All guides

Connect Anthropic Usage to Cloptima

Track and govern Anthropic usage with team attribution, model policies, and AI FinOps reporting in Cloptima.

6 min read Updated June 2026Connect your AI stack
On this page
  1. 01Point your Anthropic client at Cloptima
  2. 02The same endpoint also fronts non-Anthropic models
  3. 03Centralize access with BYOK
  4. 04Set policy boundaries
  5. 05Review spend trends

01

Point your Anthropic client at Cloptima

Set the Anthropic base URL to https://api.cloptima.ai (the client appends /v1/messages) and pass your Cloptima virtual key as the API key — it's sent as x-api-key. Add x-cloptima-* headers for attribution.

python
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.cloptima.ai",   # client calls /v1/messages
    api_key="clop_vk_dPXO67p…",              # sent as x-api-key
)

msg = client.messages.create(
    model="claude-sonnet-5-5",
    max_tokens=512,
    messages=[{"role": "user", "content": "..."}],
    extra_headers={"x-cloptima-team": "platform", "x-cloptima-app": "assistant"},
)

02

The same endpoint also fronts non-Anthropic models

Because Cloptima translates between protocols, the Anthropic surface isn't limited to Claude. Any tool that speaks the Anthropic Messages API can reach OpenAI, Gemini, or Bedrock models through the same governed key — see the Claude Code guide for a developer-friendly example.

03

Centralize access with BYOK

Use Cloptima BYOK and encrypted credential controls to keep your Anthropic key protected while developers use governed virtual keys bound to policy.

04

Set policy boundaries

Control model families, development limits, production budgets, and high-context usage for teams that depend on Anthropic models.

Put This Guide Into Practice

Cloptima automates the strategies described in this guide.

No credit card required
5-minute setup
Free trial