AIGoCode Docs
快速开始

第一次请求

使用 OpenAI、Claude 和 Gemini 兼容接口完成聊天请求

下面分别用 OpenAI Compatible、Claude Messages 和 Gemini generateContent 接口完成一次最小请求。请选择你使用的接口和环境，并把示例中的 API Key 换成你的真实密钥。

OpenAI Compatible

macOS/Linux
export AIGOCODE_API_KEY="在这里填写你的 AIGoCode API Key"

curl https://api.aigocode.app/v1/chat/completions \
  -H "Authorization: Bearer $AIGOCODE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-astra",
    "messages": [
      {
        "role": "user",
        "content": "Hello from AIGoCode!"
      }
    ]
  }'
Cmd
set "AIGOCODE_API_KEY=在这里填写你的 AIGoCode API Key"

curl.exe "https://api.aigocode.app/v1/chat/completions" ^
  -H "Authorization: Bearer %AIGOCODE_API_KEY%" ^
  -H "Content-Type: application/json" ^
  -d "{\"model\":\"gpt-6-astra\",\"messages\":[{\"role\":\"user\",\"content\":\"Hello from AIGoCode!\"}]}"
PowerShell
$env:AIGOCODE_API_KEY = "在这里填写你的 AIGoCode API Key"

$body = @{
  model = "gpt-6-astra"
  messages = @(
    @{
      role = "user"
      content = "Hello from AIGoCode!"
    }
  )
} | ConvertTo-Json -Depth 3

$response = Invoke-RestMethod `
  -Method Post `
  -Uri "https://api.aigocode.app/v1/chat/completions" `
  -Headers @{
    Authorization = "Bearer $env:AIGOCODE_API_KEY"
  } `
  -ContentType "application/json" `
  -Body $body

$response | ConvertTo-Json -Depth 10
Python
from openai import OpenAI

client = OpenAI(
    api_key="在这里填写你的 AIGoCode API Key",
    base_url="https://api.aigocode.app/v1",
)

response = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[
        {
            "role": "user",
            "content": "Hello from AIGoCode!",
        }
    ],
)

print(response.model_dump_json(indent=2))
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "在这里填写你的 AIGoCode API Key",
  baseURL: "https://api.aigocode.app/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-6-astra",
  messages: [
    {
      role: "user",
      content: "Hello from AIGoCode!",
    },
  ],
});

console.log(JSON.stringify(response, null, 2));

成功响应

成功后会返回 OpenAI Compatible 格式的响应，其中 choices[0].message.content 是模型回复内容。

response.json
{
  "id": "resp_xxx",
  "object": "chat.completion",
  "created": xxxxxx,
  "model": "gpt-6-astra",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello, AIGoCode! How can I help today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": xx,
    "completion_tokens": xx,
    "total_tokens": xx
  },
  "service_tier": "default"
}

Claude Messages

使用 Claude Messages 接口调用 Claude Sonnet 5。

macOS/Linux
export AIGOCODE_API_KEY="在这里填写你的 AIGoCode API Key"

curl https://api.aigocode.app/v1/messages \
  -H "x-api-key: $AIGOCODE_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 512,
    "messages": [
      {
        "role": "user",
        "content": "Hello from AIGoCode!"
      }
    ]
  }'
Cmd
set "AIGOCODE_API_KEY=在这里填写你的 AIGoCode API Key"

curl.exe "https://api.aigocode.app/v1/messages" ^
  -H "x-api-key: %AIGOCODE_API_KEY%" ^
  -H "anthropic-version: 2023-06-01" ^
  -H "Content-Type: application/json" ^
  -d "{\"model\":\"claude-sonnet-5\",\"max_tokens\":512,\"messages\":[{\"role\":\"user\",\"content\":\"Hello from AIGoCode!\"}]}"
PowerShell
$env:AIGOCODE_API_KEY = "在这里填写你的 AIGoCode API Key"

$body = @{
  model = "claude-sonnet-5"
  max_tokens = 512
  messages = @(
    @{
      role = "user"
      content = "Hello from AIGoCode!"
    }
  )
} | ConvertTo-Json -Depth 3

$response = Invoke-RestMethod `
  -Method Post `
  -Uri "https://api.aigocode.app/v1/messages" `
  -Headers @{
    "x-api-key" = $env:AIGOCODE_API_KEY
    "anthropic-version" = "2023-06-01"
  } `
  -ContentType "application/json" `
  -Body $body

$response | ConvertTo-Json -Depth 10
Python
import json
from urllib.request import Request, urlopen

api_key = "在这里填写你的 AIGoCode API Key"
body = {
    "model": "claude-sonnet-5",
    "max_tokens": 512,
    "messages": [
        {
            "role": "user",
            "content": "Hello from AIGoCode!",
        }
    ],
}

request = Request(
    "https://api.aigocode.app/v1/messages",
    data=json.dumps(body).encode("utf-8"),
    headers={
        "x-api-key": api_key,
        "anthropic-version": "2023-06-01",
        "Content-Type": "application/json",
    },
    method="POST",
)

with urlopen(request) as response:
    result = json.load(response)

print(json.dumps(result, ensure_ascii=False, indent=2))
Node.js
const apiKey = "在这里填写你的 AIGoCode API Key";

const response = await fetch("https://api.aigocode.app/v1/messages", {
  method: "POST",
  headers: {
    "x-api-key": apiKey,
    "anthropic-version": "2023-06-01",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "claude-sonnet-5",
    max_tokens: 512,
    messages: [
      {
        role: "user",
        content: "Hello from AIGoCode!",
      },
    ],
  }),
});

const result = await response.json();

if (!response.ok) {
  throw new Error(JSON.stringify(result));
}

console.log(JSON.stringify(result, null, 2));

