跳转到主要内容

Documentation Index

Fetch the complete documentation index at: https://docs.ominiapi.com/llms.txt

Use this file to discover all available pages before exploring further.

​
聊天 (Chat) - ChatCompletions 格式 (原生 OpenAI)

根据对话历史创建模型响应。支持流式和非流式响应。完全兼容 OpenAI Chat Completions API。
  • 接口地址: POST /v1/chat/completions
  • 基础 URL (示例): https://www.ominiapi.com

​
认证与请求头 (Headers)

  • Authorization (必选): 使用 Bearer Token 认证。格式: Bearer sk-xxxxxx
  • Content-Type: application/json

​
请求参数 (Request Body)

参数名类型必选说明
modelString是模型 ID，如 gpt-4 等
messagesArrayObject是对话消息列表，包含 role 和 content 等
temperatureNumber否采样温度，默认 1，范围 0 <= value <= 2
top_pNumber否核采样参数，默认 1，范围 0 <= value <= 1
nInteger否生成响应的数量，默认 1，必须 >= 1
streamBoolean否是否启用流式响应，默认 false
stream_optionsObject否流式响应的额外选项配置
stopString/Array否触发停止生成的字符或序列
max_tokensInteger否最大生成 Token 数
max_completion_tokensInteger否最大补全 Token 数
presence_penaltyNumber否存在惩罚，默认 0，范围 -2 <= value <= 2
frequency_penaltyNumber否频率惩罚，默认 0，范围 -2 <= value <= 2
logit_biasObject否调整特定 Token 生成概率的偏置参数
userString否终端用户的唯一标识符
toolsArrayObject否模型可调用的工具（函数）列表
tool_choiceString/Object否控制工具的选择模式
response_formatObject否指定响应格式（如 JSON 对象）
seedInteger否随机种子，用于实现确定性输出
reasoning_effortString否推理强度（用于支持推理的模型），可选: low, medium, high
modalitiesArrayString否模态设置
audioObject否音频输入/输出相关配置

​
示例代码 (cURL)

curl -X POST "[https://www.ominiapi.com/v1/chat/completions](https://www.ominiapi.com/v1/chat/completions)" \
  -H "Authorization: Bearer <您的_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [
      {
        "role": "system",
        "content": "你是我的得力助手。"
      },
      {
        "role": "user",
        "content": "你好！"
      }
    ]
  }'

​
响应体结构 (Response - 200 OK)

成功请求返回 JSON 格式结果。 
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4-0613",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！有什么我可以帮你的吗？",
        "name": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "tool_call_id": "string",
        "reasoning_content": "string"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 9,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 12,
      "audio_tokens": 0,
      "reasoning_tokens": 0
    }
  },
  "system_fingerprint": "string"
}