Vertex AI: Claude Sonnet 4.5 (Vertex)
stableClaude Sonnet 4.5 (Vertex) is available through Everstack's OpenAI-compatible gateway with routing, fallback, retries, and observability.
claude-sonnet-4-5@20250929claude-4released Sep 29, 2025
Context
200K
tokens
Max output
64K
tokens
Input
$3.00
per 1M
Output
$15.00
per 1M
Activity
Daily period usage
Aggregated managed Everstack traffic. Buckets below 5 tenants or 100 requests are withheld.
Providers
ProviderContextInput /MOutput /M
Pricing
| Item | Price | Unit |
|---|---|---|
| Input | $3.00 | per 1M tokens |
| Output | $15.00 | per 1M tokens |
| Cache read | $0.30 | per 1M tokens |
| Cache write | $3.75 | per 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-sonnet-4-5@20250929
- Family
- claude-4
- Status
- stable
- Knowledge
- -
- Released
- Sep 29, 2025
Gateway Config
- API
- v1
- Auth
- GOOGLE_APPLICATION_CREDENTIALS
- Discovery
- static
- Provider type
- static
Quick Start
index.ts
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/completionsModel
claude-sonnet-4-5@20250929Auth env
GOOGLE_APPLICATION_CREDENTIALSClaude Sonnet 4.5 (Vertex) FAQ
How much does the Claude Sonnet 4.5 (Vertex) API cost?
Through Vertex AI, Claude Sonnet 4.5 (Vertex) costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.
What is the context window of Claude Sonnet 4.5 (Vertex)?
Claude Sonnet 4.5 (Vertex) accepts up to 200K tokens of context and returns up to 64K output tokens on Vertex AI.
What can Claude Sonnet 4.5 (Vertex) do?
Claude Sonnet 4.5 (Vertex) supports chat, function calling, image input and reasoning. It accepts text, image and PDF input.
How do I call Claude Sonnet 4.5 (Vertex) through Everstack?
Point any OpenAI-compatible SDK at your Everstack gateway and set the model to @vertex-ai/claude-sonnet-4-5@20250929. Everstack adds retries, provider fallback, caching, per-tenant budgets and OpenTelemetry traces for every request.
