API 管理

管理您的 API 密钥和查看 API 调用文档

本月用量

Token 用量 2.5M
配额上限 10M
API 调用次数 128.5K

API 密钥

API 密钥用于访问推理服务的接口，请妥善保管。密钥只会在创建时显示一次，请及时复制保存。

生产环境密钥 sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
已启用 创建于 2024-03-01
测试环境密钥 sk-yyyyyyyyyyyyyyyyyyyyyyyyyyyyyyyy
已启用 创建于 2024-02-15

API 文档

POST /v1/chat/completions

创建聊天完成请求，支持流式和非流式响应

curl https://api.gxcoreshub.cn/v1 \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen2.5-72b",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "stream": false
  }'
POST /v1/completions

创建文本补全请求

curl https://api.gxcoreshub.cn/v1/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "qwen2.5-72b",
    "prompt": "Once upon a time",
    "max_tokens": 100
  }'
GET /v1/models

获取可用的模型列表

curl https://api.gxcoreshub.cn/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

SDK 示例

Python 
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.gxcoreshub.cn/v1"
)

response = client.chat.completions.create(
    model="qwen2.5-72b",
    messages=[
        {"role": "user", "content": "你好！"}
    ]
)

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