curl http://localhost:8000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer tr-YOUR_KEY" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [{"role": "user", "content": "你好，介绍一下你自己"}]
  }'

from openai import OpenAI

client = OpenAI(
    api_key="tr-YOUR_KEY",
    base_url="http://localhost:8000/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-4-6",
    messages=[{"role": "user", "content": "你好，介绍一下你自己"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "tr-YOUR_KEY",
  baseURL: "http://localhost:8000/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-4-6",
  messages: [{ role: "user", content: "你好，介绍一下你自己" }],
});
console.log(response.choices[0].message.content);

Token Relay 自动完成 Anthropic ↔ OpenAI 格式转换，Claude Code 可直接用。

export ANTHROPIC_BASE_URL="http://localhost:8000/v1"
export ANTHROPIC_API_KEY="tr-YOUR_KEY"

claude --model claude-sonnet-4-6

1. Cursor Settings → Models → OpenAI
2. API Key：tr-xxxx
3. Base URL：http://localhost:8000/v1
4. Model：填入模型 ID，如 claude-sonnet-4-6

设置 → 语言模型 → 添加自定义 OpenAI 服务商

• API Key：tr-xxxx
• API Host：http://localhost:8000

OPENAI_API_KEY=tr-YOUR_KEY
BASE_URL=http://localhost:8000

Admin Panel → Settings → Connections → OpenAI API

• API Key：tr-xxxx
• API Base URL：http://localhost:8000/v1

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    api_key="tr-YOUR_KEY",
    base_url="http://localhost:8000/v1",
    model="claude-sonnet-4-6",
)