聊天补全#

通过 OpenAI 兼容的聊天补全 API 实现文本生成和多轮对话。

接口说明#

最小请求#

curl https://api.unigateway.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "用三点说明 AI 网关的价值。"}
    ]
  }'

Python（OpenAI SDK）#

from openai import OpenAI

client = OpenAI(
    api_key="<YOUR_UNIGATEWAY_API_KEY>",
    base_url="https://api.unigateway.ai/v1",
)

resp = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "用三点总结。"}],
)

print(resp.choices[0].message.content)

TypeScript（OpenAI SDK）#

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.UNIGATEWAY_API_KEY,
  baseURL: "https://api.unigateway.ai/v1",
});

const resp = await client.chat.completions.create({
  model: "gpt-5.4",
  messages: [{ role: "user", content: "用三点总结。" }],
});

console.log(resp.choices[0].message.content);

参数说明#

跨模型示例#

GPT#

curl https://api.unigateway.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "system", "content": "你是简洁的技术助手。"},
      {"role": "user", "content": "写一份从单一 Provider 迁移到 UniGateway 的说明。"}
    ],
    "temperature": 0.3
  }'

Claude（通过 OpenAI 兼容接口）#

curl https://api.unigateway.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-4-6",
    "messages": [
      {"role": "user", "content": "用一句话解释量子计算。"}
    ],
    "max_tokens": 200
  }'

Gemini（通过 OpenAI 兼容接口）#

curl https://api.unigateway.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNIGATEWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3-pro-preview",
    "messages": [
      {"role": "user", "content": "用三点说明 AI 网关路由。"}
    ]
  }'

使用 Claude 特有能力如 thinking 和 cache_control，请用 POST /v1/messages。使用 Gemini 特有能力如 responseModalities 和 imageConfig，请用 POST /v1beta/models/{model}:generateContent。

响应格式#

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1760000000,
  "model": "gpt-5.4",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "AI 网关统一模型接入、简化计费，并实现智能路由。"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 18,
    "total_tokens": 42
  }
}

常见错误#