Using Claude Opus 4.6 on GCP Vertex AI

Implementation guide · Claude 4.6 · Anthropic

Serverless

GCP Vertex AI exposes Claude Opus 4.6 through model ID claude-opus-4-6. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-07-26. Next refresh: weekly.

Quick Start

1
Create an account at GCP Vertex AI and generate an API key.
2
Use the GCP Vertex AI SDK or REST API to call claude-opus-4-6 — see the documentation for request format.
3
You'll be billed $15.00/1M input, $75.00/1M output tokens. See full pricing.

API Portal Documentation Pricing

Code Examples

Install

pip install google-cloud-aiplatform

API key

GOOGLE_CLOUD_PROJECT

Model ID

claude-opus-4-6

For Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".

import os
import vertexai
from vertexai.generative_models import GenerativeModel

# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("claude-opus-4-6")
response = model.generate_content("Hello")
print(response.text)

Pricing on GCP Vertex AI

Type	Price (per 1M)
Input tokens	$15.00
Output tokens	$75.00

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsCode Execution

About Claude Opus 4.6

Claude Opus 4.6 is Anthropic's Claude 4.6 model with multimodal text and image input and an optional reasoning mode. It offers a 1M-token context window and scores 80.8 on SWE-bench Verified.

Full model details →

Model Specs

Released2026-02-05

Context1m

ArchitectureDecoder Only

Knowledge cutoff2025-12

Google Cloud Platform (GCP)

Mountain View, California, United States