Use the Anthropic Node SDK with a custom baseURL.

What was actually verified on production?

Six probes were sent to https://monkeytheme.com/v1/messages with a deliberately invalid test key, on 2026-08-09. Every probe returned HTTP 401 with a structured JSON body and the x-request-id header in the response. The sub2api backend log shows ingress_reject_reason=invalid_api_key with latency_ms=0-3, meaning the relay gates on auth before any upstream call. The Node SDK behaviour mirrors the Python SDK because both implement the same wire protocol.

Install and configure the client

The Anthropic Node SDK is on npm as @anthropic-ai/sdk. It accepts baseURL, apiKey, and authToken on the constructor. The README documents ANTHROPIC_BASE_URL and ANTHROPIC_API_KEY as environment fallbacks.

npm install @anthropic-ai/sdk

export ANTHROPIC_BASE_URL="https://monkeytheme.com"
export ANTHROPIC_API_KEY="***"

Do not commit the key into source. process.env is fine for the snippet below; for production prefer a secrets manager or a .env.local file outside version control.

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

const client = new Anthropic({
  apiKey: process.env.ANTHROPIC_API_KEY,
  baseURL: process.env.ANTHROPIC_BASE_URL,
});

Verify the key before sending real prompts

The Anthropic SDK does not expose a models.list() helper. To confirm a key is alive, send a single-token client.messages.create() call with max_tokens: 1. If the key is bad you get a 401 with a request ID; if the key is good you get a 1-token Claude reply with a model field that confirms the upstream model name.

const resp = await client.messages.create({
  model: "claude-3-5-sonnet-20241022",
  max_tokens: 1,
  messages: [{ role: "user", content: "Reply with OK" }],
});
console.log(resp.model, resp.stop_reason, resp.usage);

If resp.model prints a Claude model name visible to your account, the SDK wiring is correct. The Anthropic SDK pins anthropic-version to 2023-06-01 on every request; you do not need to set it yourself.

How should errors be handled?

The SDK throws APIError for non-2xx responses and AnthropicError for other SDK-side issues. Both expose .status and .headers. Log the request ID from the error headers; do not log the API key.

try {
  const resp = await client.messages.create({
    model: "claude-3-5-sonnet-20241022",
    max_tokens: 64,
    messages: [{ role: "user", content: "hi" }],
  });
} catch (err) {
  if (err.status) {
    const reqId = err.headers?.get?.("x-request-id");
    console.error("HTTP", err.status, "request_id", reqId);
  } else {
    console.error("network/TLS:", err.cause ?? err.message);
  }
  throw err;
}

A 401 with code=INVALID_API_KEY from MonkeyAI is the same code the OpenAI route returns. The relay does not distinguish between Anthropic and OpenAI keys at this layer; both are MonkeyAI keys, and they live in the same backend.

Streaming, tools and retries

Streaming on /v1/messages uses Server-Sent Events. The Anthropic SDK exposes a stream helper via client.messages.stream(...). Retries on 429 and 5xx are on by default; set maxRetries: 0 while debugging so a transient 429 does not silently mask the real failure.

const stream = client.messages.stream({
  model: "claude-3-5-sonnet-20241022",
  max_tokens: 256,
  messages: [{ role: "user", content: "Summarise this in one sentence." }],
});

for await (const event of stream) {
  if (event.type === "content_block_delta" && event.delta.type === "text_delta") {
    process.stdout.write(event.delta.text);
  }
}

const final = await stream.finalMessage();

Tools work the same way they do against api.anthropic.com. If a tool_use block comes back, the SDK parses it into resp.content. If you instead see a 400 from upstream after a 200 from the relay, the upstream account likely rejected the tool schema, not MonkeyAI.

Common configuration mistakes

• Setting baseURL to https://monkeytheme.com/v1 with the SDK on top. The SDK already adds /v1; the resulting path becomes /v1/v1/messages and nginx returns 404.
• Setting apiKey to the OpenAI-style sk-*** value and then wondering why Bearer works but the SDK still 401s. The Anthropic SDK sends x-api-key; the relay accepts it on /v1/messages, but the same string is the MonkeyAI account key.
• Stripping anthropic-version with a fetch interceptor. The SDK sets it; removing it does not help and breaks upstream compatibility checks.
• Calling client.models.list() on the Anthropic client. There is no such method on the Anthropic SDK; use fetch against GET /v1/models directly.
• Treating a 401 INVALID_API_KEY as evidence of upstream outage. The 401 came from the relay's auth gate, not from the upstream account. Check the API key first.

Sources

• Anthropic TypeScript SDK README (pinned revision)
• Official Anthropic TypeScript SDK repository
• Anthropic API reference: client SDKs
• MonkeyAI: OpenAI Node SDK custom Base URL
• MonkeyAI: Anthropic Python SDK custom Base URL

FAQ

Related guides