Anthropic

Sentisec speaks the Anthropic Messages API natively. Any client that sends POST /v1/messages — Claude Code, the Anthropic Python and TypeScript SDKs, your own client — points at Sentisec with a base-URL change and no code change.

Model ids beginning claude- route to Anthropic automatically, so there is nothing else to configure.

Setup

export ANTHROPIC_BASE_URL=https://api.sentisec.ch/ws/<your-workspace-id>
export ANTHROPIC_API_KEY=$SENTISEC_API_KEY

Note there is no /v1 on the Anthropic-shaped base URL — the SDKs append it themselves.

First call

curl -X POST https://api.sentisec.ch/ws/<your-workspace-id>/v1/messages \
  -H "Authorization: Bearer $SENTISEC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "hi"}]
  }'

You get back the standard Anthropic Messages body. The session appears under Sessions in the dashboard.

Claude Code

export ANTHROPIC_BASE_URL=https://api.sentisec.ch/ws/<your-workspace-id>
export ANTHROPIC_API_KEY=$SENTISEC_API_KEY
claude  # the CLI now runs through Sentisec — no other changes

Using Claude Code on a subscription rather than an API key? You do not need an Anthropic key at all — see subscription mode.

Anthropic SDKs

import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.sentisec.ch/ws/<your-workspace-id>",
    api_key=os.environ["SENTISEC_API_KEY"],
)

resp = client.messages.create(
    model="claude-sonnet-4",
    max_tokens=256,
    messages=[{"role": "user", "content": "hi"}],
)

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: "https://api.sentisec.ch/ws/<your-workspace-id>",
  apiKey: process.env.SENTISEC_API_KEY!,
});

const resp = await client.messages.create({
  model: "claude-sonnet-4",
  max_tokens: 256,
  messages: [{ role: "user", content: "hi" }],
});

Streaming ("stream": true) works on the same route, and tool calls are gated on both the streaming and non-streaming paths.

Model ids

These are the ids surfaced in model discovery (GET .../v1/models). Any id starting with claude- is forwarded to Anthropic, which is the source of truth for what your key can call — so a newer model works the day Anthropic ships it.

What you get

Every call runs through the integrity engine before it reaches Anthropic, and every tool call the model asks for is evaluated before your tools run it. Verdicts and forensic evidence land in the dashboard. Vision, tool use, and long context are all forwarded untouched.

If something goes wrong

More: Provider unavailable.

More

• Quickstart — cURL — minimal HTTP example
• Quickstart — Python SDK
• Dashboard — sessions, verdicts, forensic evidence
• Providers — every provider Sentisec carries