Claude on Vertex AI

The Vertex API for accessing Claude is nearly-identical to the Messages API and supports all of the same options, with two key differences:

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 using the Claude 3 models from Anthropic for more information on the setup required, as well as 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 Use Claude 3 for the latest information.

API model IDs

Model	Vertex AI API model ID
Claude Opus 4.6	claude-opus-4-6
Claude Sonnet 4.6	claude-sonnet-4-6
Claude Sonnet 4.5	claude-sonnet-4-5@20250929
Claude Sonnet 4	claude-sonnet-4@20250514
Claude Sonnet 3.7 ⚠️	claude-3-7-sonnet@20250219
Claude Opus 4.5	claude-opus-4-5@20251101
Claude Opus 4.1	claude-opus-4-1@20250805
Claude Opus 4	claude-opus-4@20250514
Claude Haiku 4.5	claude-haiku-4-5@20251001
Claude Haiku 3.5 ⚠️	claude-3-5-haiku@20241022
Claude Haiku 3 ⚠️

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:

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

Claude is also available through Amazon Bedrock and Microsoft Foundry.

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.

Turning on this service does not give Google or Anthropic any access to your content.

Feature support

For all currently supported features on Vertex AI, see API features overview.

Context window

Claude Opus 4.6, Sonnet 4.6, Sonnet 4.5, and Sonnet 4 have a 1M-token context window on Vertex AI.

For Claude Sonnet 4.5 and Sonnet 4, the 1M-token context window is in beta. To use, include the context-1m-2025-08-07 beta header in your API requests.

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 vs regional endpoints

Starting with Claude Sonnet 4.5 and all future models, Google Vertex AI offers two endpoint types:

Global endpoints: Dynamic routing for maximum availability
Regional endpoints: Guaranteed data routing through specific geographic regions

Regional endpoints include a 10% pricing premium over global endpoints.

This applies to Claude Sonnet 4.5 and future models only. Older models (Claude Sonnet 4, Opus 4, and earlier) maintain their existing pricing structures.

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)

Regional endpoints:

Route traffic through specific geographic regions
Required for data residency and compliance requirements
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:

Using regional endpoints:

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

Additional resources

Google 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: Pricing documentation

MODEL_ID=claude-opus-4-6
LOCATION=global
PROJECT_ID=MY_PROJECT_ID

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://$LOCATION-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/anthropic/models/${MODEL_ID}:streamRawPredict -d \
'{
  "anthropic_version": "vertex-2023-10-16",
  "messages": [{
    "role": "user",
    "content": "Hey Claude!"
  }],
  "max_tokens": 100,
}'

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-4-6",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)

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-4-6",
    max_tokens=100,
    messages=[
        {
            "role": "user",
            "content": "Hey Claude!",
        }
    ],
)
print(message)