跳到正文
RunAPI 开发者文档
EN 中文
API 参考
API 参考

OpenAI Chat Completions

通过 RunAPI 的 OpenAI 兼容 Chat Completions operation 发送请求。

查看 Markdown
01

概览

使用兼容模型和对应协议的请求、响应结构调用 RunAPI 的 OpenAI 兼容 Chat Completions operation。

快速开始

  1. 创建 API Key，并将其设置为 RUNAPI_API_KEY。
  2. 选择兼容模型，然后发送文档所列的路径参数和 JSON 请求体。
  3. 读取此 operation 展示的 JSON 响应或服务器发送事件，并处理协议错误。

端点

POST /v1/chat/completions
基础 URL
https://runapi.ai
Contract 版本
v1
首选身份验证
Authorization: Bearer YOUR_API_TOKEN
02

身份验证载体

RunAPI 接受下列每种载体；生成的示例使用该协议的首选请求头。

header - 首选
Authorization: Bearer YOUR_API_TOKEN
header
x-api-key: YOUR_API_TOKEN
header
x-goog-api-key: YOUR_API_TOKEN
query
?key=YOUR_API_TOKEN
03

兼容模型

打开模型页可查看当前价格、限流和商业使用详情。

展开 53 个兼容模型
04

请求 Contract

JSON 请求体

这里只列出同时具有公共协议与 RunAPI 支持证据的字段；其他 JSON 请求体字段会原样传递。

JSON 请求体9 个字段
max_tokens["integer", "null"]
可选

Compatibility generation token limit retained for supported models; model support can vary.

messagesarray
必填

Conversation messages in OpenAI Chat Completions format.

messages[].content["string", "array"]
可选
messages[].rolestring
必填
modelstring
必填

RunAPI model identifier returned by the compatible model catalog.

stream["boolean", "null"]
可选

Return Chat Completions chunks as server-sent events.

默认值: false
temperature["number", "null"]
可选

Sampling temperature; model support can vary.

toolsarray
可选

Tools the model may call.

top_p["number", "null"]
可选

Nucleus sampling probability; model support can vary.

请求示例

JSON 
{
  "messages": [
    {
      "content": "Say hello in one sentence.",
      "role": "user"
    }
  ],
  "model": "gpt-5.4",
  "stream": false
}
05

同步响应

HTTP 200

Schema

JSON 
{
  "additionalProperties": true,
  "properties": {
    "choices": {
      "type": "array"
    },
    "created": {
      "type": "integer"
    },
    "id": {
      "type": "string"
    },
    "model": {
      "type": "string"
    },
    "object": {
      "const": "chat.completion",
      "type": "string"
    },
    "usage": {
      "additionalProperties": true,
      "properties": {
        "completion_tokens": {
          "type": "integer"
        },
        "prompt_tokens": {
          "type": "integer"
        },
        "total_tokens": {
          "type": "integer"
        }
      },
      "required": [
        "prompt_tokens",
        "completion_tokens",
        "total_tokens"
      ],
      "type": "object"
    }
  },
  "required": [
    "id",
    "object",
    "created",
    "model",
    "choices"
  ],
  "type": "object"
}

示例

JSON 
{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "Hello! How can I help today?",
        "role": "assistant"
      }
    }
  ],
  "created": 1785196800,
  "id": "chatcmpl_example",
  "model": "gpt-5.4",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 8,
    "prompt_tokens": 12,
    "total_tokens": 20
  }
}
06

SSE 事件：chunk

text/event-stream

Schema

JSON 
{
  "additionalProperties": true,
  "properties": {
    "choices": {
      "type": "array"
    },
    "created": {
      "type": "integer"
    },
    "id": {
      "type": "string"
    },
    "model": {
      "type": "string"
    },
    "object": {
      "const": "chat.completion.chunk",
      "type": "string"
    },
    "usage": {
      "oneOf": [
        {
          "additionalProperties": true,
          "properties": {
            "completion_tokens": {
              "type": "integer"
            },
            "prompt_tokens": {
              "type": "integer"
            },
            "total_tokens": {
              "type": "integer"
            }
          },
          "required": [
            "prompt_tokens",
            "completion_tokens",
            "total_tokens"
          ],
          "type": "object"
        },
        {
          "type": "null"
        }
      ]
    }
  },
  "required": [
    "id",
    "object",
    "choices"
  ],
  "type": "object"
}

示例

JSON 
{
  "choices": [
    {
      "delta": {
        "content": "Hello"
      },
      "finish_reason": null,
      "index": 0
    }
  ],
  "id": "chatcmpl_example",
  "object": "chat.completion.chunk",
  "usage": null
}
07

协议错误：invalid_request

HTTP 400

Schema

JSON 
{
  "additionalProperties": true,
  "properties": {
    "error": {
      "additionalProperties": true,
      "properties": {
        "code": {
          "type": [
            "string",
            "null"
          ]
        },
        "message": {
          "type": "string"
        },
        "param": {
          "type": [
            "string",
            "null"
          ]
        },
        "type": {
          "type": "string"
        }
      },
      "required": [
        "message",
        "type"
      ],
      "type": "object"
    }
  },
  "required": [
    "error"
  ],
  "type": "object"
}

示例

JSON 
{
  "error": {
    "code": null,
    "message": "messages is required",
    "param": "messages",
    "type": "invalid_request_error"
  }
}
08

Usage

Schema

JSON 
{
  "additionalProperties": true,
  "properties": {
    "completion_tokens": {
      "type": "integer"
    },
    "prompt_tokens": {
      "type": "integer"
    },
    "total_tokens": {
      "type": "integer"
    }
  },
  "required": [
    "prompt_tokens",
    "completion_tokens",
    "total_tokens"
  ],
  "type": "object"
}

示例

JSON 
{
  "completion_tokens": 8,
  "prompt_tokens": 12,
  "total_tokens": 20
}
09

生成的代码示例

每个 cURL、JavaScript 和 Python 示例都会发送此 Contract 中经过验证的请求，无需协议专用 SDK。

CURL 
curl -X POST https://runapi.ai/v1/chat/completions \
  -H Authorization:\ Bearer\ YOUR_API_TOKEN \
  -H Content-Type:\ application/json \
  -d \{\"model\":\"gpt-5.4\",\"messages\":\[\{\"role\":\"user\",\"content\":\"Say\ hello\ in\ one\ sentence.\"\}\],\"stream\":false\}
JAVASCRIPT 
const response = await fetch("https://runapi.ai/v1/chat/completions", {
  method: "POST",
  headers: {
  "Authorization": "Bearer YOUR_API_TOKEN",
  "Content-Type": "application/json"
},
  body: JSON.stringify({
  "model": "gpt-5.4",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one sentence."
    }
  ],
  "stream": false
})
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data);

安装

BASH 
pip install requests
PYTHON 
import requests

response = requests.post(
    "https://runapi.ai/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_TOKEN", "Content-Type": "application/json"},
    json={"model": "gpt-5.4", "messages": [{"role": "user", "content": "Say hello in one sentence."}], "stream": False}
)
response.raise_for_status()
print(response.json())
10

相关指南