Qwen3.8-27B 模型服务 · OpenAI 兼容接口
| Base URL | https://chat.jicreate.cn/v1 |
|---|---|
| 模型 ID | qwen3.8-27b |
| 认证方式 | 请求头 Authorization: Bearer <API Key> |
| 流式输出 | 支持 SSE(stream: true) |
Authorization: Bearer <你的Key> 传递。未携带或 Key 错误将返回
401。
| 接口 | 方法 | 说明 |
|---|---|---|
/v1/models | GET | 列出可用模型 |
/v1/chat/completions | POST | 对话补全(最常用) |
/v1/completions | POST | 纯文本补全 |
/v1/responses | POST | Responses API |
/health | GET | 服务健康检查(无需 Key) |
curl https://chat.jicreate.cn/v1/chat/completions \
-H "Authorization: Bearer 你的APIKey" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-27b",
"messages": [
{"role": "user", "content": "介绍一下你自己"}
]
}'
curl -N https://chat.jicreate.cn/v1/chat/completions \
-H "Authorization: Bearer 你的APIKey" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-27b",
"messages": [{"role": "user", "content": "你好"}],
"stream": true
}'
流式响应按 data: {…} 逐段返回,最后以 data: [DONE] 结束。
from openai import OpenAI
client = OpenAI(
base_url="https://chat.jicreate.cn/v1",
api_key="你的APIKey",
)
resp = client.chat.completions.create(
model="qwen3.8-27b",
messages=[{"role": "user", "content": "你好"}],
stream=True,
)
for chunk in resp:
print(chunk.choices[0].delta.content or "", end="")
curl https://chat.jicreate.cn/v1/responses \
-H "Authorization: Bearer 你的APIKey" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen3.8-27b",
"input": "写一首关于夏天的短诗",
"max_output_tokens": 200
}'
| 状态码 | 说明 |
|---|---|
401 | 缺少或错误的 API Key |
404 | 接口路径不存在 |
503 | GPU worker 未连接,请稍后重试 |
504 | 上游响应超时 |
错误响应统一为 OpenAI 风格:{"error": {"message": "…", "type": "…"}}
/v1/* 接口都必须携带 API Keyqwen3.8-27b