其他客户端与协议
OpenAI 兼容
Chat Completions 与 Responses 接口，适用于 OpenAI SDK 与任何 OpenAI 兼容客户端。
适用于 OpenAI 官方 SDK 以及任何 OpenAI 兼容客户端。Key 绑定的分组需支持 OpenAI 协议；Claude 等其他厂商模型同样可以通过这个协议调用。
请求地址与认证
SDK base_url
https://api.easyapi.cc/v1带 /v1
Chat Completions
POST https://api.easyapi.cc/v1/chat/completionsResponses
POST https://api.easyapi.cc/v1/responses模型列表
GET https://api.easyapi.cc/v1/models认证头为 Authorization: Bearer YOUR_API_KEY。下面示例的模型名取自模型广场，可换成任意列出的模型。
Chat Completions
发送 messages，回复在 choices[0].message.content。
curl
curl https://api.easyapi.cc/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-5",
"messages": [{ "role": "user", "content": "请只回复：Hello" }]
}'Python · pip install openai
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.easyapi.cc/v1")
resp = client.chat.completions.create(
model="gpt-5",
messages=[{"role": "user", "content": "请只回复：Hello"}],
)
print(resp.choices[0].message.content)Node.js · npm install openai
import OpenAI from 'openai'
const client = new OpenAI({ apiKey: 'YOUR_API_KEY', baseURL: 'https://api.easyapi.cc/v1' })
const resp = await client.chat.completions.create({
model: 'gpt-5',
messages: [{ role: 'user', content: '请只回复：Hello' }],
})
console.log(resp.choices[0].message.content)Responses
Codex 使用的协议。发送 input，回复在 output 里类型为 output_text 的条目，SDK 提供 output_text 快捷属性。
curl
curl https://api.easyapi.cc/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{ "model": "gpt-5", "input": "请只回复：Hello" }'Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.easyapi.cc/v1")
resp = client.responses.create(model="gpt-5", input="请只回复：Hello")
print(resp.output_text)流式输出
请求体加 "stream": true，返回 SSE 事件流，与官方格式一致。SDK 中传 stream=True 后按块迭代即可。
Python
from openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.easyapi.cc/v1")
stream = client.chat.completions.create(
model="gpt-5",
messages=[{"role": "user", "content": "用一句话介绍你自己"}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True)