Authentication and base URL | Tutujin API Docs

Every endpoint uses the same API key. You create keys in the console and they start with sk-. OpenAI-format requests send the key in an Authorization: Bearer header. The native Claude and Gemini endpoints also accept the headers their official SDKs send by default, so with an official SDK you only change the base URL and the key.

Three header styles

API format	Header	Works on
OpenAI-compatible (Chat Completions, Responses, Embeddings, images, audio, Rerank)	`Authorization: Bearer sk-...`	Every endpoint
Native Claude Messages	`x-api-key: sk-...` plus `anthropic-version: 2023-06-01`	`/v1/messages` and the models endpoint
Native Gemini generateContent	`x-goog-api-key: sk-...`	`/v1beta/models/...` and the models endpoint

Authorization: Bearer works on every endpoint, including the native Claude and Gemini paths. The other two styles exist so the official SDKs work unchanged. Native Gemini paths also accept a ?key= URL parameter, but URLs tend to end up in logs and proxies, so prefer the header.

curl https://open.tutujin.com/v1/chat/completions \
  -H "Authorization: Bearer $TUTUJIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4-mini",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl https://open.tutujin.com/v1/messages \
  -H "x-api-key: $TUTUJIN_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-haiku-5-5",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl "https://open.tutujin.com/v1beta/models/gemini-3.8-flash:generateContent" \
  -H "x-goog-api-key: $TUTUJIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"role": "user", "parts": [{"text": "Hello"}]}]
  }'

Setting the base URL

The OpenAI SDK's base URL includes /v1. The Anthropic and Google SDKs append the endpoint path themselves, so give them the site root.

SDK or method	Option	Value
OpenAI SDK (Python / Node.js)	`base_url` / `baseURL`, or the `OPENAI_BASE_URL` environment variable	`https://open.tutujin.com/v1`
Anthropic SDK	`base_url` / `baseURL`	`https://open.tutujin.com`
Google Gen AI SDK	`base_url` inside `http_options`	`https://open.tutujin.com`
Plain HTTP	Full URL	e.g. `https://open.tutujin.com/v1/chat/completions`, `https://open.tutujin.com/v1/messages`

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://open.tutujin.com/v1",
    api_key=os.environ["TUTUJIN_API_KEY"],
)

import os
import anthropic

client = anthropic.Anthropic(
    base_url="https://open.tutujin.com",
    api_key=os.environ["TUTUJIN_API_KEY"],
)

import os
from google import genai
from google.genai import types

client = genai.Client(
    api_key=os.environ["TUTUJIN_API_KEY"],
    http_options=types.HttpOptions(base_url="https://open.tutujin.com"),
)

Full SDK setups are in the OpenAI SDK and Anthropic SDK guides.

Key restrictions

When you create or edit a key in the console, you can restrict it:

Setting	What happens when a request breaks it
Group	Decides the line the key uses and the price it pays — see Choosing a group
Spending limit	Once the key has spent its limit it returns 401; other keys keep working
Expiry	After the expiry date the key returns 401
Model allowlist	Calling a model outside the list returns 403
IP allowlist	Requests from other IPs return 403

The console shows keys masked by default. Use one key per project and per environment, and give production keys a model allowlist and an IP allowlist, so a leaked key can only do limited damage. More in API key security best practices.

Keep keys on your servers only, in environment variables or a secrets manager. Never put them in web, app or mini-program front-end code, and never commit them to a repository.

Authentication errors

Status	Usual cause	What to do
401	The key is wrong, deleted, disabled or expired, or it has used up its spending limit	Check the full key in the header and its status in the console
403	The account balance ran out, the IP or model is not on the allowlist, or the key's group is unavailable	Fix the setting or add credit as the message says; do not retry automatically

The full list of status codes and retry advice is in Errors and retries.

Still stuck? Add our WeChat support JsnonoChat and send the request id from the error message, and we will look into it.