API setup
guide

Setup steps

1. Create your account. Sign in with email, Google, or GitHub and complete any required email verification.
2. Create an API key. Use a separate key for each application and keep it private.
3. Configure your client. Enter the base URL, your VM API key, and the exact model ID.
4. Verify the connection. Use a model enabled for your account, then review the response, usage and charges in Usage & logs.

View connection settings

Client settings

In a desktop chat client, choose a provider option that supports a custom endpoint. Your client and the selected model must use the same API format. Compatibility can vary by client and feature.

The current API uses Anthropic Messages. Other protocols and model quotes in the directory are reference information; confirm support before integrating them.

Modelclaude-sonnet-5-5claude-opus-5-5claude-haiku-5-5API formatAnthropic MessagesProgramming languagePythonJavaScript (Node.js)cURL (bash)

Claudeclaude-haiku-5-5

Anthropic Messages

VM standard rates

USD / 1M tokens · Total input ≤ 100K

Input$0.03

Output$0.15

Cache read$0.003

Cache write$0.036

Long context · Total input > 100K

Input$0.15

Output$0.75

Cache read$0.015

Cache write—

Contact support for long-context usage types without a listed rate.

Model source details

QC reference prices · not VimuRoute prices

USD / 1M Token: Input: $0.10 · Output: $0.50 · Cache write: $0.12 · Cache read: $0.01

Above 100K prompt tokens (including cache writes and cache hits): Input: $0.50 · Output: $2.50 · Cache read: $0.05

QC applies a 5× multiplier to the whole request, including cache reads and writes.

QC context / maximum output: 1M / 128K

QC directory · checked November 4, 2026

View model informationOpen console Copy setup guide link

Replace the example endpoint and key with your account settings. Check the selected model and API permissions in the console.

Idempotency-Key is an optional UUID header. Reuse it when retrying the same operation; the server generates one if omitted. SDK examples disable automatic retries.

from uuid import uuid4
from anthropic import Anthropic

client = Anthropic(
    base_url="https://vimuroute.com",
    api_key="YOUR_VM_API_KEY",
    max_retries=0
)
request_id = str(uuid4())
response = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello!"}],
    extra_headers={"Idempotency-Key": request_id}
)
print(response.content[0].text)

Run this example on your computer or server. Keep real API keys out of public browser code.

Troubleshooting

Read the credit and billing rules

Setup help

Use these self-service links for account access, email verification, password recovery, and setup information.

support@vimuroute.com