Chat Completions

清霄 API 文本对话接口，兼容 OpenAI Chat Completions。可用 model id 以控制台为准。

项	值
Path	POST /v1/chat/completions
Base	https://api.qingxiaocloud.com
Auth	Authorization: Bearer sk-…
Content-Type	application/json

请求示例

curl -sS "https://api.qingxiaocloud.com/v1/chat/completions" \
  -H "Authorization: Bearer sk-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [
      {"role": "system", "content": "你是简洁的助手。"},
      {"role": "user", "content": "你好"}
    ],
    "stream": false
  }'

请求字段

字段	必填	说明
model	*	模型 ID（控制台）
messages	*	对话消息列表（如 role / content）
temperature		默认 1；范围 0–2
top_p		默认 1；范围 0–1
n		默认 1；≥1
stream		默认 false
stream_options		object
stop		string | array
max_tokens		最大生成 Token
max_completion_tokens		最大补全 Token
presence_penalty		默认 0；-2–2
frequency_penalty		默认 0；-2–2
logit_bias		object
tool_choice		string | object
response_format		object
reasoning_effort		"low" | "medium" | "high"
modalities		array

响应字段（200）

字段	说明
id / object / created / model	object 例：chat.completion
choices[]	index；message（role / content / name / tool_calls / tool_call_id / reasoning_content）；finish_reason
usage	prompt_tokens / completion_tokens / total_tokens；prompt_tokens_details；completion_tokens_details（含 reasoning_tokens）
system_fingerprint	string

响应示例

{
  "id": "string",
  "object": "chat.completion",
  "created": 0,
  "model": "string",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "string",
        "reasoning_content": "string"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 0,
    "completion_tokens": 0,
    "total_tokens": 0,
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  }
}

错误体：error.message / type / param / code（常见 400 / 429）。

列出模型

curl -sS "https://api.qingxiaocloud.com/v1/models" \
  -H "Authorization: Bearer sk-YOUR_KEY"

模型目录与价格以控制台为准；文档不维护货架页。