Anthropic SDK on your own GPUs.

Your Anthropic API key stays in api_key; the warden key rides in its own header.

Protocol: Anthropic Messages
Support: Full support
Verified: Run against a live warden on 2026-10-04 with anthropic 1.11.0 (Python), @anthropic-ai/sdk 0.131.0, curl. Python, TypeScript and curl in both modes; router mode’s claude-haiku-4-5 was answered here.

The Claude models your rules name run here; every other model and /v1 path goes to Anthropic on your own login. Local only needs no Anthropic account: the warden key is the api_key and the model is a served name.

Requirements

Routing must be on, with at least one enabled rule.
The key must be allowed to relay to Anthropic (May relay).

Setup

In the console, Connect writes these files with your warden’s address, your key and the model you picked. Here they are with placeholders.

Router: keep your Anthropic key

base_url is this warden; your Anthropic API key stays in api_key and the warden key goes in default headers.

Python

import anthropic

# api_key is your own Anthropic key (ANTHROPIC_API_KEY), used for pass-through.
client = anthropic.Anthropic(
    base_url="https://your-warden",
    default_headers={"X-LMWarden-Key": "vw_YOUR_KEY"},
)
message = client.messages.create(
    model="claude-haiku-4-5",  # a model your rules serve here; others go to Anthropic
    max_tokens=256,
    messages=[{"role": "user", "content": "Reply with the single word OK."}],
)
print(message.content[0].text)

TypeScript

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

// apiKey is your own Anthropic key (ANTHROPIC_API_KEY), used for pass-through.
const client = new Anthropic({
  baseURL: "https://your-warden",
  defaultHeaders: { "X-LMWarden-Key": "vw_YOUR_KEY" },
});
const message = await client.messages.create({
  model: "claude-haiku-4-5", // a model your rules serve here; others go to Anthropic
  max_tokens: 256,
  messages: [{ role: "user", content: "Reply with the single word OK." }],
});
console.log(message.content);

curl

curl https://your-warden/v1/messages \
  -H "X-LMWarden-Key: vw_YOUR_KEY" \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model": "claude-haiku-4-5", "max_tokens": 256, "messages": [{"role": "user", "content": "Reply with the single word OK."}]}'

Local only

The warden key is the api_key and the model is a served name.

Python

import anthropic

client = anthropic.Anthropic(base_url="https://your-warden", api_key="vw_YOUR_KEY")
message = client.messages.create(
    model="your-served-model-name",
    max_tokens=256,
    messages=[{"role": "user", "content": "Reply with the single word OK."}],
)
print(message.content[0].text)

TypeScript

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

const client = new Anthropic({ baseURL: "https://your-warden", apiKey: "vw_YOUR_KEY" });
const message = await client.messages.create({
  model: "your-served-model-name",
  max_tokens: 256,
  messages: [{ role: "user", content: "Reply with the single word OK." }],
});
console.log(message.content);

curl

curl https://your-warden/v1/messages \
  -H "x-api-key: vw_YOUR_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "content-type: application/json" \
  -d '{"model": "your-served-model-name", "max_tokens": 256, "messages": [{"role": "user", "content": "Reply with the single word OK."}]}'

Official documentation: https://platform.claude.com/docs/en/api/sdks/python (read 2026-10-04).