响应（Responses API）
API 配置
保存后下方「Try It」面板会自动携带此 API Key 发送真实请求。
Base: api.xrtoken.net
OpenAI Responses API 兼容端点，透传至上游。支持流式（SSE）与非流式响应。
与 /v1/chat/completions 的区别：请求用 input 代替 messages、max_output_tokens
代替 max_tokens；流式为 typed events，以 response.completed 事件（含 usage）结束。
任意 chat 类模型均可调用；若上游不支持 Responses API，将透传上游错误并退费。 Codex 等仅支持 Responses API 的客户端可直接把 base_url 指向本网关。
Authorization
BearerAuth AuthorizationBearer <token>
API 密钥认证（OpenAI 格式）。在 Authorization 请求头中传入：
Authorization: Bearer tr-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
In: header
Request Body
application/json
TypeScript Definitions
Use the request body type in TypeScript.
Response Body
application/json
application/json
application/json
application/json
application/json
curl -X post "https://api.xrtoken.net/v1/responses" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-4o", "input": "用一句话介绍你自己" }'{
"id": "string",
"object": "response",
"status": "string",
"output": [
{}
],
"usage": {
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0
}
}{
"error": "model field is required",
"type": "invalid_request_error"
}{
"error": "invalid or missing API key",
"type": "auth_error"
}{
"error": "insufficient balance -- please top up or upgrade your plan",
"type": "billing_error"
}{
"error": "rate limit exceeded",
"type": "rate_limit_error"
}{
"error": "upstream provider error",
"type": "server_error"
}