calling)
• API endpoints (Message Batches, Models, Admin, Compliance, Usage and Cost)
• Claude Managed Agents
• Server-side fallback (the fallbacks parameter; use the client-side fallback pattern instead)

Context window

Claude Fable 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6 have a 1M-token context window on Vertex AI. Other Claude models, including Sonnet 4.5 and Sonnet 4 (deprecated), have a 200k-token context window.

Vertex AI limits request payloads to 30 MB. When sending large documents or many images, you may reach this limit before the token limit.

Global, multi-region, and regional endpoints

Vertex AI offers three endpoint types:

• Global endpoints: Dynamic routing for maximum availability
• Multi-region endpoints: Dynamic routing within a geographic area (for example, the United States or the European Union) for data residency with high availability
• Regional endpoints: Guaranteed data routing through specific geographic regions

Regional and multi-region endpoints include a 10% pricing premium over global endpoints.

When to use each option

Global endpoints (recommended):

• Provide maximum availability and uptime
• Dynamically route requests to regions with available capacity
• No pricing premium
• Best for applications where data residency is flexible
• Only supports pay-as-you-go traffic (provisioned throughput requires regional endpoints)

Multi-region endpoints:

• Dynamically route requests across regions within a geographic area (currently us and eu)
• Useful when you need data residency within a broad geography but want higher availability than a single region
• 10% pricing premium over global endpoints
• Only supports pay-as-you-go traffic (provisioned throughput requires regional endpoints)

Regional endpoints:

• Route traffic through specific geographic regions
• Required for single-region data residency, strict compliance mandates, or provisioned throughput
• Support both pay-as-you-go and provisioned throughput
• 10% pricing premium reflects infrastructure costs for dedicated regional capacity

Implementation

Using global endpoints (recommended):

Set the region parameter to "global" when initializing the client:

from anthropic import AnthropicVertex

project_id = "MY_PROJECT_ID"
region = "global"

client = AnthropicVertex(project_id=project_id, region=region)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)

Using multi-region endpoints:

Set the region parameter to a multi-region identifier: "us" for the United States or "eu" for the European Union. The SDK routes requests to the corresponding multi-region endpoint (https://aiplatform.us.rep.googleapis.com or https://aiplatform.eu.rep.googleapis.com), which dynamically balances traffic across regions within that geography.

from anthropic import AnthropicVertex

project_id = "MY_PROJECT_ID"
region = "us"  # Multi-region identifier: "us" or "eu"

client = AnthropicVertex(project_id=project_id, region=region)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)

Using regional endpoints:

Specify a specific region like "us-east1" or "europe-west1":

from anthropic import AnthropicVertex

project_id = "MY_PROJECT_ID"
region = "us-east1"  # Specify a specific region

client = AnthropicVertex(project_id=project_id, region=region)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)

Additional resources

• Vertex AI pricing: cloud.google.com/vertex-ai/generative-ai/pricing
• Claude models documentation: Claude on Vertex AI
• Google blog post: Global endpoint for Claude models
• Anthropic pricing details: Cloud platform pricing