银河杂货铺 · AI 中转服务

OpenAI · Chat Completions

完整兼容 OpenAI Chat 接口，支持流式、工具调用、JSON Mode。推荐直接复用官方 SDK，只需覆写 `baseURL` 与密钥。

• 支持 `stream`、`response_format`、`parallel_tool_calls`

curl --request POST \
  --url https://api.glmbigmodel.me/v1/chat/completions \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful AI assistant."},
      {"role": "user", "content": "列出银河杂货铺提供的能力"}
    ],
    "temperature": 0.7,
    "stream": false
  }'

{
  "id": "chatcmpl-92b5",
  "object": "chat.completion",
  "created": 1763036400,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "..." },
      "finish_reason": "stop"
    }
  ],
  "usage": {"prompt_tokens": 56, "completion_tokens": 128, "total_tokens": 184},
}

OpenAI · Responses

OpenAI 最先进的模型响应接口。支持文本和图像输入，以及文本输出。创建与模型的有状态交互，将先前响应的输出用作输入。通过文件搜索、网络搜索、计算机使用等内置工具扩展模型的能力。使用函数调用允许模型访问外部系统和数据。 相关指南可参阅OpenAI官网

curl --request POST \
  --url https://api.glmbigmodel.me/v1/responses \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "o3-mini",
    "input": "一只啄木鸟能啄多少木头?",
    "reasoning": {
      "effort": "high"
    }
  }'

{
  "id": "resp_67ccd7eca01881908ff0b5146584e408072912b2993db808",
  "object": "response",
  "created_at": 1741477868,
  "status": "completed",
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "model": "o1-2024-12-17",
  "output": [
    {
      "type": "message",
      "id": "msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "这是一个源自英文绕口令"How much wood would a woodchuck chuck if a woodchuck could chuck wood"的问题。在现实中，啄木鸟(woodpecker)和土拨鼠(woodchuck)是不同的动物，而且土拨鼠实际上并不"啄(chuck)"木头。\n\n从科学角度看，啄木鸟每天确实会啄树木以寻找食物、建造巢穴或进行通讯。一只啄木鸟平均每天可能啄树约8000-12000次，视物种和具体目的而定。如果我们将这转换为木材量，假设每次啄击移除约0.1-0.2立方厘米的木材，那么一只啄木鸟理论上每天可能移除约800-2400立方厘米的木材。\n\n然而，啄木鸟主要是为了觅食和筑巢而啄木，而不是单纯地移除木材，所以这个计算只是一个有趣的理论估算。",
          "annotations": []
        }
      ]
    }
  ],
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "reasoning": {
    "effort": "high",
    "summary": null
  },
  "store": true,
  "temperature": 1.0,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "tool_choice": "auto",
  "tools": [],
  "top_p": 1.0,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 81,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 1035,
    "output_tokens_details": {
      "reasoning_tokens": 832
    },
    "total_tokens": 1116
  },
  "user": null,
  "metadata": {}
}

Anthropic · Messages

给定一组包含文本和/或图像内容的结构化输入消息列表，模型将生成对话中的下一条消息。Messages API 可用于单次查询或无状态的多轮对话。

curl --request POST \
  --url https://api.glmbigmodel.me/v1/anthropic/messages \
  --header "x-api-key: $NEWAPI_API_KEY" \
  --header "anthropic-version: 2023-06-01" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "claude-3-5-sonnet-20241022",
    "max_tokens": 1024,
    "messages": [
        {"role": "user", "content": "Hello, world"}
    ]
}'

{
  "content": [
    {
      "text": "Hi! My name is Claude.",
      "type": "text"
    }
  ],
  "id": "msg_013Zva2CMHLNnXjNJKqJ2EF",
  "model": "claude-3-5-sonnet-20241022", 
  "role": "assistant",
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "type": "message",
  "usage": {
    "input_tokens": 2095,
    "output_tokens": 503
  }
}

DeepSeek · Reasoning Content

Deepseek-reasoner 是 DeepSeek 推出的推理模型。在输出最终回答之前，模型会先输出一段思维链内容，以提升最终答案的准确性。API 向用户开放 deepseek-reasoner 思维链的内容，以供用户查看、展示、蒸馏使用。

curl --request POST \
  --url https://api.glmbigmodel.me/v1/chat/completions \
  --header "Authorization: Bearer $API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "deepseek-reasoner",
    "messages": [
      {
        "role": "user",
        "content": "9.11 and 9.8, which is greater?"
      }
    ],
    "max_tokens": 4096
  }'

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "deepseek-reasoner",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "reasoning_content": "让我一步步思考:\n1. 我们需要比较9.11和9.8的大小\n2. 两个数都是小数,我们可以直接比较\n3. 9.8 = 9.80\n4. 9.11 < 9.80\n5. 所以9.8更大",
      "content": "9.8 is greater than 9.11."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 15,
    "total_tokens": 25
  }
}

Google Gemini · Generate Content

Google Gemini API 支持使用图片、音频、代码、工具等生成内容。给定输入 GenerateContentRequest 生成模型响应。支持文本生成、视觉理解、音频处理、长上下文、代码执行、JSON 模式、函数调用等多种功能。

curl "https://api.glmbigmodel.me/v1beta/models/gemini-2.0-flash:generateContent?key=$API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[{"text": "Write a story about a magic backpack."}]
        }]
       }'

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [{"text": "..."}]
      },
      "safetyRatings": [...],
      "finishReason": "STOP"
    }
  ],
  "modelVersion": string,
  "responseId": string
}