成功响应

以下是使用上面的请求体真实调用 claude-sonnet-5 得到的响应。

response.json
{
  "id": "msg_xxx",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-5",
  "content": [
    {
      "type": "text",
      "text": "Hello! Claude here, from Anthropic. What can I help you with today — code, questions, writing, or something else?",
      "citations": []
    }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "stop_details": null,
  "context_management": {
    "applied_edits": []
  },
  "usage": {
    "input_tokens": xx,
    "cache_creation_input_tokens": xx,
    "cache_read_input_tokens": xx,
    "cache_creation": {
      "ephemeral_5m_input_tokens": xx,
      "ephemeral_1h_input_tokens": xx
    },
    "output_tokens": xx,
    "output_tokens_details": {
      "thinking_tokens": xx
    },
    "service_tier": "standard",
    "inference_geo": "not_available"
  }
}

Gemini generateContent

使用 Gemini generateContent 接口调用 Gemini 3.8 Flash。

macOS/Linux
export AIGOCODE_API_KEY="在这里填写你的 AIGoCode API Key"

curl "https://api.aigocode.app/v1beta/models/gemini-3.8-flash:generateContent?key=$AIGOCODE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [
          {
            "text": "Hello from AIGoCode!"
          }
        ]
      }
    ],
    "generationConfig": {
      "thinkingConfig": {
        "thinkingBudget": 0,
        "includeThoughts": false
      }
    }
  }'
Cmd
set "AIGOCODE_API_KEY=在这里填写你的 AIGoCode API Key"

curl.exe "https://api.aigocode.app/v1beta/models/gemini-3.8-flash:generateContent?key=%AIGOCODE_API_KEY%" ^
  -H "Content-Type: application/json" ^
  -d "{\"contents\":[{\"parts\":[{\"text\":\"Hello from AIGoCode!\"}]}],\"generationConfig\":{\"thinkingConfig\":{\"thinkingBudget\":0,\"includeThoughts\":false}}}"
PowerShell
$env:AIGOCODE_API_KEY = "在这里填写你的 AIGoCode API Key"

$body = @{
  contents = @(
    @{
      parts = @(
        @{
          text = "Hello from AIGoCode!"
        }
      )
    }
  )
  generationConfig = @{
    thinkingConfig = @{
      thinkingBudget = 0
      includeThoughts = $false
    }
  }
} | ConvertTo-Json -Depth 7

$response = Invoke-RestMethod `
  -Method Post `
  -Uri "https://api.aigocode.app/v1beta/models/gemini-3.8-flash:generateContent?key=$env:AIGOCODE_API_KEY" `
  -ContentType "application/json" `
  -Body $body

$response | ConvertTo-Json -Depth 10
Python
import json
from urllib.parse import quote
from urllib.request import Request, urlopen

api_key = "在这里填写你的 AIGoCode API Key"
url = (
    "https://api.aigocode.app/v1beta/models/"
    f"gemini-3.8-flash:generateContent?key={quote(api_key, safe='')}"
)
body = {
    "contents": [
        {
            "parts": [
                {
                    "text": "Hello from AIGoCode!",
                }
            ]
        }
    ],
    "generationConfig": {
        "thinkingConfig": {
            "thinkingBudget": 0,
            "includeThoughts": False,
        }
    },
}

request = Request(
    url,
    data=json.dumps(body).encode("utf-8"),
    headers={"Content-Type": "application/json"},
    method="POST",
)

with urlopen(request) as response:
    result = json.load(response)

print(json.dumps(result, ensure_ascii=False, indent=2))
Node.js
const apiKey = "在这里填写你的 AIGoCode API Key";
const url =
  "https://api.aigocode.app/v1beta/models/" +
  `gemini-3.8-flash:generateContent?key=${encodeURIComponent(apiKey)}`;

const response = await fetch(url, {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    contents: [
      {
        parts: [
          {
            text: "Hello from AIGoCode!",
          },
        ],
      },
    ],
    generationConfig: {
      thinkingConfig: {
        thinkingBudget: 0,
        includeThoughts: false,
      },
    },
  }),
});

const result = await response.json();

if (!response.ok) {
  throw new Error(JSON.stringify(result));
}

console.log(JSON.stringify(result, null, 2));

成功响应

以下是使用上面的请求体真实调用 gemini-3.8-flash 得到的响应。

response.json
{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "thoughtSignature": "xxx",
            "text": "Hello to the team at AIGoCode! 👋\n\nHow can I help you today? Whether you're working on code, brainstorming features, or tackling a tough technical problem, I'm ready to assist."
          }
        ]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": xx,
    "candidatesTokenCount": xx,
    "totalTokenCount": xx
  },
  "modelVersion": "gemini-3.8-flash",
  "responseId": "resp_xxx"
}

下一步

Base URL

AIGoCode 各兼容协议和常见客户端的服务地址

认证方式

AIGoCode API Key 的 Bearer Token 使用方式

On this page

OpenAI Compatible成功响应Claude Messages成功响应Gemini generateContent成功响应下一步