补全

传统文本补全接口（Legacy Completions），适用于非对话式的文本生成场景。

新项目推荐

新项目建议直接使用 聊天接口，补全接口仅为兼容老模型保留。

创建补全 POST

POST https://api.nassaapi.xyz/completions

Authorization

Authorization: Bearer sk-xxxx
Content-Type: application/json

请求参数

参数	类型	必填	说明
model	string	✅	模型 ID
prompt	string	✅	文本 Prompt
max_tokens	int	❌	最大生成 Token 数
temperature	number	❌	采样温度，0–2
stop	string | array	❌	停止序列

示例请求

cURL

curl -X POST "https://api.nassaapi.xyz/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-xxxx" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "写一首关于春天的诗：",
    "max_tokens": 256,
    "temperature": 0.8
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxxx",
    base_url="https://api.nassaapi.xyz"
)

response = client.completions.create(
    model="gpt-3.5-turbo-instruct",
    prompt="写一首关于春天的诗：",
    max_tokens=256,
    temperature=0.8
)
print(response.choices[0].text)

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-xxxx',
  baseURL: 'https://api.nassaapi.xyz',
});

const response = await client.completions.create({
  model: 'gpt-3.5-turbo-instruct',
  prompt: '写一首关于春天的诗：',
  max_tokens: 256,
  temperature: 0.8,
});
console.log(response.choices[0].text);

响应

{
  "id": "cmpl-abc123",
  "object": "text_completion",
  "created": 1677858242,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": "\n春风拂面暖意浓，\n百花争艳满园红。",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 24,
    "total_tokens": 36
  }
}