Vertex AI

Vertex AI: Claude Opus 5 (Vertex)

stable

Claude Opus 5 (Vertex) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.

claude-opus-5@defaultclaude-opusreleased Jul 24, 2026
ProviderQuick start
Context
1M
tokens
Max output
128K
tokens
Input
$5.00
per 1M
Output
$25.00
per 1M

Activity

Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.

Providers

ProviderContextInput /MOutput /M
Anthropic
Anthropic
1M$5.00$25.00
AWS Bedrock
AWS Bedrock
1M$5.00$25.00
OpenRouter
OpenRouter
1M$5.00$25.00
Vertex AI
Vertex AI
1M$5.00$25.00

Pricing

ItemPriceUnit
Input$5.00per 1M tokens
Output$25.00per 1M tokens
Cache read$0.50per 1M tokens
Cache write$6.25per 1M tokens

Performance

Reliability

Compare

Compare usage and performance
Place this model beside up to three other catalog models.

Capabilities

Capabilities
Modalities
Input
Output
Details
Model ID
claude-opus-5@default
Family
claude-opus
Status
stable
Knowledge
May 1, 2026
Released
Jul 24, 2026
Gateway Config
API
v1
Auth
GOOGLE_APPLICATION_CREDENTIALS
Discovery
static
Provider type
static

Quick Start

index.ts
import Everstack from "@everstack/node";const client = new Everstack({  apiKey: process.env.EVERSTACK_API_KEY!,  baseUrl: "https://{instance}.{region}.everstack.ai",});const completion = await client.chat.completions.create({  model: "@vertex-ai/claude-opus-5@default",  messages: [{ role: "user", content: "Explain vector cache routing." }],});console.log(completion.choices[0]?.message?.content);

Endpoint

Base URL
https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}
Chat completions
https://{location}-aiplatform.googleapis.com/v1/projects/{project}/locations/{location}/chat/completions
Model
claude-opus-5@default
Auth env
GOOGLE_APPLICATION_CREDENTIALS

Claude Opus 5 (Vertex) FAQ

How much does the Claude Opus 5 (Vertex) API cost?

Through Vertex AI, Claude Opus 5 (Vertex) costs $5.00 per 1M input tokens and $25.00 per 1M output tokens.

What is the context window of Claude Opus 5 (Vertex)?

Claude Opus 5 (Vertex) accepts up to 1M tokens of context and returns up to 128K output tokens on Vertex AI.

Which providers offer Claude Opus 5 (Vertex)?

Claude Opus 5 (Vertex) is available from Anthropic, AWS Bedrock, OpenRouter and Vertex AI. Everstack can route between them with automatic fallback when one is unavailable.

What can Claude Opus 5 (Vertex) do?

Claude Opus 5 (Vertex) supports chat, function calling, image input and reasoning. It accepts text, image and PDF input.

How do I call Claude Opus 5 (Vertex) through Everstack?

Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @vertex-ai/claude-opus-5@default. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.