跳到主要内容

Portkey

Portkey 是 GenAI 构建者的生产技术栈。 官方网站：portkey.ai

1.1 使用方法​

方式一：通过模型目录添加自定义提供商（推荐）​

  1. 登录 Portkey 仪表板，进入 Model Catalog

  2. 选择 Add Provider → Self-hosted / Custom

  3. 输入 API 端点和 API Key

  4. 添加自定义模型并设置 Model Slug

  5. 使用 @luchentech/minimax/minimax-m2.5 调用

方式二：透传模式​

from portkey_ai import Portkey

client = Portkey(
    api_key="PORTKEY_API_KEY",
    provider="passthrough",
    custom_host="https://api.luchentech.com/inference/v1",
    default_headers={
        "authorization": "Bearer YOUR_HPC_AI_API_KEY"
    }
)

response = client.chat.completions.create(
    model="minimax/minimax-m2.5",
    messages=[{"role": "user", "content": "Hello!"}]
)

方式三：cURL​

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-provider: passthrough" \
  -H "x-portkey-custom-host: https://api.luchentech.com/inference/v1" \
  -H "authorization: Bearer YOUR_HPC_AI_API_KEY" \
  -d '{
    "model": "minimax/minimax-m2.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

方式四：OpenAI SDK 兼容​

from openai import OpenAI

client = OpenAI(
    api_key="PORTKEY_API_KEY",
    base_url="https://api.portkey.ai/v1"
)

# 通过请求头指定提供商
response = client.chat.completions.create(
    model="minimax/minimax-m2.5",
    messages=[{"role": "user", "content": "Hello!"}],
    extra_headers={
        "x-portkey-provider": "passthrough",
        "x-portkey-custom-host": "https://api.luchentech.com/inference/v1"
    }
)

1.2 故障排除​

常见问题解决方案
请求失败验证 custom_host URL 格式
授权失败确保正确传递 authorization 请求头
模型未找到确保 Model Slug 与添加的自定义模型匹配

1.3 参考​